linux/arch/sparc/kernel/process_32.c

496 lines
13 KiB
C
Raw Normal View History

/* linux/arch/sparc/kernel/process.c
*
* Copyright (C) 1995, 2008 David S. Miller (davem@davemloft.net)
* Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <stdarg.h>
#include <linux/elfcore.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/smp.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/pm.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h 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>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/cpu.h>
#include <asm/auxio.h>
#include <asm/oplib.h>
#include <asm/uaccess.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/delay.h>
#include <asm/processor.h>
#include <asm/psr.h>
#include <asm/elf.h>
#include <asm/prom.h>
#include <asm/unistd.h>
#include <asm/setup.h>
#include "kernel.h"
/*
* Power management idle function
* Set in pm platform drivers (apc.c and pmc.c)
*/
void (*sparc_idle)(void);
/*
* Power-off handler instantiation for pm.h compliance
* This is done via auxio, but could be used as a fallback
* handler when auxio is not present-- unused for now...
*/
void (*pm_power_off)(void) = machine_power_off;
EXPORT_SYMBOL(pm_power_off);
/*
* sysctl - toggle power-off restriction for serial console
* systems in machine_power_off()
*/
int scons_pwroff = 1;
extern void fpsave(unsigned long *, unsigned long *, void *, unsigned long *);
struct task_struct *last_task_used_math = NULL;
struct thread_info *current_set[NR_CPUS];
/* Idle loop support. */
void arch_cpu_idle(void)
{
if (sparc_idle)
(*sparc_idle)();
local_irq_enable();
}
/* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */
void machine_halt(void)
{
local_irq_enable();
mdelay(8);
local_irq_disable();
prom_halt();
panic("Halt failed!");
}
void machine_restart(char * cmd)
{
char *p;
local_irq_enable();
mdelay(8);
local_irq_disable();
p = strchr (reboot_command, '\n');
if (p) *p = 0;
if (cmd)
prom_reboot(cmd);
if (*reboot_command)
prom_reboot(reboot_command);
prom_feval ("reset");
panic("Reboot failed!");
}
void machine_power_off(void)
{
if (auxio_power_register &&
(strcmp(of_console_device->type, "serial") || scons_pwroff)) {
u8 power_register = sbus_readb(auxio_power_register);
power_register |= AUXIO_POWER_OFF;
sbus_writeb(power_register, auxio_power_register);
}
machine_halt();
}
void show_regs(struct pt_regs *r)
{
struct reg_window32 *rw = (struct reg_window32 *) r->u_regs[14];
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
show_regs_print_info(KERN_DEFAULT);
printk("PSR: %08lx PC: %08lx NPC: %08lx Y: %08lx %s\n",
r->psr, r->pc, r->npc, r->y, print_tainted());
printk("PC: <%pS>\n", (void *) r->pc);
printk("%%G: %08lx %08lx %08lx %08lx %08lx %08lx %08lx %08lx\n",
r->u_regs[0], r->u_regs[1], r->u_regs[2], r->u_regs[3],
r->u_regs[4], r->u_regs[5], r->u_regs[6], r->u_regs[7]);
printk("%%O: %08lx %08lx %08lx %08lx %08lx %08lx %08lx %08lx\n",
r->u_regs[8], r->u_regs[9], r->u_regs[10], r->u_regs[11],
r->u_regs[12], r->u_regs[13], r->u_regs[14], r->u_regs[15]);
printk("RPC: <%pS>\n", (void *) r->u_regs[15]);
printk("%%L: %08lx %08lx %08lx %08lx %08lx %08lx %08lx %08lx\n",
rw->locals[0], rw->locals[1], rw->locals[2], rw->locals[3],
rw->locals[4], rw->locals[5], rw->locals[6], rw->locals[7]);
printk("%%I: %08lx %08lx %08lx %08lx %08lx %08lx %08lx %08lx\n",
rw->ins[0], rw->ins[1], rw->ins[2], rw->ins[3],
rw->ins[4], rw->ins[5], rw->ins[6], rw->ins[7]);
}
/*
* The show_stack is an external API which we do not use ourselves.
* The oops is printed in die_if_kernel.
*/
void show_stack(struct task_struct *tsk, unsigned long *_ksp)
{
unsigned long pc, fp;
unsigned long task_base;
struct reg_window32 *rw;
int count = 0;
if (!tsk)
tsk = current;
if (tsk == current && !_ksp)
__asm__ __volatile__("mov %%fp, %0" : "=r" (_ksp));
task_base = (unsigned long) task_stack_page(tsk);
fp = (unsigned long) _ksp;
do {
/* Bogus frame pointer? */
if (fp < (task_base + sizeof(struct thread_info)) ||
fp >= (task_base + (PAGE_SIZE << 1)))
break;
rw = (struct reg_window32 *) fp;
pc = rw->ins[7];
printk("[%08lx : ", pc);
printk("%pS ] ", (void *) pc);
fp = rw->ins[6];
} while (++count < 16);
printk("\n");
}
/*
* Note: sparc64 has a pretty intricated thread_saved_pc, check it out.
