linux/arch/alpha/kernel/process.c

399 lines
9.6 KiB
C
Raw Normal View History

/*
* linux/arch/alpha/kernel/process.c
*
* Copyright (C) 1995 Linus Torvalds
*/
/*
* This file handles the architecture-dependent parts of process handling.
*/
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/time.h>
#include <linux/major.h>
#include <linux/stat.h>
#include <linux/vt.h>
#include <linux/mman.h>
#include <linux/elfcore.h>
#include <linux/reboot.h>
#include <linux/tty.h>
#include <linux/console.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/rcupdate.h>
#include <asm/reg.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/hwrpb.h>
#include <asm/fpu.h>
#include "proto.h"
#include "pci_impl.h"
[PATCH] Don't attempt to power off if power off is not implemented The problem. It is expected that /sbin/halt -p works exactly like /sbin/halt, when the kernel does not implement power off functionality. The kernel can do a lot of work in the reboot notifiers and in device_shutdown before we even get to machine_power_off. Some of that shutdown is not safe if you are leaving the power on, and it definitely gets in the way of using sysrq or pressing ctrl-alt-del. Since the shutdown happens in generic code there is no way to fix this in architecture specific code :( Some machines are kernel oopsing today because of this. The simple solution is to turn LINUX_REBOOT_CMD_POWER_OFF into LINUX_REBOOT_CMD_HALT if power_off functionality is not implemented. This has the unfortunate side effect of disabling the power off functionality on architectures that leave pm_power_off to null and still implement something in machine_power_off. And it will break the build on some architectures that don't have a pm_power_off variable at all. On both counts I say tough. For architectures like alpha that don't implement the pm_power_off variable pm_power_off is declared in linux/pm.h and it is a generic part of our power management code, and all architectures should implement it. For architectures like parisc that have a default power off method in machine_power_off if pm_power_off is not implemented or fails. It is easy enough to set the pm_power_off variable. And nothing bad happens there, the machines just stop powering off. The current semantics are impossible without a flag at the top level so we can avoid the problem code if a power off is not implemented. pm_power_off is as good a flag as any with the bonus that it works without modification on at least x86, x86_64, powerpc, and ppc today. Andrew can you pick this up and put this in the mm tree. Kernels that don't compile or don't power off seem saner than kernels that oops or panic. Until we get the arch specific patches for the problem architectures this probably isn't smart to push into the stable kernel. Unfortunately I don't have the time at the moment to walk through every architecture and make them work. And even if I did I couldn't test it :( From: Hirokazu Takata <takata@linux-m32r.org> Add pm_power_off() for build fix of arch/m32r/kernel/process.c. From: Miklos Szeredi <miklos@szeredi.hu> UML build fix Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Hayato Fujiwara <fujiwara@linux-m32r.org> Signed-off-by: Hirokazu Takata <takata@linux-m32r.org> Signed-off-by: Miklos Szeredi <miklos@szeredi.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:46 +08:00
/*
* Power off function, if any
*/
void (*pm_power_off)(void) = machine_power_off;
EXPORT_SYMBOL(pm_power_off);
[PATCH] Don't attempt to power off if power off is not implemented The problem. It is expected that /sbin/halt -p works exactly like /sbin/halt, when the kernel does not implement power off functionality. The kernel can do a lot of work in the reboot notifiers and in device_shutdown before we even get to machine_power_off. Some of that shutdown is not safe if you are leaving the power on, and it definitely gets in the way of using sysrq or pressing ctrl-alt-del. Since the shutdown happens in generic code there is no way to fix this in architecture specific code :( Some machines are kernel oopsing today because of this. The simple solution is to turn LINUX_REBOOT_CMD_POWER_OFF into LINUX_REBOOT_CMD_HALT if power_off functionality is not implemented. This has the unfortunate side effect of disabling the power off functionality on architectures that leave pm_power_off to null and still implement something in machine_power_off. And it will break the build on some architectures that don't have a pm_power_off variable at all. On both counts I say tough. For architectures like alpha that don't implement the pm_power_off variable pm_power_off is declared in linux/pm.h and it is a generic part of our power management code, and all architectures should implement it. For architectures like parisc that have a default power off method in machine_power_off if pm_power_off is not implemented or fails. It is easy enough to set the pm_power_off variable. And nothing bad happens there, the machines just stop powering off. The current semantics are impossible without a flag at the top level so we can avoid the problem code if a power off is not implemented. pm_power_off is as good a flag as any with the bonus that it works without modification on at least x86, x86_64, powerpc, and ppc today. Andrew can you pick this up and put this in the mm tree. Kernels that don't compile or don't power off seem saner than kernels that oops or panic. Until we get the arch specific patches for the problem architectures this probably isn't smart to push into the stable kernel. Unfortunately I don't have the time at the moment to walk through every architecture and make them work. And even if I did I couldn't test it :( From: Hirokazu Takata <takata@linux-m32r.org> Add pm_power_off() for build fix of arch/m32r/kernel/process.c. From: Miklos Szeredi <miklos@szeredi.hu> UML build fix Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Hayato Fujiwara <fujiwara@linux-m32r.org> Signed-off-by: Hirokazu Takata <takata@linux-m32r.org> Signed-off-by: Miklos Szeredi <miklos@szeredi.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:46 +08:00
#ifdef CONFIG_ALPHA_WTINT
/*
* Sleep the CPU.
