mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 02:50:53 +07:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
333 lines
8.4 KiB
C
333 lines
8.4 KiB
C
/*
|
|
* This file handles the architecture dependent parts of process handling.
|
|
*
|
|
* Copyright IBM Corp. 1999,2009
|
|
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>,
|
|
* Hartmut Penner <hp@de.ibm.com>,
|
|
* Denis Joseph Barrow,
|
|
*/
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/stddef.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/user.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/reboot.h>
|
|
#include <linux/init.h>
|
|
#include <linux/module.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/elfcore.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/compat.h>
|
|
#include <asm/compat.h>
|
|
#include <asm/uaccess.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/system.h>
|
|
#include <asm/io.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/irq.h>
|
|
#include <asm/timer.h>
|
|
#include <asm/nmi.h>
|
|
#include "entry.h"
|
|
|
|
asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
|
|
|
|
/*
|
|
* Return saved PC of a blocked thread. used in kernel/sched.
|
|
* resume in entry.S does not create a new stack frame, it
|
|
* just stores the registers %r6-%r15 to the frame given by
|
|
* schedule. We want to return the address of the caller of
|
|
* schedule, so we have to walk the backchain one time to
|
|
* find the frame schedule() store its return address.
|
|
*/
|
|
unsigned long thread_saved_pc(struct task_struct *tsk)
|
|
{
|
|
struct stack_frame *sf, *low, *high;
|
|
|
|
if (!tsk || !task_stack_page(tsk))
|
|
return 0;
|
|
low = task_stack_page(tsk);
|
|
high = (struct stack_frame *) task_pt_regs(tsk);
|
|
sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
return sf->gprs[8];
|
|
}
|
|
|
|
/*
|
|
* The idle loop on a S390...
|
|
*/
|
|
static void default_idle(void)
|
|
{
|
|
/* CPU is going idle. */
|
|
local_irq_disable();
|
|
if (need_resched()) {
|
|
local_irq_enable();
|
|
return;
|
|
}
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
if (cpu_is_offline(smp_processor_id())) {
|
|
preempt_enable_no_resched();
|
|
cpu_die();
|
|
}
|
|
#endif
|
|
local_mcck_disable();
|
|
if (test_thread_flag(TIF_MCCK_PENDING)) {
|
|
local_mcck_enable();
|
|
local_irq_enable();
|
|
s390_handle_mcck();
|
|
return;
|
|
}
|
|
trace_hardirqs_on();
|
|
/* Don't trace preempt off for idle. */
|
|
stop_critical_timings();
|
|
/* Stop virtual timer and halt the cpu. */
|
|
vtime_stop_cpu();
|
|
/* Reenable preemption tracer. */
|
|
start_critical_timings();
|
|
}
|
|
|
|
void cpu_idle(void)
|
|
{
|
|
for (;;) {
|
|
tick_nohz_stop_sched_tick(1);
|
|
while (!need_resched())
|
|
default_idle();
|
|
tick_nohz_restart_sched_tick();
|
|
preempt_enable_no_resched();
|
|
schedule();
|
|
preempt_disable();
|
|
}
|
|
}
|
|
|
|
extern void kernel_thread_starter(void);
|
|
|
|
asm(
|
|
".align 4\n"
|
|
"kernel_thread_starter:\n"
|
|
" la 2,0(10)\n"
|
|
" basr 14,9\n"
|
|
" la 2,0\n"
|
|
" br 11\n");
|
|
|
|
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
|
|
{
|
|
struct pt_regs regs;
|
|
|
|
memset(®s, 0, sizeof(regs));
|
|
regs.psw.mask = psw_kernel_bits | PSW_MASK_IO | PSW_MASK_EXT;
|
|
regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE;
|
|
regs.gprs[9] = (unsigned long) fn;
|
|
regs.gprs[10] = (unsigned long) arg;
|
|
regs.gprs[11] = (unsigned long) do_exit;
|
|
regs.orig_gpr2 = -1;
|
|
|
|
/* Ok, create the new process.. */
|
|
return do_fork(flags | CLONE_VM | CLONE_UNTRACED,
|
|
0, ®s, 0, NULL, NULL);
|
|
}
|
|
EXPORT_SYMBOL(kernel_thread);
|
|
|
|
/*
|
|
* Free current thread data structures etc..
