linux/arch/s390/kernel/syscall.c
Linus Torvalds 1c7d0c3af5 s390 updates for 6.11 merge window
- Remove restrictions on PAI NNPA and crypto counters, enabling
   concurrent per-task and system-wide sampling and counting events
 
 - Switch to GENERIC_CPU_DEVICES by setting up the CPU present mask in
   the architecture code and letting the generic code handle CPU bring-up
 
 - Add support for the diag204 busy indication facility to prevent
   undesirable blocking during hypervisor logical CPU utilization
   queries. Implement results caching
 
 - Improve the handling of Store Data SCLP events by suppressing
   unnecessary warning, preventing buffer release in I/O during failures,
   and adding timeout handling for Store Data requests to address potential
   firmware issues
 
 - Provide optimized __arch_hweight*() implementations
 
 - Remove the unnecessary CPU KOBJ_CHANGE uevents generated during topology
   updates, as they are unused and also not present on other architectures
 
 - Cleanup atomic_ops, optimize __atomic_set() for small values and
   __atomic_cmpxchg_bool() for compilers supporting flag output constraint
 
 - Couple of cleanups for KVM:
   - Move and improve KVM struct definitions for DAT tables from gaccess.c
     to a new header
   - Pass the asce as parameter to sie64a()
 
 - Make the crdte() and cspg() page table handling wrappers return a
   boolean to indicate success, like the other existing "compare and swap"
   wrappers
 
 - Add documentation for HWCAP flags
 
 - Switch to obtaining total RAM pages from memblock instead of
   totalram_pages() during mm init, to ensure correct calculation of zero
   page size, when defer_init is enabled
 
 - Refactor lowcore access and switch to using the get_lowcore() function
   instead of the S390_lowcore macro
 
 - Cleanups for PG_arch_1 and folio handling in UV and hugetlb code
 
 - Add missing MODULE_DESCRIPTION() macros
 
 - Fix VM_FAULT_HWPOISON handling in do_exception()
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEE3QHqV+H2a8xAv27vjYWKoQLXFBgFAmaYGegACgkQjYWKoQLX
 FBjCwwf/aRYoLIXCa9/nHGWFiUjZm6xBgVwZh55bXjfNG9TI2J9UZSsYlOFGUJKl
 gvD2Ym+LqAejK8R4EUHkfD6ftaKMQuIxNDoedxhwuSpfOQ2mZ5teu0MxTh8QcUAx
 4Y2w5XEeCuqE3SuoZ4SJa58K4rGl4cFpPsKNa8ofdzH1ZLFNe8Wqzis4kh0htqLb
 FtPj6nsgfzQ5kg14rVkGxCa4CqoFxonXgsA6nH6xZLbxKUInyq8uV44UBQ+aJq5v
 dsdzZ5XuAJHN2FpBuuOYQYZYw3XIy/kka7o4EjffORi5SGCRMWO4Zt0P6HXaNkh6
 xV8EEO8myeo7rV8dnrk1V4yGjGJmfA==
 =3IGY
 -----END PGP SIGNATURE-----

Merge tag 's390-6.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Vasily Gorbik:

 - Remove restrictions on PAI NNPA and crypto counters, enabling
   concurrent per-task and system-wide sampling and counting events

 - Switch to GENERIC_CPU_DEVICES by setting up the CPU present mask in
   the architecture code and letting the generic code handle CPU
   bring-up

 - Add support for the diag204 busy indication facility to prevent
   undesirable blocking during hypervisor logical CPU utilization
   queries. Implement results caching

 - Improve the handling of Store Data SCLP events by suppressing
   unnecessary warning, preventing buffer release in I/O during
   failures, and adding timeout handling for Store Data requests to
   address potential firmware issues

 - Provide optimized __arch_hweight*() implementations

 - Remove the unnecessary CPU KOBJ_CHANGE uevents generated during
   topology updates, as they are unused and also not present on other
   architectures

 - Cleanup atomic_ops, optimize __atomic_set() for small values and
   __atomic_cmpxchg_bool() for compilers supporting flag output
   constraint

 - Couple of cleanups for KVM:
     - Move and improve KVM struct definitions for DAT tables from
       gaccess.c to a new header
     - Pass the asce as parameter to sie64a()