*/
unsigned long thread_saved_pc(struct task_struct *tsk)
{
return task_thread_info(tsk)->kpc;
}
/*
* Free current thread data structures etc..
*/
void exit_thread(void)
{
#ifndef CONFIG_SMP
if(last_task_used_math == current) {
#else
if (test_thread_flag(TIF_USEDFPU)) {
#endif
/* Keep process from leaving FPU in a bogon state. */
put_psr(get_psr() | PSR_EF);
fpsave(&current->thread.float_regs[0], &current->thread.fsr,
&current->thread.fpqueue[0], &current->thread.fpqdepth);
#ifndef CONFIG_SMP
last_task_used_math = NULL;
#else
clear_thread_flag(TIF_USEDFPU);
#endif
}
}
void flush_thread(void)
{
current_thread_info()->w_saved = 0;
#ifndef CONFIG_SMP
if(last_task_used_math == current) {
#else
if (test_thread_flag(TIF_USEDFPU)) {
#endif
/* Clean the fpu. */
put_psr(get_psr() | PSR_EF);
fpsave(&current->thread.float_regs[0], &current->thread.fsr,
&current->thread.fpqueue[0], &current->thread.fpqdepth);
#ifndef CONFIG_SMP
last_task_used_math = NULL;
#else
clear_thread_flag(TIF_USEDFPU);
#endif
}
/* This task is no longer a kernel thread. */
if (current->thread.flags & SPARC_FLAG_KTHREAD) {
current->thread.flags &= ~SPARC_FLAG_KTHREAD;
/* We must fixup kregs as well. */
/* XXX This was not fixed for ti for a while, worked. Unused? */
current->thread.kregs = (struct pt_regs *)
(task_stack_page(current) + (THREAD_SIZE - TRACEREG_SZ));
}
}
static inline struct sparc_stackf __user *
clone_stackframe(struct sparc_stackf __user *dst,
struct sparc_stackf __user *src)
{
unsigned long size, fp;
struct sparc_stackf *tmp;
struct sparc_stackf __user *sp;
if (get_user(tmp, &src->fp))
return NULL;
fp = (unsigned long) tmp;
size = (fp - ((unsigned long) src));
fp = (unsigned long) dst;
sp = (struct sparc_stackf __user *)(fp - size);
/* do_fork() grabs the parent semaphore, we must release it
* temporarily so we can build the child clone stack frame
* without deadlocking.
*/
if (__copy_user(sp, src, size))
sp = NULL;
else if (put_user(fp, &sp->fp))
sp = NULL;
return sp;
}
asmlinkage int sparc_do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size)
{
unsigned long parent_tid_ptr, child_tid_ptr;
unsigned long orig_i1 = regs->u_regs[UREG_I1];
long ret;
parent_tid_ptr = regs->u_regs[UREG_I2];
child_tid_ptr = regs->u_regs[UREG_I4];
ret = do_fork(clone_flags, stack_start, stack_size,
(int __user *) parent_tid_ptr,
(int __user *) child_tid_ptr);
/* If we get an error and potentially restart the system
* call, we're screwed because copy_thread() clobbered
* the parent's %o1. So detect that case and restore it
* here.
*/
if ((unsigned long)ret >= -ERESTART_RESTARTBLOCK)
regs->u_regs[UREG_I1] = orig_i1;
return ret;
}
/* Copy a Sparc thread. The fork() return value conventions
* under SunOS are nothing short of bletcherous:
* Parent --> %o0 == childs pid, %o1 == 0
* Child --> %o0 == parents pid, %o1 == 1
*
* NOTE: We have a separate fork kpsr/kwim because
* the parent could change these values between
* sys_fork invocation and when we reach here
* if the parent should sleep while trying to
* allocate the task_struct and kernel stack in
* do_fork().
* XXX See comment above sys_vfork in sparc64. todo.
*/
extern void ret_from_fork(void);
extern void ret_from_kernel_thread(void);
int copy_thread(unsigned long clone_flags, unsigned long sp,
unsigned long arg, struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs, *regs = current_pt_regs();
char *new_stack;
#ifndef CONFIG_SMP
if(last_task_used_math == current) {
#else
if (test_thread_flag(TIF_USEDFPU)) {
#endif
put_psr(get_psr() | PSR_EF);
fpsave(&p->thread.float_regs[0], &p->thread.fsr,
&p->thread.fpqueue[0], &p->thread.fpqdepth);
}
/*
* p->thread_info new_stack childregs stack bottom
* ! ! ! !
* V V (stk.fr.) V (pt_regs) V
* +----- - - - - - ------+===========+=============+
*/
new_stack = task_stack_page(p) + THREAD_SIZE;
new_stack -= STACKFRAME_SZ + TRACEREG_SZ;
childregs = (struct pt_regs *) (new_stack + STACKFRAME_SZ);
/*
* A new process must start with interrupts disabled, see schedule_tail()
* and finish_task_switch(). (If we do not do it and if a timer interrupt
* hits before we unlock and attempts to take the rq->lock, we deadlock.)
