linux/arch/s390/include/asm/syscall.h

108 lines
2.4 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Access to user system call parameters and results
*
* Copyright IBM Corp. 2008
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
*/
#ifndef _ASM_SYSCALL_H
#define _ASM_SYSCALL_H 1
#include <uapi/linux/audit.h>
#include <linux/sched.h>
[S390] signal race with restarting system calls For a ERESTARTNOHAND/ERESTARTSYS/ERESTARTNOINTR restarting system call do_signal will prepare the restart of the system call with a rewind of the PSW before calling get_signal_to_deliver (where the debugger might take control). For A ERESTART_RESTARTBLOCK restarting system call do_signal will set -EINTR as return code. There are two issues with this approach: 1) strace never sees ERESTARTNOHAND, ERESTARTSYS, ERESTARTNOINTR or ERESTART_RESTARTBLOCK as the rewinding already took place or the return code has been changed to -EINTR 2) if get_signal_to_deliver does not return with a signal to deliver the restart via the repeat of the svc instruction is left in place. This opens a race if another signal is made pending before the system call instruction can be reexecuted. The original system call will be restarted even if the second signal would have ended the system call with -EINTR. These two issues can be solved by dropping the early rewind of the system call before get_signal_to_deliver has been called and by using the TIF_RESTART_SVC magic to do the restart if no signal has to be delivered. The only situation where the system call restart via the repeat of the svc instruction is appropriate is when a SA_RESTART signal is delivered to user space. Unfortunately this breaks inferior calls by the debugger again. The system call number and the length of the system call instruction is lost over the inferior call and user space will see ERESTARTNOHAND/ ERESTARTSYS/ERESTARTNOINTR/ERESTART_RESTARTBLOCK. To correct this a new ptrace interface is added to save/restore the system call number and system call instruction length. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2011-10-30 14:16:47 +00:00
#include <linux/err.h>
#include <asm/ptrace.h>
s390: convert to generic entry This patch converts s390 to use the generic entry infrastructure from kernel/entry/*. There are a few special things on s390: - PIF_PER_TRAP is moved to TIF_PER_TRAP as the generic code doesn't know about our PIF flags in exit_to_user_mode_loop(). - The old code had several ways to restart syscalls: a) PIF_SYSCALL_RESTART, which was only set during execve to force a restart after upgrading a process (usually qemu-kvm) to pgste page table extensions. b) PIF_SYSCALL, which is set by do_signal() to indicate that the current syscall should be restarted. This is changed so that do_signal() now also uses PIF_SYSCALL_RESTART. Continuing to use PIF_SYSCALL doesn't work with the generic code, and changing it to PIF_SYSCALL_RESTART makes PIF_SYSCALL and PIF_SYSCALL_RESTART more unique. - On s390 calling sys_sigreturn or sys_rt_sigreturn is implemented by executing a svc instruction on the process stack which causes a fault. While handling that fault the fault code sets PIF_SYSCALL to hand over processing to the syscall code on exit to usermode. The patch introduces PIF_SYSCALL_RET_SET, which is set if ptrace sets a return value for a syscall. The s390x ptrace ABI uses r2 both for the syscall number and return value, so ptrace cannot set the syscall number + return value at the same time. The flag makes handling that a bit easier. do_syscall() will just skip executing the syscall if PIF_SYSCALL_RET_SET is set. CONFIG_DEBUG_ASCE was removd in favour of the generic CONFIG_DEBUG_ENTRY. CR1/7/13 will be checked both on kernel entry and exit to contain the correct asces. Signed-off-by: Sven Schnelle <svens@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2020-11-21 10:14:56 +00:00
extern const sys_call_ptr_t sys_call_table[];
extern const sys_call_ptr_t sys_call_table_emu[];
static inline long syscall_get_nr(struct task_struct *task,
struct pt_regs *regs)
{
return test_pt_regs_flag(regs, PIF_SYSCALL) ?
