diff mbox series

[RFT,v3,2/5] fork: Add shadow stack support to clone3()

Message ID 20231120-clone3-shadow-stack-v3-2-a7b8ed3e2acc@kernel.org
State New
Headers show
Series fork: Support shadow stacks in clone3() | expand

Commit Message

Mark Brown Nov. 20, 2023, 11:54 p.m. UTC 
Unlike with the normal stack there is no API for configuring the the shadow
stack for a new thread, instead the kernel will dynamically allocate a new
shadow stack with the same size as the normal stack. This appears to be due
to the shadow stack series having been in development since before the more
extensible clone3() was added rather than anything more deliberate.

Add a parameter to clone3() specifying the size of a shadow stack for
the newly created process.  If no shadow stack is specified then the
existing implicit allocation behaviour is maintained.

If the architecture does not support shadow stacks the shadow stack size
parameter must be zero, architectures that do support the feature are
expected to enforce the same requirement on individual systems that lack
shadow stack support.

Update the existing x86 implementation to pay attention to the newly added
arguments, in order to maintain compatibility we use the existing behaviour
if no shadow stack is specified. Minimal validation is done of the supplied
parameters, detailed enforcement is left to when the thread is executed.
Since we are now using more fields from the kernel_clone_args we pass that
into the shadow stack code rather than individual fields.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/x86/include/asm/shstk.h | 11 ++++++---
 arch/x86/kernel/process.c    |  2 +-
 arch/x86/kernel/shstk.c      | 59 ++++++++++++++++++++++++++++++--------------
 include/linux/sched/task.h   |  1 +
 include/uapi/linux/sched.h   |  4 +++
 kernel/fork.c                | 22 +++++++++++++++--
 6 files changed, 74 insertions(+), 25 deletions(-)

Comments

Mark Brown Nov. 23, 2023, 12:17 p.m. UTC | #1 
On Thu, Nov 23, 2023 at 11:28:47AM +0100, Christian Brauner wrote:
> On Mon, Nov 20, 2023 at 11:54:30PM +0000, Mark Brown wrote:

> Any reasonably maximum that should be assumed here? IOW, what happens if
> userspace starts specifying 4G shadow_stack_size with each clone3() call
> for lolz?

I guess we could impose RLIMIT_STACK?

> > +	} else {
> > +		/*
> > +		 * 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 (clone_flags & CLONE_VFORK) {
> > +			shstk->base = 0;
> > +			shstk->size = 0;
> > +			return 0;
> > +		}

> Why is the CLONE_VFORK handling only necessary if shadow_stack_size is
> unset? In general, a comment or explanation on the interaction between
> CLONE_VFORK and shadow_stack_size would be helpful.

This is the existing implicit behaviour that clone() has, it's current
ABI for x86.  The intent is that if the user has explicitly configured a
shadow stack then we just do whatever they asked us to do, if they
didn't we try to guess something sensible.  The comment at the top of
this block when where we check if shadow_stack_size is set is intended
to capture this requirement:

	/*
	 * If the user specified a shadow stack then do some basic
	 * validation and use it, otherwise fall back to a default
	 * shadow stack size if the clone_flags don't indicate an
	 * allocation is unneeded.
	 */
	if (args->shadow_stack_size) {
		size = args->shadow_stack_size;

		if (size < 8)
			return (unsigned long)ERR_PTR(-EINVAL);
	} else {

I'm not immediately seeing somewhere else to add something?
Christian Brauner Nov. 23, 2023, 4:33 p.m. UTC | #2 
On Thu, Nov 23, 2023 at 12:17:19PM +0000, Mark Brown wrote:
> On Thu, Nov 23, 2023 at 11:28:47AM +0100, Christian Brauner wrote:
> > On Mon, Nov 20, 2023 at 11:54:30PM +0000, Mark Brown wrote:
> 
> > Any reasonably maximum that should be assumed here? IOW, what happens if
> > userspace starts specifying 4G shadow_stack_size with each clone3() call
> > for lolz?
> 
> I guess we could impose RLIMIT_STACK?

Yeah, that also seems to be what acct_stack_growth() is using.

> 
> > > +	} else {
> > > +		/*
> > > +		 * 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 (clone_flags & CLONE_VFORK) {
> > > +			shstk->base = 0;
> > > +			shstk->size = 0;
> > > +			return 0;
> > > +		}
> 
> > Why is the CLONE_VFORK handling only necessary if shadow_stack_size is
> > unset? In general, a comment or explanation on the interaction between
> > CLONE_VFORK and shadow_stack_size would be helpful.
> 
> This is the existing implicit behaviour that clone() has, it's current
> ABI for x86.  The intent is that if the user has explicitly configured a
> shadow stack then we just do whatever they asked us to do, if they

So what I'm asking is: if the calling process is suspended until the
child exits or exec's does it make sense for the child to even get a
shadow stack? I don't know the answer which is why I'm asking.
diff mbox series

Patch

diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 42fee8959df7..8be7b0a909c3 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -6,6 +6,7 @@ 
 #include <linux/types.h>
 
 struct task_struct;
+struct kernel_clone_args;
 struct ksignal;
 
