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

123 lines
2.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Access to user system call parameters and results
*
* Copyright (C) 2008 Red Hat, Inc. All rights reserved.
*
* See asm-generic/syscall.h for descriptions of what we must do here.
*/
#ifndef _ASM_SYSCALL_H
#define _ASM_SYSCALL_H 1
#include <uapi/linux/audit.h>
#include <linux/sched.h>
#include <linux/thread_info.h>
powerpc: Provide syscall wrapper Implement syscall wrapper as per s390, x86, arm64. When enabled cause handlers to accept parameters from a stack frame rather than from user scratch register state. This allows for user registers to be safely cleared in order to reduce caller influence on speculation within syscall routine. The wrapper is a macro that emits syscall handler symbols that call into the target handler, obtaining its parameters from a struct pt_regs on the stack. As registers are already saved to the stack prior to calling system_call_exception, it appears that this function is executed more efficiently with the new stack-pointer convention than with parameters passed by registers, avoiding the allocation of a stack frame for this method. On a 32-bit system, we see >20% performance increases on the null_syscall microbenchmark, and on a Power 8 the performance gains amortise the cost of clearing and restoring registers which is implemented at the end of this series, seeing final result of ~5.6% performance improvement on null_syscall. Syscalls are wrapped in this fashion on all platforms except for the Cell processor as this commit does not provide SPU support. This can be quickly fixed in a successive patch, but requires spu_sys_callback to allocate a pt_regs structure to satisfy the wrapped calling convention. Co-developed-by: Andrew Donnellan <ajd@linux.ibm.com> Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com> Signed-off-by: Rohan McLure <rmclure@linux.ibm.com> Reviewed-by: Nicholas Piggin <npiggin@gmai.com> [mpe: Make incompatible with COMPAT to retain clearing of high bits of args] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20220921065605.1051927-22-rmclure@linux.ibm.com
2022-09-21 16:56:01 +10:00
#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
typedef long (*syscall_fn)(const struct pt_regs *);
#else
typedef long (*syscall_fn)(unsigned long, unsigned long, unsigned long,
unsigned long, unsigned long, unsigned long);
powerpc: Provide syscall wrapper Implement syscall wrapper as per s390, x86, arm64. When enabled cause handlers to accept parameters from a stack frame rather than from user scratch register state. This allows for user registers to be safely cleared in order to reduce caller influence on speculation within syscall routine. The wrapper is a macro that emits syscall handler symbols that call into the target handler, obtaining its parameters from a struct pt_regs on the stack. As registers are already saved to the stack prior to calling system_call_exception, it appears that this function is executed more efficiently with the new stack-pointer convention than with parameters passed by registers, avoiding the allocation of a stack frame for this method. On a 32-bit system, we see >20% performance increases on the null_syscall microbenchmark, and on a Power 8 the performance gains amortise the cost of clearing and restoring registers which is implemented at the end of this series, seeing final result of ~5.6% performance improvement on null_syscall. Syscalls are wrapped in this fashion on all platforms except for the Cell processor as this commit does not provide SPU support. This can be quickly fixed in a successive patch, but requires spu_sys_callback to allocate a pt_regs structure to satisfy the wrapped calling convention. Co-developed-by: Andrew Donnellan <ajd@linux.ibm.com> Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com> Signed-off-by: Rohan McLure <rmclure@linux.ibm.com> Reviewed-by: Nicholas Piggin <npiggin@gmai.com> [mpe: Make incompatible with COMPAT to retain clearing of high bits of args] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20220921065605.1051927-22-rmclure@linux.ibm.com
2022-09-21 16:56:01 +10:00
#endif
/* ftrace syscalls requires exporting the sys_call_table */
extern const syscall_fn sys_call_table[];
extern const syscall_fn compat_sys_call_table[];
static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
{
/*
* Note that we are returning an int here. That means 0xffffffff, ie.
* 32-bit negative 1, will be interpreted as -1 on a 64-bit kernel.
* This is important for seccomp so that compat tasks can set r0 = -1
* to reject the syscall.
*/
if (trap_is_syscall(regs))
return regs->gpr[0];
else
return -1;
}
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
regs->gpr[3] = regs->orig_gpr3;
}
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
if (trap_is_scv(regs)) {
unsigned long error = regs->gpr[3];
return IS_ERR_VALUE(error) ? error : 0;
} else {
/*
* If the system call failed,
* regs->gpr[3] contains a positive ERRORCODE.
*/
return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
}
}
static inline long syscall_get_return_value(struct task_struct *task,
struct pt_regs *regs)
{
return regs->gpr[3];
}
static inline void syscall_set_return_value(struct task_struct *task,
struct pt_regs *regs,
int error, long val)
{
if (trap_is_scv(regs)) {
regs->gpr[3] = (long) error ?: val;
} else {
/*
* In the general case it's not obvious that we must deal with
* CCR here, as the syscall exit path will also do that for us.
* However there are some places, eg. the signal code, which
* check ccr to decide if the value in r3 is actually an error.
*/
if (error) {
regs->ccr |= 0x10000000L;
regs->gpr[3] = error;
} else {
regs->ccr &= ~0x10000000L;
regs->gpr[3] = val;
}
}
}
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
unsigned long val, 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 16:26:37 -05:00
unsigned int n = 6;
if (is_tsk_32bit_task(task))
mask = 0xffffffff;
while (n--) {
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 16:26:37 -05:00
if (n == 0)
val = regs->orig_gpr3;
else
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 16:26:37 -05:00
val = regs->gpr[3 + n];
args[n] = val & mask;
}
}
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>
2019-03-18 02:30:18 +03:00
static inline int syscall_get_arch(struct task_struct *task)
{
if (is_tsk_32bit_task(task))
return AUDIT_ARCH_PPC;
else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
return AUDIT_ARCH_PPC64LE;
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>
2019-03-18 02:30:18 +03:00
else
return AUDIT_ARCH_PPC64;
}
#endif /* _ASM_SYSCALL_H */