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@memverge.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
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 = ¤t->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))
--
2.39.0Hi Gregory, I'll try to read this series next Monday, I need to recall what does syscall-user-dispatch actually do ;) just one question for now, On 01/20, Gregory Price wrote: > > --- 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; Hmm? git grep CHECKPOINT_RESTART shows nothing. Oleg.
On Fri, Jan 20, 2023 at 04:22:51PM +0100, Oleg Nesterov wrote:
> Hi Gregory,
>
> I'll try to read this series next Monday, I need to recall what does
> syscall-user-dispatch actually do ;)
>
> just one question for now,
>
> On 01/20, Gregory Price wrote:
> >
> > --- 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;
>
> Hmm? git grep CHECKPOINT_RESTART shows nothing.
>
> Oleg.
>
TIL the mailing lists don't like responses from proxy addresses.
Resending response to it goes out to everyone
Good catch, I always mixup RESTART/RESTORE. This should be RESTORE
Adjusted patch below, will send a v4 tomorrow so as not to spam the
lists. Attached an updated patch for the time being.
(brief syscall user dispatch overview)
syscall-user-dispatch is relatively simple, the goal is to implement
syscall interposition for foreign syscalls (windows, non-posix,
whatever). Since the ABI of these syscalls can't be trusted to be
anything like linux, syscall dispatch produces a SIGSYS before anything
else can do things like check register values.
How to use
1) User registers a SIGSYS signal handler
2) User does
prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON,
<address>, <length>, char* selector)
3) All 'syscall' instructions *outside* the virtual address range
(address, address+length) now produce a SIGSYS on the thread that
executed the syscall.
<selector> can be set to SYSCALL_DISPATCH_FILTER_ALLOW or
SYSCALL_DISPATCH_FILTER_BLOCK to enable/disable this signal
production from userland without having to make kernel calls.
docs: https://docs.kernel.org/admin-guide/syscall-user-dispatch.html
Updated patch
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 = ¤t->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..a348b68d07a2 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_RESTORE)))
+ return -EINVAL;
+
if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) ||
!IS_ENABLED(CONFIG_SECCOMP))
© 2016 - 2025 Red Hat, Inc.