* EV6, LCA45 and QEMU know how to power down, skipping N timer interrupts.
*/
void arch_cpu_idle(void)
{
wtint(0);
local_irq_enable();
}
void arch_cpu_idle_dead(void)
{
wtint(INT_MAX);
}
#endif /* ALPHA_WTINT */
struct halt_info {
int mode;
char *restart_cmd;
};
static void
common_shutdown_1(void *generic_ptr)
{
struct halt_info *how = (struct halt_info *)generic_ptr;
struct percpu_struct *cpup;
unsigned long *pflags, flags;
int cpuid = smp_processor_id();
/* No point in taking interrupts anymore. */
local_irq_disable();
cpup = (struct percpu_struct *)
((unsigned long)hwrpb + hwrpb->processor_offset
+ hwrpb->processor_size * cpuid);
pflags = &cpup->flags;
flags = *pflags;
/* Clear reason to "default"; clear "bootstrap in progress". */
flags &= ~0x00ff0001UL;
#ifdef CONFIG_SMP
/* Secondaries halt here. */
if (cpuid != boot_cpuid) {
flags |= 0x00040000UL; /* "remain halted" */
*pflags = flags;
set_cpu_present(cpuid, false);
set_cpu_possible(cpuid, false);
halt();
}
#endif
if (how->mode == LINUX_REBOOT_CMD_RESTART) {
if (!how->restart_cmd) {
flags |= 0x00020000UL; /* "cold bootstrap" */
} else {
/* For SRM, we could probably set environment
variables to get this to work. We'd have to
delay this until after srm_paging_stop unless
we ever got srm_fixup working.
At the moment, SRM will use the last boot device,
but the file and flags will be the defaults, when
doing a "warm" bootstrap. */
flags |= 0x00030000UL; /* "warm bootstrap" */
}
} else {
flags |= 0x00040000UL; /* "remain halted" */
}
*pflags = flags;
#ifdef CONFIG_SMP
/* Wait for the secondaries to halt. */
set_cpu_present(boot_cpuid, false);
set_cpu_possible(boot_cpuid, false);
while (cpumask_weight(cpu_present_mask))
barrier();
#endif
/* If booted from SRM, reset some of the original environment. */
if (alpha_using_srm) {
#ifdef CONFIG_DUMMY_CONSOLE
/* If we've gotten here after SysRq-b, leave interrupt
context before taking over the console. */
if (in_interrupt())
irq_exit();
/* This has the effect of resetting the VGA video origin. */
console_lock();
do_take_over_console(&dummy_con, 0, MAX_NR_CONSOLES-1, 1);
console_unlock();
#endif
pci_restore_srm_config();
set_hae(srm_hae);
}
if (alpha_mv.kill_arch)
alpha_mv.kill_arch(how->mode);
if (! alpha_using_srm && how->mode != LINUX_REBOOT_CMD_RESTART) {
/* Unfortunately, since MILO doesn't currently understand
the hwrpb bits above, we can't reliably halt the
processor and keep it halted. So just loop. */
return;
}
if (alpha_using_srm)
srm_paging_stop();
halt();
}
static void
common_shutdown(int mode, char *restart_cmd)
{
struct halt_info args;
args.mode = mode;
args.restart_cmd = restart_cmd;
on_each_cpu(common_shutdown_1, &args, 0);
}
void
machine_restart(char *restart_cmd)
{
common_shutdown(LINUX_REBOOT_CMD_RESTART, restart_cmd);
}
void
machine_halt(void)
{
common_shutdown(LINUX_REBOOT_CMD_HALT, NULL);
}
void
machine_power_off(void)
{
common_shutdown(LINUX_REBOOT_CMD_POWER_OFF, NULL);
}
/* Used by sysrq-p, among others. I don't believe r9-r15 are ever
saved in the context it's used. */
void
show_regs(struct pt_regs *regs)
{
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);
dik_show_regs(regs, NULL);
}
/*
* Re-start a thread when doing execve()
*/
void
start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
{
regs->pc = pc;
regs->ps = 8;
wrusp(sp);
}
EXPORT_SYMBOL(start_thread);
void
flush_thread(void)
{
/* Arrange for each exec'ed process to start off with a clean slate
with respect to the FPU. This is all exceptions disabled. */
current_thread_info()->ieee_state = 0;
wrfpcr(FPCR_DYN_NORMAL | ieee_swcr_to_fpcr(0));
/* Clean slate for TLS. */
current_thread_info()->pcb.unique = 0;
}
void
release_thread(struct task_struct *dead_task)
{
}
/*
* Copy architecture-specific thread state
*/
int
copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long kthread_arg,
struct task_struct *p)
{
extern void ret_from_fork(void);
extern void ret_from_kernel_thread(void);
struct thread_info *childti = task_thread_info(p);
struct pt_regs *childregs = task_pt_regs(p);
struct pt_regs *regs = current_pt_regs();
struct switch_stack *childstack, *stack;
childstack = ((struct switch_stack *) childregs) - 1;
childti->pcb.ksp = (unsigned long) childstack;
childti->pcb.flags = 1; /* set FEN, clear everything else */
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
memset(childstack, 0,
sizeof(struct switch_stack) + sizeof(struct pt_regs));
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
childstack->r10 = kthread_arg;
childregs->hae = alpha_mv.hae_cache,
childti->pcb.usp = 0;
return 0;
}
/* Note: if CLONE_SETTLS is not set, then we must inherit the
value from the parent, which will have been set by the block
copy in dup_task_struct. This is non-intuitive, but is
required for proper operation in the case of a threaded
application calling fork. */
if (clone_flags & CLONE_SETTLS)
childti->pcb.unique = regs->r20;
childti->pcb.usp = usp ?: rdusp();
*childregs = *regs;
childregs->r0 = 0;
childregs->r19 = 0;
childregs->r20 = 1; /* OSF/1 has some strange fork() semantics. */
regs->r20 = 0;
stack = ((struct switch_stack *) regs) - 1;
*childstack = *stack;
childstack->r26 = (unsigned long) ret_from_fork;
return 0;
}
/*
* Fill in the user structure for a ELF core dump.