(regs->int_code & 0xffff) : -1;
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
regs->gprs[2] = regs->orig_gpr2;
}
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
unsigned long error = regs->gprs[2];
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT)) {
/*
* Sign-extend the value so (int)-EFOO becomes (long)-EFOO
* and will match correctly in comparisons.
*/
error = (long)(int)error;
}
#endif
return IS_ERR_VALUE(error) ? error : 0;
}
static inline long syscall_get_return_value(struct task_struct *task,
struct pt_regs *regs)
{
return regs->gprs[2];
}
static inline void syscall_set_return_value(struct task_struct *task,
struct pt_regs *regs,
int error, long val)
{
s390: convert to generic entry This patch converts s390 to use the generic entry infrastructure from kernel/entry/*. There are a few special things on s390: - PIF_PER_TRAP is moved to TIF_PER_TRAP as the generic code doesn't know about our PIF flags in exit_to_user_mode_loop(). - The old code had several ways to restart syscalls: a) PIF_SYSCALL_RESTART, which was only set during execve to force a restart after upgrading a process (usually qemu-kvm) to pgste page table extensions. b) PIF_SYSCALL, which is set by do_signal() to indicate that the current syscall should be restarted. This is changed so that do_signal() now also uses PIF_SYSCALL_RESTART. Continuing to use PIF_SYSCALL doesn't work with the generic code, and changing it to PIF_SYSCALL_RESTART makes PIF_SYSCALL and PIF_SYSCALL_RESTART more unique. - On s390 calling sys_sigreturn or sys_rt_sigreturn is implemented by executing a svc instruction on the process stack which causes a fault. While handling that fault the fault code sets PIF_SYSCALL to hand over processing to the syscall code on exit to usermode. The patch introduces PIF_SYSCALL_RET_SET, which is set if ptrace sets a return value for a syscall. The s390x ptrace ABI uses r2 both for the syscall number and return value, so ptrace cannot set the syscall number + return value at the same time. The flag makes handling that a bit easier. do_syscall() will just skip executing the syscall if PIF_SYSCALL_RET_SET is set. CONFIG_DEBUG_ASCE was removd in favour of the generic CONFIG_DEBUG_ENTRY. CR1/7/13 will be checked both on kernel entry and exit to contain the correct asces. Signed-off-by: Sven Schnelle <svens@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2020-11-21 10:14:56 +00:00
set_pt_regs_flag(regs, PIF_SYSCALL_RET_SET);
regs->gprs[2] = error ? error : val;
}
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
unsigned long mask = -1UL;
syscalls: Remove start and number from syscall_get_arguments() args At Linux Plumbers, Andy Lutomirski approached me and pointed out that the function call syscall_get_arguments() implemented in x86 was horribly written and not optimized for the standard case of passing in 0 and 6 for the starting index and the number of system calls to get. When looking at all the users of this function, I discovered that all instances pass in only 0 and 6 for these arguments. Instead of having this function handle different cases that are never used, simply rewrite it to return the first 6 arguments of a system call. This should help out the performance of tracing system calls by ptrace, ftrace and perf. Link: http://lkml.kernel.org/r/20161107213233.754809394@goodmis.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Dave Martin <dave.martin@arm.com> Cc: "Dmitry V. Levin" <ldv@altlinux.org> Cc: x86@kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts Acked-by: Max Filippov <jcmvbkbc@gmail.com> # For xtensa changes Acked-by: Will Deacon <will.deacon@arm.com> # For the arm64 bits Reviewed-by: Thomas Gleixner <tglx@linutronix.de> # for x86 Reviewed-by: Dmitry V. Levin <ldv@altlinux.org> Reported-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-11-07 21:26:37 +00:00
unsigned int n = 6;
#ifdef CONFIG_COMPAT
if (test_tsk_thread_flag(task, TIF_31BIT))
mask = 0xffffffff;
#endif
while (n-- > 0)
