s390/syscall: Merge __do_syscall() and do_syscall()

The compiler inlines do_syscall() into __do_syscall(). Therefore do this in
C code as well, since this makes the code easier to understand.

Also adjust and add various unlikely() and likely() annotations.

Furthermore this allows to replace the separate exit_to_user_mode() and
syscall_exit_to_user_mode_work() calls with a combined
syscall_exit_to_user_mode() call which results in slightly better code.

Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
This commit is contained in:
Heiko Carstens 2025-03-10 10:33:42 +01:00 committed by Vasily Gorbik
parent b46525437e
commit a0f2a8d051

View File

@ -82,47 +82,10 @@ SYSCALL_DEFINE0(ni_syscall)
return -ENOSYS;
}
static void do_syscall(struct pt_regs *regs)
void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
{
unsigned long nr;
nr = regs->int_code & 0xffff;
if (!nr) {
nr = regs->gprs[1] & 0xffff;
regs->int_code &= ~0xffffUL;
regs->int_code |= nr;
}
regs->gprs[2] = nr;
if (nr == __NR_restart_syscall && !(current->restart_block.arch_data & 1)) {
regs->psw.addr = current->restart_block.arch_data;
current->restart_block.arch_data = 1;
}
nr = syscall_enter_from_user_mode_work(regs, nr);
/*
* In the s390 ptrace ABI, both the syscall number and the return value
* use gpr2. However, userspace puts the syscall number either in the
* svc instruction itself, or uses gpr1. To make at least skipping syscalls
* work, the ptrace code sets PIF_SYSCALL_RET_SET, which is checked here
* and if set, the syscall will be skipped.
*/
if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
goto out;
regs->gprs[2] = -ENOSYS;
if (likely(nr >= NR_syscalls))
goto out;
do {
regs->gprs[2] = current->thread.sys_call_table[nr](regs);
} while (test_and_clear_pt_regs_flag(regs, PIF_EXECVE_PGSTE_RESTART));
out:
syscall_exit_to_user_mode_work(regs);
}
void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
{
add_random_kstack_offset();
enter_from_user_mode(regs);
regs->psw = get_lowcore()->svc_old_psw;
@ -130,15 +93,39 @@ void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
update_timer_sys();
if (cpu_has_bear())
current->thread.last_break = regs->last_break;
local_irq_enable();
regs->orig_gpr2 = regs->gprs[2];
if (per_trap)
if (unlikely(per_trap))
set_thread_flag(TIF_PER_TRAP);
regs->flags = 0;
set_pt_regs_flag(regs, PIF_SYSCALL);
do_syscall(regs);
exit_to_user_mode();
nr = regs->int_code & 0xffff;
if (likely(!nr)) {
nr = regs->gprs[1] & 0xffff;
regs->int_code &= ~0xffffUL;
regs->int_code |= nr;
}
regs->gprs[2] = nr;
if (nr == __NR_restart_syscall && !(current->restart_block.arch_data & 1)) {
regs->psw.addr = current->restart_block.arch_data;
current->restart_block.arch_data = 1;
}
nr = syscall_enter_from_user_mode_work(regs, nr);
/*
* In the s390 ptrace ABI, both the syscall number and the return value
* use gpr2. However, userspace puts the syscall number either in the
* svc instruction itself, or uses gpr1. To make at least skipping syscalls
* work, the ptrace code sets PIF_SYSCALL_RET_SET, which is checked here
* and if set, the syscall will be skipped.
*/
if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
goto out;
regs->gprs[2] = -ENOSYS;
if (unlikely(nr >= NR_syscalls))
goto out;
do {
regs->gprs[2] = current->thread.sys_call_table[nr](regs);
} while (test_and_clear_pt_regs_flag(regs, PIF_EXECVE_PGSTE_RESTART));
out:
syscall_exit_to_user_mode(regs);
}