kernel_optimize_test/arch/s390/kernel/process.c

425 lines
11 KiB
C
Raw Normal View History

/*
* arch/s390/kernel/process.c
*
* S390 version
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
* Hartmut Penner (hp@de.ibm.com),
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
*
* Derived from "arch/i386/kernel/process.c"
* Copyright (C) 1995, Linus Torvalds
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
Remove fs.h from mm.h Remove fs.h from mm.h. For this, 1) Uninline vma_wants_writenotify(). It's pretty huge anyway. 2) Add back fs.h or less bloated headers (err.h) to files that need it. As result, on x86_64 allyesconfig, fs.h dependencies cut down from 3929 files rebuilt down to 3444 (-12.3%). Cross-compile tested without regressions on my two usual configs and (sigh): alpha arm-mx1ads mips-bigsur powerpc-ebony alpha-allnoconfig arm-neponset mips-capcella powerpc-g5 alpha-defconfig arm-netwinder mips-cobalt powerpc-holly alpha-up arm-netx mips-db1000 powerpc-iseries arm arm-ns9xxx mips-db1100 powerpc-linkstation arm-assabet arm-omap_h2_1610 mips-db1200 powerpc-lite5200 arm-at91rm9200dk arm-onearm mips-db1500 powerpc-maple arm-at91rm9200ek arm-picotux200 mips-db1550 powerpc-mpc7448_hpc2 arm-at91sam9260ek arm-pleb mips-ddb5477 powerpc-mpc8272_ads arm-at91sam9261ek arm-pnx4008 mips-decstation powerpc-mpc8313_rdb arm-at91sam9263ek arm-pxa255-idp mips-e55 powerpc-mpc832x_mds arm-at91sam9rlek arm-realview mips-emma2rh powerpc-mpc832x_rdb arm-ateb9200 arm-realview-smp mips-excite powerpc-mpc834x_itx arm-badge4 arm-rpc mips-fulong powerpc-mpc834x_itxgp arm-carmeva arm-s3c2410 mips-ip22 powerpc-mpc834x_mds arm-cerfcube arm-shannon mips-ip27 powerpc-mpc836x_mds arm-clps7500 arm-shark mips-ip32 powerpc-mpc8540_ads arm-collie arm-simpad mips-jazz powerpc-mpc8544_ds arm-corgi arm-spitz mips-jmr3927 powerpc-mpc8560_ads arm-csb337 arm-trizeps4 mips-malta powerpc-mpc8568mds arm-csb637 arm-versatile mips-mipssim powerpc-mpc85xx_cds arm-ebsa110 i386 mips-mpc30x powerpc-mpc8641_hpcn arm-edb7211 i386-allnoconfig mips-msp71xx powerpc-mpc866_ads arm-em_x270 i386-defconfig mips-ocelot powerpc-mpc885_ads arm-ep93xx i386-up mips-pb1100 powerpc-pasemi arm-footbridge ia64 mips-pb1500 powerpc-pmac32 arm-fortunet ia64-allnoconfig mips-pb1550 powerpc-ppc64 arm-h3600 ia64-bigsur mips-pnx8550-jbs powerpc-prpmc2800 arm-h7201 ia64-defconfig mips-pnx8550-stb810 powerpc-ps3 arm-h7202 ia64-gensparse mips-qemu powerpc-pseries arm-hackkit ia64-sim mips-rbhma4200 powerpc-up arm-integrator ia64-sn2 mips-rbhma4500 s390 arm-iop13xx ia64-tiger mips-rm200 s390-allnoconfig arm-iop32x ia64-up mips-sb1250-swarm s390-defconfig arm-iop33x ia64-zx1 mips-sead s390-up arm-ixp2000 m68k mips-tb0219 sparc arm-ixp23xx m68k-amiga mips-tb0226 sparc-allnoconfig arm-ixp4xx m68k-apollo mips-tb0287 sparc-defconfig arm-jornada720 m68k-atari mips-workpad sparc-up arm-kafa m68k-bvme6000 mips-wrppmc sparc64 arm-kb9202 m68k-hp300 mips-yosemite sparc64-allnoconfig arm-ks8695 m68k-mac parisc sparc64-defconfig arm-lart m68k-mvme147 parisc-allnoconfig sparc64-up arm-lpd270 m68k-mvme16x parisc-defconfig um-x86_64 arm-lpd7a400 m68k-q40 parisc-up x86_64 arm-lpd7a404 m68k-sun3 powerpc x86_64-allnoconfig arm-lubbock m68k-sun3x powerpc-cell x86_64-defconfig arm-lusl7200 mips powerpc-celleb x86_64-up arm-mainstone mips-atlas powerpc-chrp32 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-30 06:36:13 +08:00
#include <linux/fs.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/slab.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/utsname.h>
#include <linux/tick.h>
#include <linux/elfcore.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/cpu.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];
}
/*
* Need to know about CPUs going idle?