 #ifdef CONFIG_X86_USER_SHADOW_STACK
@@ -16,8 +17,8 @@  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);
+unsigned long shstk_alloc_thread_stack(struct task_struct *p,
+				       const struct kernel_clone_args *args);
 void shstk_free(struct task_struct *p);
 int setup_signal_shadow_stack(struct ksignal *ksig);
 int restore_signal_shadow_stack(void);
@@ -26,8 +27,10 @@  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 stack_size) { return 0; }
+						     const struct kernel_clone_args *args)
+{
+	return 0;
+}
 static inline void shstk_free(struct task_struct *p) {}
 static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
 static inline int restore_signal_shadow_stack(void) { return 0; }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b6f4e8399fca..a9ca80ea5056 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -207,7 +207,7 @@  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, args);
 	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 59e15dd8d0f8..a14f47d70dfb 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -191,38 +191,61 @@  void reset_thread_features(void)
 	current->thread.features_locked = 0;
 }
 
-unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags,
-				       unsigned long stack_size)
+unsigned long shstk_alloc_thread_stack(struct task_struct *tsk,
+				       const struct kernel_clone_args *args)
 {
 	struct thread_shstk *shstk = &tsk->thread.shstk;
+	unsigned long clone_flags = args->flags;
 	unsigned long addr, size;
 
 	/*
 	 * If shadow stack is not enabled on the new thread, skip any
-	 * switch to a new shadow stack.
+	 * implicit switch to a new shadow stack and reject attempts to
+	 * explciitly specify one.
 	 */
-	if (!features_enabled(ARCH_SHSTK_SHSTK))
-		return 0;
+	if (!features_enabled(ARCH_SHSTK_SHSTK)) {
+		if (args->shadow_stack_size)
+			return (unsigned long)ERR_PTR(-EINVAL);
 
-	/*
-	 * 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 (clone_flags & CLONE_VFORK) {
-		shstk->base = 0;
-		shstk->size = 0;
 		return 0;
 	}
 
 	/*
-	 * For !CLONE_VM the child will use a copy of the parents shadow
-	 * stack.
+	 * If the user specified a shadow stack then do some basic
+	 * validation and use it, otherwise fall back to a default
+	 * shadow stack size if the clone_flags don't indicate an
+	 * allocation is unneeded.
 	 */
-	if (!(clone_flags & CLONE_VM))
-		return 0;
+	if (args->shadow_stack_size) {
+		size = args->shadow_stack_size;
+
+		if (size < 8)
+			return (unsigned long)ERR_PTR(-EINVAL);
+	} else {
+		/*
+		 * 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 (clone_flags & CLONE_VFORK) {
+			shstk->base = 0;
+			shstk->size = 0;
+			return 0;
+		}
+
+		/*
+		 * For !CLONE_VM the child will use a copy of the
+		 * parents shadow stack.
+		 */
+		if (!(clone_flags & CLONE_VM))
+			return 0;
+
+		size = args->stack_size;
+
+	}
 
-	size = adjust_shstk_size(stack_size);
+	size = adjust_shstk_size(size);
 	addr = alloc_shstk(0, size, 0, false);
 	if (IS_ERR_VALUE(addr))
 		return addr;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..e86a09cfccd8 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -41,6 +41,7 @@  struct kernel_clone_args {
 	void *fn_arg;
 	struct cgroup *cgrp;
 	struct css_set *cset;
+	unsigned long shadow_stack_size;
 };
 
 /*
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..a998b6d0c897 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -84,6 +84,8 @@ 
  *                kernel's limit of nested PID namespaces.
  * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
  *                a file descriptor for the cgroup.
+ * @shadow_stack_size: Specify the size of the shadow stack to allocate
+ *                     for the child process.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -101,12 +103,14 @@  struct clone_args {
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
 	__aligned_u64 cgroup;
+	__aligned_u64 shadow_stack_size;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
 #define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
+#define CLONE_ARGS_SIZE_VER3 96 /* sizeof fourth published struct */
 
 /*
  * Scheduling policies
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..b8ca8194bca5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3067,7 +3067,9 @@  noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		     CLONE_ARGS_SIZE_VER1);
 	BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) !=
 		     CLONE_ARGS_SIZE_VER2);
-	BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2);
+	BUILD_BUG_ON(offsetofend(struct clone_args, shadow_stack_size) !=
+		     CLONE_ARGS_SIZE_VER3);
+	BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER3);
 
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
@@ -3110,6 +3112,7 @@  noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		.tls		= args.tls,
 		.set_tid_size	= args.set_tid_size,
 		.cgroup		= args.cgroup,
+		.shadow_stack_size	= args.shadow_stack_size,
 	};
 
 	if (args.set_tid &&
@@ -3150,6 +3153,21 @@  static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
 	return true;
 }
 
+/**
+ * clone3_shadow_stack_valid - check and prepare shadow stack
+ * @kargs: kernel clone args
+ *
+ * Verify that shadow stacks are only enabled if supported.
+ */
+static inline bool clone3_shadow_stack_valid(struct kernel_clone_args *kargs)
+{
+	if (!kargs->shadow_stack_size)
+		return true;
+
+	/* The architecture must check support on the specific machine */
+	return IS_ENABLED(CONFIG_ARCH_HAS_USER_SHADOW_STACK);
+}
+
 static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
 	/* Verify that no unknown flags are passed along. */
@@ -3172,7 +3190,7 @@  static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	    kargs->exit_signal)
 		return false;
 
-	if (!clone3_stack_valid(kargs))
+	if (!clone3_stack_valid(kargs) || !clone3_shadow_stack_valid(kargs))
 		return false;
 
 	return true;