linux-stable/kernel/entry/syscall_user_dispatch.c

165 lines
4.0 KiB
C
Raw Normal View History

kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2020 Collabora Ltd.
*/
#include <linux/sched.h>
#include <linux/prctl.h>
#include <linux/ptrace.h>
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
#include <linux/syscall_user_dispatch.h>
#include <linux/uaccess.h>
#include <linux/signal.h>
#include <linux/elf.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <asm/syscall.h>
#include "common.h"
static void trigger_sigsys(struct pt_regs *regs)
{
struct kernel_siginfo info;
clear_siginfo(&info);
info.si_signo = SIGSYS;
info.si_code = SYS_USER_DISPATCH;
info.si_call_addr = (void __user *)KSTK_EIP(current);
info.si_errno = 0;
info.si_arch = syscall_get_arch(current);
info.si_syscall = syscall_get_nr(current, regs);
force_sig_info(&info);
}
bool syscall_user_dispatch(struct pt_regs *regs)
{
struct syscall_user_dispatch *sd = &current->syscall_dispatch;
char state;
if (likely(instruction_pointer(regs) - sd->offset < sd->len))
return false;
if (unlikely(arch_syscall_is_vdso_sigreturn(regs)))
return false;
if (likely(sd->selector)) {
/*
* access_ok() is performed once, at prctl time, when
* the selector is loaded by userspace.
*/
exit/syscall_user_dispatch: Send ordinary signals on failure Use force_fatal_sig instead of calling do_exit directly. This ensures the ordinary signal handling path gets invoked, core dumps as appropriate get created, and for multi-threaded processes all of the threads are terminated not just a single thread. When asked Gabriel Krisman Bertazi <krisman@collabora.com> said [1]: > ebiederm@xmission.com (Eric W. Biederman) asked: > > > Why does do_syscal_user_dispatch call do_exit(SIGSEGV) and > > do_exit(SIGSYS) instead of force_sig(SIGSEGV) and force_sig(SIGSYS)? > > > > Looking at the code these cases are not expected to happen, so I would > > be surprised if userspace depends on any particular behaviour on the > > failure path so I think we can change this. > > Hi Eric, > > There is not really a good reason, and the use case that originated the > feature doesn't rely on it. > > Unless I'm missing yet another problem and others correct me, I think > it makes sense to change it as you described. > > > Is using do_exit in this way something you copied from seccomp? > > I'm not sure, its been a while, but I think it might be just that. The > first prototype of SUD was implemented as a seccomp mode. If at some point it becomes interesting we could relax "force_fatal_sig(SIGSEGV)" to instead say "force_sig_fault(SIGSEGV, SEGV_MAPERR, sd->selector)". I avoid doing that in this patch to avoid making it possible to catch currently uncatchable signals. Cc: Gabriel Krisman Bertazi <krisman@collabora.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> [1] https://lkml.kernel.org/r/87mtr6gdvi.fsf@collabora.com Link: https://lkml.kernel.org/r/20211020174406.17889-14-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2021-10-20 17:44:00 +00:00
if (unlikely(__get_user(state, sd->selector))) {
signal: Replace force_fatal_sig with force_exit_sig when in doubt Recently to prevent issues with SECCOMP_RET_KILL and similar signals being changed before they are delivered SA_IMMUTABLE was added. Unfortunately this broke debuggers[1][2] which reasonably expect to be able to trap synchronous SIGTRAP and SIGSEGV even when the target process is not configured to handle those signals. Add force_exit_sig and use it instead of force_fatal_sig where historically the code has directly called do_exit. This has the implementation benefits of going through the signal exit path (including generating core dumps) without the danger of allowing userspace to ignore or change these signals. This avoids userspace regressions as older kernels exited with do_exit which debuggers also can not intercept. In the future is should be possible to improve the quality of implementation of the kernel by changing some of these force_exit_sig calls to force_fatal_sig. That can be done where it matters on a case-by-case basis with careful analysis. Reported-by: Kyle Huey <me@kylehuey.com> Reported-by: kernel test robot <oliver.sang@intel.com> [1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com [2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020 Fixes: 00b06da29cf9 ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed") Fixes: a3616a3c0272 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die") Fixes: 83a1f27ad773 ("signal/powerpc: On swapcontext failure force SIGSEGV") Fixes: 9bc508cf0791 ("signal/s390: Use force_sigsegv in default_trap_handler") Fixes: 086ec444f866 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig") Fixes: c317d306d550 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails") Fixes: 695dd0d634df ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit") Fixes: 1fbd60df8a85 ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.") Fixes: 941edc5bf174 ("exit/syscall_user_dispatch: Send ordinary signals on failure") Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Tested-by: Kyle Huey <khuey@kylehuey.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2021-11-18 20:23:21 +00:00