*
* Thus, kpsr |= PSR_PIL.
*/
ti->ksp = (unsigned long) new_stack;
p->thread.kregs = childregs;
if (unlikely(p->flags & PF_KTHREAD)) {
extern int nwindows;
unsigned long psr;
memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
p->thread.flags |= SPARC_FLAG_KTHREAD;
p->thread.current_ds = KERNEL_DS;
ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
childregs->u_regs[UREG_G1] = sp; /* function */
childregs->u_regs[UREG_G2] = arg;
psr = childregs->psr = get_psr();
ti->kpsr = psr | PSR_PIL;
ti->kwim = 1 << (((psr & PSR_CWP) + 1) % nwindows);
return 0;
}
memcpy(new_stack, (char *)regs - STACKFRAME_SZ, STACKFRAME_SZ + TRACEREG_SZ);
childregs->u_regs[UREG_FP] = sp;
p->thread.flags &= ~SPARC_FLAG_KTHREAD;
p->thread.current_ds = USER_DS;
ti->kpc = (((unsigned long) ret_from_fork) - 0x8);
ti->kpsr = current->thread.fork_kpsr | PSR_PIL;
ti->kwim = current->thread.fork_kwim;
if (sp != regs->u_regs[UREG_FP]) {
struct sparc_stackf __user *childstack;
struct sparc_stackf __user *parentstack;
/*
* This is a clone() call with supplied user stack.
* Set some valid stack frames to give to the child.
*/
childstack = (struct sparc_stackf __user *)
(sp & ~0xfUL);
parentstack = (struct sparc_stackf __user *)
regs->u_regs[UREG_FP];
#if 0
printk("clone: parent stack:\n");
show_stackframe(parentstack);
#endif
childstack = clone_stackframe(childstack, parentstack);
if (!childstack)
return -EFAULT;
#if 0
printk("clone: child stack:\n");
show_stackframe(childstack);
#endif
childregs->u_regs[UREG_FP] = (unsigned long)childstack;
}
#ifdef CONFIG_SMP
/* FPU must be disabled on SMP. */
childregs->psr &= ~PSR_EF;
clear_tsk_thread_flag(p, TIF_USEDFPU);
#endif
/* Set the return value for the child. */
childregs->u_regs[UREG_I0] = current->pid;
childregs->u_regs[UREG_I1] = 1;
/* Set the return value for the parent. */
regs->u_regs[UREG_I1] = 0;
if (clone_flags & CLONE_SETTLS)
childregs->u_regs[UREG_G7] = regs->u_regs[UREG_I3];
return 0;
}
/*
* fill in the fpu structure for a core dump.
*/
int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs)
{
if (used_math()) {
memset(fpregs, 0, sizeof(*fpregs));
fpregs->pr_q_entrysize = 8;
return 1;
}
#ifdef CONFIG_SMP
if (test_thread_flag(TIF_USEDFPU)) {
put_psr(get_psr() | PSR_EF);
fpsave(&current->thread.float_regs[0], &current->thread.fsr,
&current->thread.fpqueue[0], &current->thread.fpqdepth);
if (regs != NULL) {
regs->psr &= ~(PSR_EF);
clear_thread_flag(TIF_USEDFPU);
}
}
#else
if (current == last_task_used_math) {
put_psr(get_psr() | PSR_EF);
fpsave(&current->thread.float_regs[0], &current->thread.fsr,
&current->thread.fpqueue[0], &current->thread.fpqdepth);
if (regs != NULL) {
regs->psr &= ~(PSR_EF);
last_task_used_math = NULL;
}
}
#endif
memcpy(&fpregs->pr_fr.pr_regs[0],
&current->thread.float_regs[0],
(sizeof(unsigned long) * 32));
fpregs->pr_fsr = current->thread.fsr;
fpregs->pr_qcnt = current->thread.fpqdepth;
fpregs->pr_q_entrysize = 8;
fpregs->pr_en = 1;
if(fpregs->pr_qcnt != 0) {
memcpy(&fpregs->pr_q[0],
&current->thread.fpqueue[0],
sizeof(struct fpq) * fpregs->pr_qcnt);
}
/* Zero out the rest. */
memset(&fpregs->pr_q[fpregs->pr_qcnt], 0,
sizeof(struct fpq) * (32 - fpregs->pr_qcnt));
return 1;
}
unsigned long get_wchan(struct task_struct *task)
{
unsigned long pc, fp, bias = 0;
unsigned long task_base = (unsigned long) task;
unsigned long ret = 0;
struct reg_window32 *rw;
int count = 0;
if (!task || task == current ||
task->state == TASK_RUNNING)
goto out;
fp = task_thread_info(task)->ksp + bias;
do {
/* Bogus frame pointer? */
if (fp < (task_base + sizeof(struct thread_info)) ||
fp >= (task_base + (2 * PAGE_SIZE)))
break;
rw = (struct reg_window32 *) fp;
pc = rw->ins[7];
if (!in_sched_functions(pc)) {
ret = pc;
goto out;
}
fp = rw->ins[6] + bias;
} while (++count < 16);
out:
return ret;
}