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 --- include/linux/ptrace.h | 2 ++ include/uapi/linux/ptrace.h | 6 +++++- kernel/entry/syscall_user_dispatch.c | 5 +++++ kernel/ptrace.c | 5 +++++ 4 files changed, 17 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..f097c06224c9 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..a6ad815bd4be 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -370,6 +370,11 @@ 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)) { + if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTART)) + return -EINVAL; + } + if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP))

If a dispatch selector has been configured for Syscall User Dispatch, report Syscall User Dispath as configured in proc/status.

This provides an indicator to userland checkpoint/restart software that it must manage special signal conditions (similar to SECCOMP)

Signed-off-by: Gregory Price gregory.price@memverge.com --- fs/proc/array.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/proc/array.c b/fs/proc/array.c index 49283b8103c7..c85cdb4c137c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -428,6 +428,13 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) seq_printf(m, "THP_enabled:\t%d\n", thp_enabled); }

+static inline void task_syscall_user_dispatch(struct seq_file *m, + struct task_struct *p) +{ + seq_put_decimal_ull(m, "\nSyscall_user_dispatch:\t", + (p->syscall_dispatch.selector != NULL)); +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -451,6 +458,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); task_context_switch_counts(m, task); + task_syscall_user_dispatch(m, task); return 0; }

This patch implements simple getter interface for syscall user dispatch configuration info.

To support checkpoint/resume of a syscall user dispatch process, the prctl settings for syscall user dispatch must be fetchable. Presently, these settings are write-only, making it impossible to implement transparent checkpoint (coordination with the software is required).

As Syscall User Dispatch is explicitly not for secure-container development, exposing the configuration state via prctl does not violate the original design intent.

Signed-off-by: Gregory Price gregory.price@memverge.com --- .../admin-guide/syscall-user-dispatch.rst | 18 +++++++ include/linux/syscall_user_dispatch.h | 7 +++ include/uapi/linux/prctl.h | 3 ++ kernel/entry/syscall_user_dispatch.c | 14 +++++ kernel/sys.c | 4 ++ .../syscall_user_dispatch/sud_test.c | 54 +++++++++++++++++++ 6 files changed, 100 insertions(+)

diff --git a/Documentation/admin-guide/syscall-user-dispatch.rst b/Documentation/admin-guide/syscall-user-dispatch.rst index 60314953c728..8b2c8b6441b7 100644 --- a/Documentation/admin-guide/syscall-user-dispatch.rst +++ b/Documentation/admin-guide/syscall-user-dispatch.rst @@ -45,6 +45,10 @@ only the syscall dispatcher address and the userspace key. As the ABI of these intercepted syscalls is unknown to Linux, these syscalls are not instrumentable via ptrace or the syscall tracepoints.

+A getter interface is supplied for the purpose of userland +checkpoint/restore software being able to suspend and restore the +current state of the system. + Interface ---------

@@ -73,6 +77,20 @@ thread-wide, without the need to invoke the kernel directly. selector can be set to SYSCALL_DISPATCH_FILTER_ALLOW or SYSCALL_DISPATCH_FILTER_BLOCK. Any other value should terminate the program with a SIGSYS.

+ +A thread can fetch the current Syscall User Dispatch configuration with the following prctl: + + prctl(PR_GET_SYSCALL_USER_DISPATCH, <dispatch_config>)) + +<dispatch_config> is a pointer to a ``struct syscall_user_dispatch`` as defined in ``linux/include/linux/syscall_user_dispatch.h``:: + + struct syscall_user_dispatch { + char __user *selector; + unsigned long offset; + unsigned long len; + bool on_dispatch; + }; + Security Notes --------------

diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index a0ae443fb7df..aab25e5b6496 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -16,6 +16,7 @@ struct syscall_user_dispatch { bool on_dispatch; };

+int get_syscall_user_dispatch(struct syscall_user_dispatch __user *usd); int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector);

@@ -25,6 +26,12 @@ int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, #else struct syscall_user_dispatch {};

+static inline int get_syscall_user_dispatch( + struct syscall_user_dispatch __user *usd) +{ + return -EINVAL; +} + static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a5e06dcbba13..221c0e369cc0 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -284,4 +284,7 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0

+/* Get Syscall User Dispatch configuraiton settings */ +#define PR_GET_SYSCALL_USER_DISPATCH 65 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index f097c06224c9..71441664571a 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -73,6 +73,20 @@ bool syscall_user_dispatch(struct pt_regs *regs) return true; }

+int get_syscall_user_dispatch(struct syscall_user_dispatch __user *usd) +{ + struct syscall_user_dispatch *sd = &current->syscall_dispatch; + + if (usd) { + if (copy_to_user(usd, sd, sizeof(*sd))) + return -EFAULT; + } else { + return -EINVAL; + } + + return 0; +} + int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector) { diff --git a/kernel/sys.c b/kernel/sys.c index 5fd54bf0e886..b762c49fc424 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2618,6 +2618,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = set_syscall_user_dispatch(arg2, arg3, arg4, (char __user *) arg5); break; + case PR_GET_SYSCALL_USER_DISPATCH: + error = get_syscall_user_dispatch( + (struct syscall_user_dispatch __user *) arg2); + break; #ifdef CONFIG_SCHED_CORE case PR_SCHED_CORE: error = sched_core_share_pid(arg2, arg3, arg4, arg5); diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index b5d592d4099e..555912f3c192 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -35,6 +35,16 @@ #define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK) #define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW)

+#ifndef PR_GET_SYSCALL_USER_DISPATCH +#define PR_GET_SYSCALL_USER_DISPATCH 65 +#endif +struct syscall_user_dispatch { + char *selector; + unsigned long offset; + unsigned long len; + bool on_dispatch; +}; + /* Test Summary: * * - dispatch_trigger_sigsys: Verify if PR_SET_SYSCALL_USER_DISPATCH is @@ -309,4 +319,48 @@ TEST(direct_dispatch_range) } }

+ +TEST(get_dispatch_settings) +{ + int ret = 0; + struct syscall_user_dispatch usd; + + glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW; + + /* Check the negative paths - bad user pointer */ + ret = prctl(PR_GET_SYSCALL_USER_DISPATCH, NULL); + ASSERT_EQ(-1, ret) { + TH_LOG("Kernel reported success to accessing a NULL pointer"); + } + ASSERT_EQ(EINVAL, errno); + + /* Get the settings prior to it being activated */ + ret = prctl(PR_GET_SYSCALL_USER_DISPATCH, &usd); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel failed to fetch syscall user dispatch settings"); + } + + /* Make sure selector is off prior to prctl. */ + SYSCALL_DISPATCH_OFF(glob_sel); + ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0L, &glob_sel); + ASSERT_EQ(0, ret) { + TH_LOG("Failed to get Syscall User Dispatch settings"); + } + + /* sanity check the settings */ + ret = prctl(PR_GET_SYSCALL_USER_DISPATCH, &usd); + ASSERT_EQ(0, ret) { + TH_LOG("Failed to get Syscall User Dispatch settings"); + } + ASSERT_EQ(&glob_sel, usd.selector) { + TH_LOG("Selector is an unexpected pointer"); + } + ASSERT_EQ(0, usd.offset) { + TH_LOG("Offset is an unexpected value"); + } + ASSERT_EQ(0, usd.len) { + TH_LOG("Length is an unexpected value"); + } +} + TEST_HARNESS_MAIN