*/
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
static ATOMIC_NOTIFIER_HEAD(idle_chain);
DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
int register_idle_notifier(struct notifier_block *nb)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
return atomic_notifier_chain_register(&idle_chain, nb);
}
EXPORT_SYMBOL(register_idle_notifier);
int unregister_idle_notifier(struct notifier_block *nb)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
return atomic_notifier_chain_unregister(&idle_chain, nb);
}
EXPORT_SYMBOL(unregister_idle_notifier);
static int s390_idle_enter(void)
{
struct s390_idle_data *idle;
int nr_calls = 0;
void *hcpu;
int rc;
hcpu = (void *)(long)smp_processor_id();
rc = __atomic_notifier_call_chain(&idle_chain, S390_CPU_IDLE, hcpu, -1,
&nr_calls);
if (rc == NOTIFY_BAD) {
nr_calls--;
__atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE,
hcpu, nr_calls, NULL);
return rc;
}
idle = &__get_cpu_var(s390_idle);
spin_lock(&idle->lock);
idle->idle_count++;
idle->in_idle = 1;
idle->idle_enter = get_clock();
spin_unlock(&idle->lock);
return NOTIFY_OK;
}
void s390_idle_leave(void)
{
struct s390_idle_data *idle;
idle = &__get_cpu_var(s390_idle);
spin_lock(&idle->lock);
idle->idle_time += get_clock() - idle->idle_enter;
idle->in_idle = 0;
spin_unlock(&idle->lock);
atomic_notifier_call_chain(&idle_chain, S390_CPU_NOT_IDLE,
(void *)(long) smp_processor_id());
}
extern void s390_handle_mcck(void);
/*
* The idle loop on a S390...
*/
static void default_idle(void)
{
[PATCH] sched: resched and cpu_idle rework Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce confusion, and make their semantics rigid. Improves efficiency of resched_task and some cpu_idle routines. * In resched_task: - TIF_NEED_RESCHED is only cleared with the task's runqueue lock held, and as we hold it during resched_task, then there is no need for an atomic test and set there. The only other time this should be set is when the task's quantum expires, in the timer interrupt - this is protected against because the rq lock is irq-safe. - If TIF_NEED_RESCHED is set, then we don't need to do anything. It won't get unset until the task get's schedule()d off. - If we are running on the same CPU as the task we resched, then set TIF_NEED_RESCHED and no further action is required. - If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set after TIF_NEED_RESCHED has been set, then we need to send an IPI. Using these rules, we are able to remove the test and set operation in resched_task, and make clear the previously vague semantics of POLLING_NRFLAG. * In idle routines: - Enter cpu_idle with preempt disabled. When the need_resched() condition becomes true, explicitly call schedule(). This makes things a bit clearer (IMO), but haven't updated all architectures yet. - Many do a test and clear of TIF_NEED_RESCHED for some reason. According to the resched_task rules, this isn't needed (and actually breaks the assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock held). So remove that. Generally one less locked memory op when switching to the idle thread. - Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner most polling idle loops. The above resched_task semantics allow it to be set until before the last time need_resched() is checked before going into a halt requiring interrupt wakeup. Many idle routines simply never enter such a halt, and so POLLING_NRFLAG can be always left set, completely eliminating resched IPIs when rescheduling the idle task. POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Con Kolivas <kernel@kolivas.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 13:39:04 +08:00
/* CPU is going idle. */
local_irq_disable();
[PATCH] sched: resched and cpu_idle rework Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce confusion, and make their semantics rigid. Improves efficiency of resched_task and some cpu_idle routines. * In resched_task: - TIF_NEED_RESCHED is only cleared with the task's runqueue lock held, and as we hold it during resched_task, then there is no need for an atomic test and set there. The only other time this should be set is when the task's quantum expires, in the timer interrupt - this is protected against because the rq lock is irq-safe. - If TIF_NEED_RESCHED is set, then we don't need to do anything. It won't get unset until the task get's schedule()d off. - If we are running on the same CPU as the task we resched, then set TIF_NEED_RESCHED and no further action is required. - If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set after TIF_NEED_RESCHED has been set, then we need to send an IPI. Using these rules, we are able to remove the test and set operation in resched_task, and make clear the previously vague semantics of POLLING_NRFLAG. * In idle routines: - Enter cpu_idle with preempt disabled. When the need_resched() condition becomes true, explicitly call schedule(). This makes things a bit clearer (IMO), but haven't updated all architectures yet. - Many do a test and clear of TIF_NEED_RESCHED for some reason. According to the resched_task rules, this isn't needed (and actually breaks the assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock held). So remove that. Generally one less locked memory op when switching to the idle thread. - Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner most polling idle loops. The above resched_task semantics allow it to be set until before the last time need_resched() is checked before going into a halt requiring interrupt wakeup. Many idle routines simply never enter such a halt, and so POLLING_NRFLAG can be always left set, completely eliminating resched IPIs when rescheduling the idle task. POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Con Kolivas <kernel@kolivas.