syscalls: Remove start and number from syscall_get_arguments() args At Linux Plumbers, Andy Lutomirski approached me and pointed out that the function call syscall_get_arguments() implemented in x86 was horribly written and not optimized for the standard case of passing in 0 and 6 for the starting index and the number of system calls to get. When looking at all the users of this function, I discovered that all instances pass in only 0 and 6 for these arguments. Instead of having this function handle different cases that are never used, simply rewrite it to return the first 6 arguments of a system call. This should help out the performance of tracing system calls by ptrace, ftrace and perf. Link: http://lkml.kernel.org/r/20161107213233.754809394@goodmis.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Dave Martin <dave.martin@arm.com> Cc: "Dmitry V. Levin" <ldv@altlinux.org> Cc: x86@kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts Acked-by: Max Filippov <jcmvbkbc@gmail.com> # For xtensa changes Acked-by: Will Deacon <will.deacon@arm.com> # For the arm64 bits Reviewed-by: Thomas Gleixner <tglx@linutronix.de> # for x86 Reviewed-by: Dmitry V. Levin <ldv@altlinux.org> Reported-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-11-07 21:26:37 +00:00
if (n > 0)
args[n] = regs->gprs[2 + n] & mask;
args[0] = regs->orig_gpr2 & mask;
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
const unsigned long *args)
{
syscalls: Remove start and number from syscall_set_arguments() args After removing the start and count arguments of syscall_get_arguments() it seems reasonable to remove them from syscall_set_arguments(). Note, as of today, there are no users of syscall_set_arguments(). But we are told that there will be soon. But for now, at least make it consistent with syscall_get_arguments(). Link: http://lkml.kernel.org/r/20190327222014.GA32540@altlinux.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Dave Martin <dave.martin@arm.com> Cc: "Dmitry V. Levin" <ldv@altlinux.org> Cc: x86@kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Acked-by: Max Filippov <jcmvbkbc@gmail.com> # For xtensa changes Acked-by: Will Deacon <will.deacon@arm.com> # For the arm64 bits Reviewed-by: Thomas Gleixner <tglx@linutronix.de> # for x86 Reviewed-by: Dmitry V. Levin <ldv@altlinux.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2019-03-28 00:07:31 +00:00
unsigned int n = 6;
while (n-- > 0)
syscalls: Remove start and number from syscall_set_arguments() args After removing the start and count arguments of syscall_get_arguments() it seems reasonable to remove them from syscall_set_arguments(). Note, as of today, there are no users of syscall_set_arguments(). But we are told that there will be soon. But for now, at least make it consistent with syscall_get_arguments(). Link: http://lkml.kernel.org/r/20190327222014.GA32540@altlinux.org Cc: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Dave Martin <dave.martin@arm.com> Cc: "Dmitry V. Levin" <ldv@altlinux.org> Cc: x86@kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Acked-by: Max Filippov <jcmvbkbc@gmail.com> # For xtensa changes Acked-by: Will Deacon <will.deacon@arm.com> # For the arm64 bits Reviewed-by: Thomas Gleixner <tglx@linutronix.de> # for x86 Reviewed-by: Dmitry V. Levin <ldv@altlinux.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2019-03-28 00:07:31 +00:00
if (n > 0)
regs->gprs[2 + n] = args[n];
regs->orig_gpr2 = args[0];
}
syscall_get_arch: add "struct task_struct *" argument This argument is required to extend the generic ptrace API with PTRACE_GET_SYSCALL_INFO request: syscall_get_arch() is going to be called from ptrace_request() along with syscall_get_nr(), syscall_get_arguments(), syscall_get_error(), and syscall_get_return_value() functions with a tracee as their argument. The primary intent is that the triple (audit_arch, syscall_nr, arg1..arg6) should describe what system call is being called and what its arguments are. Reverts: 5e937a9ae913 ("syscall_get_arch: remove useless function arguments") Reverts: 1002d94d3076 ("syscall.h: fix doc text for syscall_get_arch()") Reviewed-by: Andy Lutomirski <luto@kernel.org> # for x86 Reviewed-by: Palmer Dabbelt <palmer@sifive.com> Acked-by: Paul Moore <paul@paul-moore.com> Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Acked-by: Kees Cook <keescook@chromium.org> # seccomp parts Acked-by: Mark Salter <msalter@redhat.com> # for the c6x bit Cc: Elvira Khabirova <lineprinter@altlinux.org> Cc: Eugene Syromyatnikov <esyr@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: x86@kernel.org Cc: linux-alpha@vger.kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Cc: linux-audit@redhat.com Signed-off-by: Dmitry V. Levin <ldv@altlinux.org> Signed-off-by: Paul Moore <paul@paul-moore.com>