force_exit_sig(SIGSEGV);
exit/syscall_user_dispatch: Send ordinary signals on failure Use force_fatal_sig instead of calling do_exit directly. This ensures the ordinary signal handling path gets invoked, core dumps as appropriate get created, and for multi-threaded processes all of the threads are terminated not just a single thread. When asked Gabriel Krisman Bertazi <krisman@collabora.com> said [1]: > ebiederm@xmission.com (Eric W. Biederman) asked: > > > Why does do_syscal_user_dispatch call do_exit(SIGSEGV) and > > do_exit(SIGSYS) instead of force_sig(SIGSEGV) and force_sig(SIGSYS)? > > > > Looking at the code these cases are not expected to happen, so I would > > be surprised if userspace depends on any particular behaviour on the > > failure path so I think we can change this. > > Hi Eric, > > There is not really a good reason, and the use case that originated the > feature doesn't rely on it. > > Unless I'm missing yet another problem and others correct me, I think > it makes sense to change it as you described. > > > Is using do_exit in this way something you copied from seccomp? > > I'm not sure, its been a while, but I think it might be just that. The > first prototype of SUD was implemented as a seccomp mode. If at some point it becomes interesting we could relax "force_fatal_sig(SIGSEGV)" to instead say "force_sig_fault(SIGSEGV, SEGV_MAPERR, sd->selector)". I avoid doing that in this patch to avoid making it possible to catch currently uncatchable signals. Cc: Gabriel Krisman Bertazi <krisman@collabora.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> [1] https://lkml.kernel.org/r/87mtr6gdvi.fsf@collabora.com Link: https://lkml.kernel.org/r/20211020174406.17889-14-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2021-10-20 17:44:00 +00:00
return true;
}
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW))
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
return false;
exit/syscall_user_dispatch: Send ordinary signals on failure Use force_fatal_sig instead of calling do_exit directly. This ensures the ordinary signal handling path gets invoked, core dumps as appropriate get created, and for multi-threaded processes all of the threads are terminated not just a single thread. When asked Gabriel Krisman Bertazi <krisman@collabora.com> said [1]: > ebiederm@xmission.com (Eric W. Biederman) asked: > > > Why does do_syscal_user_dispatch call do_exit(SIGSEGV) and > > do_exit(SIGSYS) instead of force_sig(SIGSEGV) and force_sig(SIGSYS)? > > > > Looking at the code these cases are not expected to happen, so I would > > be surprised if userspace depends on any particular behaviour on the > > failure path so I think we can change this. > > Hi Eric, > > There is not really a good reason, and the use case that originated the > feature doesn't rely on it. > > Unless I'm missing yet another problem and others correct me, I think > it makes sense to change it as you described. > > > Is using do_exit in this way something you copied from seccomp? > > I'm not sure, its been a while, but I think it might be just that. The > first prototype of SUD was implemented as a seccomp mode. If at some point it becomes interesting we could relax "force_fatal_sig(SIGSEGV)" to instead say "force_sig_fault(SIGSEGV, SEGV_MAPERR, sd->selector)". I avoid doing that in this patch to avoid making it possible to catch currently uncatchable signals. Cc: Gabriel Krisman Bertazi <krisman@collabora.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> [1] https://lkml.kernel.org/r/87mtr6gdvi.fsf@collabora.com Link: https://lkml.kernel.org/r/20211020174406.17889-14-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2021-10-20 17:44:00 +00:00
if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
