[PATCH v3 1/3] ptrace,syscall_user_dispatch: Implement Syscall User Dispatch Suspension

[Gregory Price <gourry.memverge@xxxxxxxxx>]

Adds PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH to ptrace options, and
modify Syscall User Dispatch to suspend interception when enabled.

This is modeled after the SUSPEND_SECCOMP feature, which suspends
SECCOMP interposition.  Without doing this, software like CRIU will
inject system calls into a process and be intercepted by Syscall
User Dispatch, either causing a crash (due to blocked signals) or
the delivery of those signals to a ptracer (not the intended behavior).

Since Syscall User Dispatch is not a privileged feature, a check
for permissions is not required, however attempting to set this
option when CONFIG_CHECKPOINT_RESTORE it not supported should be
disallowed, as its intended use is checkpoint/resume.

Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 include/linux/ptrace.h               | 2 ++
 include/uapi/linux/ptrace.h          | 6 +++++-
 kernel/entry/syscall_user_dispatch.c | 5 +++++
 kernel/ptrace.c                      | 4 ++++
 4 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eaaef3ffec22..461ae5c99d57 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -45,6 +45,8 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 
 #define PT_EXITKILL		(PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
 #define PT_SUSPEND_SECCOMP	(PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT)
+#define PT_SUSPEND_SYSCALL_USER_DISPATCH \
+	(PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH << PT_OPT_FLAG_SHIFT)
 
 extern long arch_ptrace(struct task_struct *child, long request,
 			unsigned long addr, unsigned long data);
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index 195ae64a8c87..ba9e3f19a22c 100644
--- a/include/uapi/linux/ptrace.h
+++ b/include/uapi/linux/ptrace.h
@@ -146,9 +146,13 @@ struct ptrace_rseq_configuration {
 /* eventless options */
 #define PTRACE_O_EXITKILL		(1 << 20)
 #define PTRACE_O_SUSPEND_SECCOMP	(1 << 21)
+#define PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH	(1 << 22)
 
 #define PTRACE_O_MASK		(\
-	0x000000ff | PTRACE_O_EXITKILL | PTRACE_O_SUSPEND_SECCOMP)
+	0x000000ff | \
+	PTRACE_O_EXITKILL | \
+	PTRACE_O_SUSPEND_SECCOMP | \
+	PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH)
 
 #include <asm/ptrace.h>
 
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 0b6379adff6b..b5ec75164805 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -8,6 +8,7 @@
 #include <linux/uaccess.h>
 #include <linux/signal.h>
 #include <linux/elf.h>
+#include <linux/ptrace.h>
 
 #include <linux/sched/signal.h>
 #include <linux/sched/task_stack.h>
@@ -36,6 +37,10 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 	struct syscall_user_dispatch *sd = &current->syscall_dispatch;
 	char state;
 
+	if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) &&
+	    unlikely(current->ptrace & PT_SUSPEND_SYSCALL_USER_DISPATCH))
+		return false;
+
 	if (likely(instruction_pointer(regs) - sd->offset < sd->len))
 		return false;
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54482193e1ed..99467ba5f55b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -370,6 +370,10 @@ static int check_ptrace_options(unsigned long data)
 	if (data & ~(unsigned long)PTRACE_O_MASK)
 		return -EINVAL;
 
+	if (unlikely(data & PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH) &&
+	    (!IS_ENABLED(CONFIG_CHECKPOINT_RESTART)))
+			return -EINVAL;
+
 	if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
 		if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
 		    !IS_ENABLED(CONFIG_SECCOMP))
-- 
2.39.0