Files
Linus Torvalds 3424d8c18a Merge tag 'core-entry-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull generic entry code updates from Thomas Gleixner:

 - Make syscall user dispatching configurable

   Not all architectures can makes use of syscall user dispatching.
   Allow them to disable the feature completely.

 - Consolidate stack randomization for the generic entry code and the
   architectures using it.

   Stack randomization on syscall entry was sprinkled throughout the
   architecture specific low level entry code and in some cases at the
   wrong points, e.g. before establishing state, which violates the
   non-instrumentable constraints of that code.

   Clean this up by integrating stack randomization into the generic
   entry code helpers so that it is invoked at the earliest possible
   point right after establishing state and converting all generic entry
   code using architecture over.

 - Clean up the syscall number handling in the generic entry code. It
   works correctly for architectures which have a separate return value
   storage in pt_regs, but fails to distinguish the case where user
   space handed in -1 as syscall number from the case where the entry
   code rejects it by returning -1 to the callers. Aside of that the
   return value functionality of those interfaces is not really
   intuitive.

   Fix this by separating the decision to reject a syscall (user
   dispatch, ptrace, seccomp ...) from the potential modification of the
   syscall number through these mechanisms.

   This solves most of the problems for architectures which do not have
   a separate return value storage in pt_regs except for the case where
   a tracepoint has a BPF script or a probe attached which overwrite
   both the syscall number and the return value. But that's a problem
   which cannot be solved in the generic code, that only can be
   addressed by separating the storage model in the affected
   architectures.

* tag 'core-entry-2026-08-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  entry, treewide: Make syscall_enter_from_user_mode[_work]() indicate syscall execution
  entry: Make return type of syscall_trace_enter() bool
  entry: Rework trace_syscall_enter()
  entry: Rework syscall_audit_enter()
  syscall_user_dispatch: Introduce ARCH_SUPPORTS_SYSCALL_USER_DISPATCH
  entry: Fix seccomp bypass after ptrace with TSYNC
  x86/entry: Simplify the syscall number logic
  x86/entry: Get rid of the sys_ni_syscall() indirection
  x86/entry: Make syscall functions static
  ptrace, treewide: Rename ptrace_report_syscall_entry() to ptrace_report_syscall_permit_entry()
  seccomp, treewide: Rename and convert __secure_computing() to return boolean
  entry: Use syscall number instead of rereading it
  entry: Remove syscall_enter_from_user_mode()
  x86/syscall: Use [syscall_]enter_from_user_mode_randomize_stack()
  s390/syscall: Use enter_from_user_mode_randomize_stack()
  riscv/syscall: Use syscall_enter_from_user_mode_randomize_stack()
  powerpc/syscall: Use syscall_enter_from_user_mode_randomize_stack()
  loongarch/syscall: Use syscall_enter_from_user_mode_randomize_stack()
  entry: Provide [syscall_]enter_from_user_mode_randomize_stack()
  randomize_kstack: Provide add_random_kstack_offset_irqsoff()
  ...
2026-08-18 15:00:56 -07:00

149 lines
3.8 KiB
C

/* 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>
#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);
#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_set_nr(struct task_struct *task, struct pt_regs *regs, int nr)
{
/*
* Unlike syscall_get_nr(), syscall_set_nr() can be called only when
* the target task is stopped for tracing on entering syscall, so
* there is no need to have the same check syscall_get_nr() has.
*/
regs->gpr[0] = nr;
}
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;
}
}
/*
* Mark that a return value has been explicitly set by seccomp or
* ptrace so that system_call_exception() can skip the syscall
* unconditionally, even when the user requested syscall(-1).
*/
set_thread_flag(TIF_SYSCALL_RET);
}
static inline void syscall_get_arguments(struct task_struct *task,
struct pt_regs *regs,
unsigned long *args)
{
unsigned long val, mask = -1UL;
unsigned int n = 6;
if (is_tsk_32bit_task(task))
mask = 0xffffffff;
while (n--) {
if (n == 0)
val = regs->orig_gpr3;
else
val = regs->gpr[3 + n];
args[n] = val & mask;
}
}
static inline void syscall_set_arguments(struct task_struct *task,
struct pt_regs *regs,
const unsigned long *args)
{
memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
/* Also copy the first argument into orig_gpr3 */
regs->orig_gpr3 = args[0];
}
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;
else
return AUDIT_ARCH_PPC64;
}
#endif /* _ASM_SYSCALL_H */