signal: Replace force_fatal_sig with force_exit_sig when in doubt Recently to prevent issues with SECCOMP_RET_KILL and similar signals being changed before they are delivered SA_IMMUTABLE was added. Unfortunately this broke debuggers[1][2] which reasonably expect to be able to trap synchronous SIGTRAP and SIGSEGV even when the target process is not configured to handle those signals. Add force_exit_sig and use it instead of force_fatal_sig where historically the code has directly called do_exit. This has the implementation benefits of going through the signal exit path (including generating core dumps) without the danger of allowing userspace to ignore or change these signals. This avoids userspace regressions as older kernels exited with do_exit which debuggers also can not intercept. In the future is should be possible to improve the quality of implementation of the kernel by changing some of these force_exit_sig calls to force_fatal_sig. That can be done where it matters on a case-by-case basis with careful analysis. Reported-by: Kyle Huey <me@kylehuey.com> Reported-by: kernel test robot <oliver.sang@intel.com> [1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com [2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020 Fixes: 00b06da29cf9 ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed") Fixes: a3616a3c0272 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die") Fixes: 83a1f27ad773 ("signal/powerpc: On swapcontext failure force SIGSEGV") Fixes: 9bc508cf0791 ("signal/s390: Use force_sigsegv in default_trap_handler") Fixes: 086ec444f866 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig") Fixes: c317d306d550 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails") Fixes: 695dd0d634df ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit") Fixes: 1fbd60df8a85 ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.") Fixes: 941edc5bf174 ("exit/syscall_user_dispatch: Send ordinary signals on failure") Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Tested-by: Kyle Huey <khuey@kylehuey.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2021-11-18 20:23:21 +00:00
force_exit_sig(SIGSYS);
exit/syscall_user_dispatch: Send ordinary signals on failure Use force_fatal_sig instead of calling do_exit directly. This ensures the ordinary signal handling path gets invoked, core dumps as appropriate get created, and for multi-threaded processes all of the threads are terminated not just a single thread. When asked Gabriel Krisman Bertazi <krisman@collabora.com> said [1]: > ebiederm@xmission.com (Eric W. Biederman) asked: > > > Why does do_syscal_user_dispatch call do_exit(SIGSEGV) and > > do_exit(SIGSYS) instead of force_sig(SIGSEGV) and force_sig(SIGSYS)? > > > > Looking at the code these cases are not expected to happen, so I would > > be surprised if userspace depends on any particular behaviour on the > > failure path so I think we can change this. > > Hi Eric, > > There is not really a good reason, and the use case that originated the > feature doesn't rely on it. > > Unless I'm missing yet another problem and others correct me, I think > it makes sense to change it as you described. > > > Is using do_exit in this way something you copied from seccomp? > > I'm not sure, its been a while, but I think it might be just that. The > first prototype of SUD was implemented as a seccomp mode. If at some point it becomes interesting we could relax "force_fatal_sig(SIGSEGV)" to instead say "force_sig_fault(SIGSEGV, SEGV_MAPERR, sd->selector)". I avoid doing that in this patch to avoid making it possible to catch currently uncatchable signals. Cc: Gabriel Krisman Bertazi <krisman@collabora.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> [1] https://lkml.kernel.org/r/87mtr6gdvi.fsf@collabora.com Link: https://lkml.kernel.org/r/20211020174406.17889-14-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2021-10-20 17:44:00 +00:00
return true;
}
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
}
sd->on_dispatch = true;
syscall_rollback(current, regs);
trigger_sigsys(regs);
return true;
}
static int task_set_syscall_user_dispatch(struct task_struct *task, unsigned long mode,
unsigned long offset, unsigned long len,
char __user *selector)
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
{
switch (mode) {
case PR_SYS_DISPATCH_OFF:
if (offset || len || selector)
return -EINVAL;
break;
case PR_SYS_DISPATCH_ON:
/*
* Validate the direct dispatcher region just for basic
* sanity against overflow and a 0-sized dispatcher
* region. If the user is able to submit a syscall from
* an address, that address is obviously valid.