2019-03-17 23:30:18 +00:00
static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_COMPAT
syscall_get_arch: add "struct task_struct *" argument This argument is required to extend the generic ptrace API with PTRACE_GET_SYSCALL_INFO request: syscall_get_arch() is going to be called from ptrace_request() along with syscall_get_nr(), syscall_get_arguments(), syscall_get_error(), and syscall_get_return_value() functions with a tracee as their argument. The primary intent is that the triple (audit_arch, syscall_nr, arg1..arg6) should describe what system call is being called and what its arguments are. Reverts: 5e937a9ae913 ("syscall_get_arch: remove useless function arguments") Reverts: 1002d94d3076 ("syscall.h: fix doc text for syscall_get_arch()") Reviewed-by: Andy Lutomirski <luto@kernel.org> # for x86 Reviewed-by: Palmer Dabbelt <palmer@sifive.com> Acked-by: Paul Moore <paul@paul-moore.com> Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Acked-by: Kees Cook <keescook@chromium.org> # seccomp parts Acked-by: Mark Salter <msalter@redhat.com> # for the c6x bit Cc: Elvira Khabirova <lineprinter@altlinux.org> Cc: Eugene Syromyatnikov <esyr@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: x86@kernel.org Cc: linux-alpha@vger.kernel.org Cc: linux-snps-arc@lists.infradead.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: uclinux-h8-devel@lists.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-mips@vger.kernel.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-riscv@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: sparclinux@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-arch@vger.kernel.org Cc: linux-audit@redhat.com Signed-off-by: Dmitry V. Levin <ldv@altlinux.org> Signed-off-by: Paul Moore <paul@paul-moore.com>
2019-03-17 23:30:18 +00:00
if (test_tsk_thread_flag(task, TIF_31BIT))
return AUDIT_ARCH_S390;
#endif
return AUDIT_ARCH_S390X;
}
s390: convert to generic entry This patch converts s390 to use the generic entry infrastructure from kernel/entry/*. There are a few special things on s390: - PIF_PER_TRAP is moved to TIF_PER_TRAP as the generic code doesn't know about our PIF flags in exit_to_user_mode_loop(). - The old code had several ways to restart syscalls: a) PIF_SYSCALL_RESTART, which was only set during execve to force a restart after upgrading a process (usually qemu-kvm) to pgste page table extensions. b) PIF_SYSCALL, which is set by do_signal() to indicate that the current syscall should be restarted. This is changed so that do_signal() now also uses PIF_SYSCALL_RESTART. Continuing to use PIF_SYSCALL doesn't work with the generic code, and changing it to PIF_SYSCALL_RESTART makes PIF_SYSCALL and PIF_SYSCALL_RESTART more unique. - On s390 calling sys_sigreturn or sys_rt_sigreturn is implemented by executing a svc instruction on the process stack which causes a fault. While handling that fault the fault code sets PIF_SYSCALL to hand over processing to the syscall code on exit to usermode. The patch introduces PIF_SYSCALL_RET_SET, which is set if ptrace sets a return value for a syscall. The s390x ptrace ABI uses r2 both for the syscall number and return value, so ptrace cannot set the syscall number + return value at the same time. The flag makes handling that a bit easier. do_syscall() will just skip executing the syscall if PIF_SYSCALL_RET_SET is set. CONFIG_DEBUG_ASCE was removd in favour of the generic CONFIG_DEBUG_ENTRY. CR1/7/13 will be checked both on kernel entry and exit to contain the correct asces. Signed-off-by: Sven Schnelle <svens@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2020-11-21 10:14:56 +00:00
static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
{
return false;
}
#endif /* _ASM_SYSCALL_H */