*/
void
dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti)
{
/* switch stack follows right below pt_regs: */
struct switch_stack * sw = ((struct switch_stack *) pt) - 1;
dest[ 0] = pt->r0;
dest[ 1] = pt->r1;
dest[ 2] = pt->r2;
dest[ 3] = pt->r3;
dest[ 4] = pt->r4;
dest[ 5] = pt->r5;
dest[ 6] = pt->r6;
dest[ 7] = pt->r7;
dest[ 8] = pt->r8;
dest[ 9] = sw->r9;
dest[10] = sw->r10;
dest[11] = sw->r11;
dest[12] = sw->r12;
dest[13] = sw->r13;
dest[14] = sw->r14;
dest[15] = sw->r15;
dest[16] = pt->r16;
dest[17] = pt->r17;
dest[18] = pt->r18;
dest[19] = pt->r19;
dest[20] = pt->r20;
dest[21] = pt->r21;
dest[22] = pt->r22;
dest[23] = pt->r23;
dest[24] = pt->r24;
dest[25] = pt->r25;
dest[26] = pt->r26;
dest[27] = pt->r27;
dest[28] = pt->r28;
dest[29] = pt->gp;
dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp;
dest[31] = pt->pc;
/* Once upon a time this was the PS value. Which is stupid
since that is always 8 for usermode. Usurped for the more
useful value of the thread's UNIQUE field. */
dest[32] = ti->pcb.unique;
}
EXPORT_SYMBOL(dump_elf_thread);
int
dump_elf_task(elf_greg_t *dest, struct task_struct *task)
{
dump_elf_thread(dest, task_pt_regs(task), task_thread_info(task));
return 1;
}
EXPORT_SYMBOL(dump_elf_task);
int
dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task)
{
struct switch_stack *sw = (struct switch_stack *)task_pt_regs(task) - 1;
memcpy(dest, sw->fp, 32 * 8);
return 1;
}
EXPORT_SYMBOL(dump_elf_task_fp);
/*
* Return saved PC of a blocked thread. This assumes the frame
* pointer is the 6th saved long on the kernel stack and that the
* saved return address is the first long in the frame. This all
* holds provided the thread blocked through a call to schedule() ($15
* is the frame pointer in schedule() and $15 is saved at offset 48 by
* entry.S:do_switch_stack).
*
* Under heavy swap load I've seen this lose in an ugly way. So do
* some extra sanity checking on the ranges we expect these pointers
* to be in so that we can fail gracefully. This is just for ps after
* all. -- r~
*/
unsigned long
thread_saved_pc(struct task_struct *t)
{
unsigned long base = (unsigned long)task_stack_page(t);
unsigned long fp, sp = task_thread_info(t)->pcb.ksp;
if (sp > base && sp+6*8 < base + 16*1024) {
fp = ((unsigned long*)sp)[6];
if (fp > sp && fp < base + 16*1024)
return *(unsigned long *)fp;
}
return 0;
}
unsigned long
get_wchan(struct task_struct *p)
{
unsigned long schedule_frame;
unsigned long pc;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
/*
* This one depends on the frame size of schedule(). Do a
* "disass schedule" in gdb to find the frame size. Also, the
* code assumes that sleep_on() follows immediately after
* interruptible_sleep_on() and that add_timer() follows
* immediately after interruptible_sleep(). Ugly, isn't it?
* Maybe adding a wchan field to task_struct would be better,
* after all...
*/
pc = thread_saved_pc(p);
if (in_sched_functions(pc)) {
schedule_frame = ((unsigned long *)task_thread_info(p)->pcb.ksp)[6];
return ((unsigned long *)schedule_frame)[12];
}
return pc;
}