*/
if (offset && offset + len <= offset)
return -EINVAL;
/*
* access_ok() will clear memory tags for tagged addresses
* if current has memory tagging enabled.
* To enable a tracer to set a tracees selector the
* selector address must be untagged for access_ok(),
* otherwise an untagged tracer will always fail to set a
* tagged tracees selector.
*/
if (selector && !access_ok(untagged_addr(selector), sizeof(*selector)))
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
return -EFAULT;
break;
default:
return -EINVAL;
}
task->syscall_dispatch.selector = selector;
task->syscall_dispatch.offset = offset;
task->syscall_dispatch.len = len;
task->syscall_dispatch.on_dispatch = false;
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
if (mode == PR_SYS_DISPATCH_ON)
set_task_syscall_work(task, SYSCALL_USER_DISPATCH);
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
else
clear_task_syscall_work(task, SYSCALL_USER_DISPATCH);
kernel: Implement selective syscall userspace redirection Introduce a mechanism to quickly disable/enable syscall handling for a specific process and redirect to userspace via SIGSYS. This is useful for processes with parts that require syscall redirection and parts that don't, but who need to perform this boundary crossing really fast, without paying the cost of a system call to reconfigure syscall handling on each boundary transition. This is particularly important for Windows games running over Wine. The proposed interface looks like this: prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector]) The range [<offset>,<offset>+<length>) is a part of the process memory map that is allowed to by-pass the redirection code and dispatch syscalls directly, such that in fast paths a process doesn't need to disable the trap nor the kernel has to check the selector. This is essential to return from SIGSYS to a blocked area without triggering another SIGSYS from rt_sigreturn. selector is an optional pointer to a char-sized userspace memory region that has a key switch for the mechanism. This key switch is set to either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the redirection without calling the kernel. The feature is meant to be set per-thread and it is disabled on fork/clone/execv. Internally, this doesn't add overhead to the syscall hot path, and it requires very little per-architecture support. I avoided using seccomp, even though it duplicates some functionality, due to previous feedback that maybe it shouldn't mix with seccomp since it is not a security mechanism. And obviously, this should never be considered a security mechanism, since any part of the program can by-pass it by using the syscall dispatcher. For the sysinfo benchmark, which measures the overhead added to executing a native syscall that doesn't require interception, the overhead using only the direct dispatcher region to issue syscalls is pretty much irrelevant. The overhead of using the selector goes around 40ns for a native (unredirected) syscall in my system, and it is (as expected) dominated by the supervisor-mode user-address access. In fact, with SMAP off, the overhead is consistently less than 5ns on my test box. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
2020-11-27 19:32:34 +00:00
return 0;
}
int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
unsigned long len, char __user *selector)
{
return task_set_syscall_user_dispatch(current, mode, offset, len, selector);
}
int syscall_user_dispatch_get_config(struct task_struct *task, unsigned long size,
void __user *data)
{
struct syscall_user_dispatch *sd = &task->syscall_dispatch;
struct ptrace_sud_config cfg;
if (size != sizeof(cfg))
return -EINVAL;
if (test_task_syscall_work(task, SYSCALL_USER_DISPATCH))
cfg.mode = PR_SYS_DISPATCH_ON;
else
cfg.mode = PR_SYS_DISPATCH_OFF;
cfg.offset = sd->offset;
cfg.len = sd->len;
cfg.selector = (__u64)(uintptr_t)sd->selector;
if (copy_to_user(data, &cfg, sizeof(cfg)))
return -EFAULT;
return 0;
}
int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long size,
void __user *data)
{
struct ptrace_sud_config cfg;
if (size != sizeof(cfg))
return -EINVAL;
if (copy_from_user(&cfg, data, sizeof(cfg)))
return -EFAULT;
return task_set_syscall_user_dispatch(task, cfg.mode, cfg.offset, cfg.len,
(char __user *)(uintptr_t)cfg.selector);
}