|
|
*/
|
|
void exit_thread(void)
|
|
{
|
|
}
|
|
|
|
void flush_thread(void)
|
|
{
|
|
}
|
|
|
|
void release_thread(struct task_struct *dead_task)
|
|
{
|
|
}
|
|
|
|
int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
|
|
unsigned long unused,
|
|
struct task_struct *p, struct pt_regs *regs)
|
|
{
|
|
struct thread_info *ti;
|
|
struct fake_frame
|
|
{
|
|
struct stack_frame sf;
|
|
struct pt_regs childregs;
|
|
} *frame;
|
|
|
|
frame = container_of(task_pt_regs(p), struct fake_frame, childregs);
|
|
p->thread.ksp = (unsigned long) frame;
|
|
/* Store access registers to kernel stack of new process. */
|
|
frame->childregs = *regs;
|
|
frame->childregs.gprs[2] = 0; /* child returns 0 on fork. */
|
|
frame->childregs.gprs[15] = new_stackp;
|
|
frame->sf.back_chain = 0;
|
|
|
|
/* new return point is ret_from_fork */
|
|
frame->sf.gprs[8] = (unsigned long) ret_from_fork;
|
|
|
|
/* fake return stack for resume(), don't go back to schedule */
|
|
frame->sf.gprs[9] = (unsigned long) frame;
|
|
|
|
/* Save access registers to new thread structure. */
|
|
save_access_regs(&p->thread.acrs[0]);
|
|
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the child.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(&p->thread.fp_regs, ¤t->thread.fp_regs,
|
|
sizeof(s390_fp_regs));
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS)
|
|
p->thread.acrs[0] = regs->gprs[6];
|
|
#else /* CONFIG_64BIT */
|
|
/* Save the fpu registers to new thread structure. */
|
|
save_fp_regs(&p->thread.fp_regs);
|
|
/* Set a new TLS ? */
|
|
if (clone_flags & CLONE_SETTLS) {
|
|
if (is_compat_task()) {
|
|
p->thread.acrs[0] = (unsigned int) regs->gprs[6];
|
|
} else {
|
|
p->thread.acrs[0] = (unsigned int)(regs->gprs[6] >> 32);
|
|
p->thread.acrs[1] = (unsigned int) regs->gprs[6];
|
|
}
|
|
}
|
|
#endif /* CONFIG_64BIT */
|
|
/* start new process with ar4 pointing to the correct address space */
|
|
p->thread.mm_segment = get_fs();
|
|
/* Don't copy debug registers */
|
|
memset(&p->thread.per_info, 0, sizeof(p->thread.per_info));
|
|
clear_tsk_thread_flag(p, TIF_SINGLE_STEP);
|
|
/* Initialize per thread user and system timer values */
|
|
ti = task_thread_info(p);
|
|
ti->user_timer = 0;
|
|
ti->system_timer = 0;
|
|
return 0;
|
|
}
|
|
|
|
SYSCALL_DEFINE0(fork)
|
|
{
|
|
struct pt_regs *regs = task_pt_regs(current);
|
|
return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL);
|
|
}
|
|
|
|
SYSCALL_DEFINE4(clone, unsigned long, newsp, unsigned long, clone_flags,
|
|
int __user *, parent_tidptr, int __user *, child_tidptr)
|
|
{
|
|
struct pt_regs *regs = task_pt_regs(current);
|
|
|
|
if (!newsp)
|
|
newsp = regs->gprs[15];
|
|
return do_fork(clone_flags, newsp, regs, 0,
|
|
parent_tidptr, child_tidptr);
|
|
}
|
|
|
|
/*
|
|
* This is trivial, and on the face of it looks like it
|
|
* could equally well be done in user mode.
|
|
*
|
|
* Not so, for quite unobvious reasons - register pressure.
|
|
* In user mode vfork() cannot have a stack frame, and if
|
|
* done by calling the "clone()" system call directly, you
|
|
* do not have enough call-clobbered registers to hold all
|
|
* the information you need.
|
|
*/
|
|
SYSCALL_DEFINE0(vfork)
|
|
{
|
|
struct pt_regs *regs = task_pt_regs(current);
|
|
return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD,
|
|
regs->gprs[15], regs, 0, NULL, NULL);
|
|
}
|
|
|
|
asmlinkage void execve_tail(void)
|
|
{
|
|
current->thread.fp_regs.fpc = 0;
|
|
if (MACHINE_HAS_IEEE)
|
|
asm volatile("sfpc %0,%0" : : "d" (0));
|
|
}
|
|
|
|
/*
|
|
* sys_execve() executes a new program.
|
|
*/
|
|
SYSCALL_DEFINE3(execve, char __user *, name, char __user * __user *, argv,
|
|
char __user * __user *, envp)
|
|
{
|
|
struct pt_regs *regs = task_pt_regs(current);
|
|
char *filename;
|
|
long rc;
|
|
|
|
filename = getname(name);
|
|
rc = PTR_ERR(filename);
|
|
if (IS_ERR(filename))
|
|
return rc;
|
|
rc = do_execve(filename, argv, envp, regs);
|
|
if (rc)
|
|
goto out;
|
|
execve_tail();
|
|
rc = regs->gprs[2];
|
|
out:
|
|
putname(filename);
|
|
return rc;
|
|
}
|
|
|
|
/*
|
|
* fill in the FPU structure for a core dump.
|
|
*/
|
|
int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs)
|
|
{
|
|
#ifndef CONFIG_64BIT
|
|
/*
|
|
* save fprs to current->thread.fp_regs to merge them with
|
|
* the emulated registers and then copy the result to the dump.
|
|
*/
|
|
save_fp_regs(¤t->thread.fp_regs);
|
|
memcpy(fpregs, ¤t->thread.fp_regs, sizeof(s390_fp_regs));
|
|
#else /* CONFIG_64BIT */
|
|
save_fp_regs(fpregs);
|
|
#endif /* CONFIG_64BIT */
|
|
return 1;
|
|
}
|
|
EXPORT_SYMBOL(dump_fpu);
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
{
|
|
struct stack_frame *sf, *low, *high;
|
|
unsigned long return_address;
|
|
int count;
|
|
|
|
if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p))
|
|
return 0;
|
|
low = task_stack_page(p);
|
|
high = (struct stack_frame *) task_pt_regs(p);
|
|
sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
for (count = 0; count < 16; count++) {
|
|
sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
|
|
if (sf <= low || sf > high)
|
|
return 0;
|
|
return_address = sf->gprs[8] & PSW_ADDR_INSN;
|
|
if (!in_sched_functions(return_address))
|
|
return return_address;
|
|
}
|
|
return 0;
|
|
}
|