 - Make the crdte() and cspg() page table handling wrappers return a
   boolean to indicate success, like the other existing "compare and
   swap" wrappers

 - Add documentation for HWCAP flags

 - Switch to obtaining total RAM pages from memblock instead of
   totalram_pages() during mm init, to ensure correct calculation of
   zero page size, when defer_init is enabled

 - Refactor lowcore access and switch to using the get_lowcore()
   function instead of the S390_lowcore macro

 - Cleanups for PG_arch_1 and folio handling in UV and hugetlb code

 - Add missing MODULE_DESCRIPTION() macros

 - Fix VM_FAULT_HWPOISON handling in do_exception()

* tag 's390-6.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (54 commits)
  s390/mm: Fix VM_FAULT_HWPOISON handling in do_exception()
  s390/kvm: Move bitfields for dat tables
  s390/entry: Pass the asce as parameter to sie64a()
  s390/sthyi: Use cached data when diag is busy
  s390/sthyi: Move diag operations
  s390/hypfs_diag: Diag204 busy loop
  s390/diag: Add busy-indication-facility requirements
  s390/diag: Diag204 add busy return errno
  s390/diag: Return errno's from diag204
  s390/sclp: Diag204 busy indication facility detection
  s390/atomic_ops: Make use of flag output constraint
  s390/atomic_ops: Improve __atomic_set() for small values
  s390/atomic_ops: Use symbolic names
  s390/smp: Switch to GENERIC_CPU_DEVICES
  s390/hwcaps: Add documentation for HWCAP flags
  s390/pgtable: Make crdte() and cspg() return a value
  s390/topology: Remove CPU KOBJ_CHANGE uevents
  s390/sclp: Add timeout to Store Data requests
  s390/sclp: Prevent release of buffer in I/O
  s390/sclp: Suppress unnecessary Store Data warning
  ...
2024-07-18 15:41:45 -07:00

144 lines
3.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* S390 version
* Copyright IBM Corp. 1999, 2000
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
* Thomas Spatzier (tspat@de.ibm.com)
*
* Derived from "arch/i386/kernel/sys_i386.c"
*
* This file contains various random system calls that
* have a non-standard calling sequence on the Linux/s390
* platform.
*/
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/msg.h>
#include <linux/shm.h>
#include <linux/stat.h>
#include <linux/syscalls.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/personality.h>
#include <linux/unistd.h>
#include <linux/ipc.h>
#include <linux/uaccess.h>
#include <linux/string.h>
#include <linux/thread_info.h>
#include <linux/entry-common.h>
#include <asm/ptrace.h>
#include <asm/vtime.h>
#include "entry.h"
#ifdef CONFIG_SYSVIPC
/*
* sys_ipc() is the de-multiplexer for the SysV IPC calls.
*/
SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, unsigned long, second,
unsigned long, third, void __user *, ptr)
{
if (call >> 16)
return -EINVAL;
/* The s390 sys_ipc variant has only five parameters instead of six
* like the generic variant. The only difference is the handling of
* the SEMTIMEDOP subcall where on s390 the third parameter is used
* as a pointer to a struct timespec where the generic variant uses
* the fifth parameter.
* Therefore we can call the generic variant by simply passing the
* third parameter also as fifth parameter.
*/
return ksys_ipc(call, first, second, third, ptr, third);
}
#endif /* CONFIG_SYSVIPC */
SYSCALL_DEFINE1(s390_personality, unsigned int, personality)
{
unsigned int ret = current->personality;
if (personality(current->personality) == PER_LINUX32 &&
personality(personality) == PER_LINUX)
personality |= PER_LINUX32;
if (personality != 0xffffffff)
set_personality(personality);
if (personality(ret) == PER_LINUX32)
ret &= ~PER_LINUX32;
return ret;
}
SYSCALL_DEFINE0(ni_syscall)
{
return -ENOSYS;
}
static void do_syscall(struct pt_regs *regs)
{
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;
regs->int_code = get_lowcore()->svc_int_code;
update_timer_sys();
if (static_branch_likely(&cpu_has_bear))
current->thread.last_break = regs->last_break;
local_irq_enable();
regs->orig_gpr2 = regs->gprs[2];
if (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();
}