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 13:39:04 +08:00
if (need_resched()) {
local_irq_enable();
[PATCH] sched: resched and cpu_idle rework Make some changes to the NEED_RESCHED and POLLING_NRFLAG to reduce confusion, and make their semantics rigid. Improves efficiency of resched_task and some cpu_idle routines. * In resched_task: - TIF_NEED_RESCHED is only cleared with the task's runqueue lock held, and as we hold it during resched_task, then there is no need for an atomic test and set there. The only other time this should be set is when the task's quantum expires, in the timer interrupt - this is protected against because the rq lock is irq-safe. - If TIF_NEED_RESCHED is set, then we don't need to do anything. It won't get unset until the task get's schedule()d off. - If we are running on the same CPU as the task we resched, then set TIF_NEED_RESCHED and no further action is required. - If we are running on another CPU, and TIF_POLLING_NRFLAG is *not* set after TIF_NEED_RESCHED has been set, then we need to send an IPI. Using these rules, we are able to remove the test and set operation in resched_task, and make clear the previously vague semantics of POLLING_NRFLAG. * In idle routines: - Enter cpu_idle with preempt disabled. When the need_resched() condition becomes true, explicitly call schedule(). This makes things a bit clearer (IMO), but haven't updated all architectures yet. - Many do a test and clear of TIF_NEED_RESCHED for some reason. According to the resched_task rules, this isn't needed (and actually breaks the assumption that TIF_NEED_RESCHED is only cleared with the runqueue lock held). So remove that. Generally one less locked memory op when switching to the idle thread. - Many idle routines clear TIF_POLLING_NRFLAG, and only set it in the inner most polling idle loops. The above resched_task semantics allow it to be set until before the last time need_resched() is checked before going into a halt requiring interrupt wakeup. Many idle routines simply never enter such a halt, and so POLLING_NRFLAG can be always left set, completely eliminating resched IPIs when rescheduling the idle task. POLLING_NRFLAG width can be increased, to reduce the chance of resched IPIs. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Con Kolivas <kernel@kolivas.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 13:39:04 +08:00
return;
}
if (s390_idle_enter() == NOTIFY_BAD) {
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();
s390_idle_leave();
local_irq_enable();
s390_handle_mcck();
return;
}
trace_hardirqs_on();
/* Wait for external, I/O or machine check interrupt. */
[S390] noexec protection This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-06 04:18:17 +08:00
__load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
PSW_MASK_IO | PSW_MASK_EXT);
}
void cpu_idle(void)
{
for (;;) {
tick_nohz_stop_sched_tick();
while (!need_resched())
default_idle();
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
void show_regs(struct pt_regs *regs)
{
print_modules();
printk("CPU: %d %s %s %.*s\n",
task_thread_info(current)->cpu, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
current->comm, current->pid, current,
(void *) current->thread.ksp);
show_registers(regs);
/* Show stack backtrace if pt_regs is from kernel mode */
if (!(regs->psw.mask & PSW_MASK_PSTATE))
show_trace(NULL, (unsigned long *) regs->gprs[15]);
[S390] kernel: show last breaking-event-address on oops Newer s390 models have a breaking-event-address-recording register. Each time an instruction causes a break in the sequential instruction execution, the address is saved in that hardware register. On a program interrupt the address is copied to the lowcore address 272-279, which makes it software accessible. This patch changes the program check handler and the stack overflow checker to copy the value into the pt_regs argument. The oops output is enhanced to show the last known breaking address. It might give additional information if the stack trace is corrupted. The feature is only available on 64 bit. The new oops output looks like: [---------snip----------] Modules linked in: vmcp sunrpc qeth_l2 dm_mod qeth ccwgroup CPU: 2 Not tainted 2.6.24zlive-host #8 Process modprobe (pid: 4788, task: 00000000bf3d8718, ksp: 00000000b2b0b8e0) Krnl PSW : 0704200180000000 000003e000020028 (vmcp_init+0x28/0xe4 [vmcp]) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:2 PM:0 EA:3 Krnl GPRS: 0000000004000002 000003e000020000 0000000000000000 0000000000000001 000000000015734c ffffffffffffffff 000003e0000b3b00 0000000000000000 000003e00007ca30 00000000b5bb5d40 00000000b5bb5800 000003e0000b3b00 000003e0000a2000 00000000003ecf50 00000000b2b0bd50 00000000b2b0bcb0 Krnl Code: 000003e000020018: c0c000040ff4 larl %r12,3e0000a2000 000003e00002001e: e3e0f0000024 stg %r14,0(%r15) 000003e000020024: a7f40001 brc 15,3e000020026 >000003e000020028: e310c0100004 lg %r1,16(%r12) 000003e00002002e: c020000413dc larl %r2,3e0000a27e6 000003e000020034: c0a00004aee6 larl %r10,3e0000b5e00 000003e00002003a: a7490001 lghi %r4,1 000003e00002003e: a75900f0 lghi %r5,240 Call Trace: ([<000000000014b300>] blocking_notifier_call_chain+0x2c/0x40) [<000000000015735c>] sys_init_module+0x19d8/0x1b08 [<0000000000110afc>] sysc_noemu+0x10/0x16 [<000002000011cda2>] 0x2000011cda2 Last Breaking-Event-Address: [<000003e000020024>] vmcp_init+0x24/0xe4 [vmcp] [---------snip----------] Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 13:46:30 +08:00
show_last_breaking_event(regs);
}
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(&regs, 0, sizeof(regs));
[S390] noexec protection This provides a noexec protection on s390 hardware. Our hardware does not have any bits left in the pte for a hw noexec bit, so this is a different approach using shadow page tables and a special addressing mode that allows separate address spaces for code and data. As a special feature of our "secondary-space" addressing mode, separate page tables can be specified for the translation of data addresses (storage operands) and instruction addresses. The shadow page table is used for the instruction addresses and the standard page table for the data addresses. The shadow page table is linked to the standard page table by a pointer in page->lru.next of the struct page corresponding to the page that contains the standard page table (since page->private is not really private with the pte_lock and the page table pages are not in the LRU list). Depending on the software bits of a pte, it is either inserted into both page tables or just into the standard (data) page table. Pages of a vma that does not have the VM_EXEC bit set get mapped only in the data address space. Any try to execute code on such a page will cause a page translation exception. The standard reaction to this is a SIGSEGV with two exceptions: the two system call opcodes 0x0a77 (sys_sigreturn) and 0x0aad (sys_rt_sigreturn) are allowed. They are stored by the kernel to the signal stack frame. Unfortunately, the signal return mechanism cannot be modified to use an SA_RESTORER because the exception unwinding code depends on the system call opcode stored behind the signal stack frame. This feature requires that user space is executed in secondary-space mode and the kernel in home-space mode, which means that the addressing modes need to be switched and that the noexec protection only works for user space. After switching the addressing modes, we cannot use the mvcp/mvcs instructions anymore to copy between kernel and user space. A new mvcos instruction has been added to the z9 EC/BC hardware which allows to copy between arbitrary address spaces, but on older hardware the page tables need to be walked manually. Signed-off-by: Gerald Schaefer <geraldsc@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-02-06 04:18:17 +08:00
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, &regs, 0, NULL, NULL);
}
/*
* Free current thread data structures etc..
*/
void exit_thread(void)
{
}
void flush_thread(void)
{
clear_used_math();
clear_tsk_thread_flag(current, TIF_USEDFPU);
}
void release_thread(struct task_struct *dead_task)
{
}
int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
unsigned long unused,
struct task_struct * p, struct pt_regs * regs)
{
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(&current->thread.fp_regs);
memcpy(&p->thread.fp_regs, &current->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 (test_thread_flag(TIF_31BIT)) {
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));
return 0;
}
asmlinkage long sys_fork(void)
{
struct pt_regs *regs = task_pt_regs(current);
return do_fork(SIGCHLD, regs->gprs[15], regs, 0, NULL, NULL);
}
asmlinkage long sys_clone(void)
{
struct pt_regs *regs = task_pt_regs(current);
unsigned long clone_flags;
unsigned long newsp;
int __user *parent_tidptr, *child_tidptr;
clone_flags = regs->gprs[3];
newsp = regs->orig_gpr2;
parent_tidptr = (int __user *) regs->gprs[4];
child_tidptr = (int __user *) regs->gprs[5];
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.
*/
asmlinkage long sys_vfork(void)
{
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)
{
task_lock(current);
current->ptrace &= ~PT_DTRACE;
task_unlock(current);
current->thread.fp_regs.fpc = 0;
if (MACHINE_HAS_IEEE)
asm volatile("sfpc %0,%0" : : "d" (0));
}
/*
* sys_execve() executes a new program.
*/
asmlinkage long sys_execve(void)
{
struct pt_regs *regs = task_pt_regs(current);
char *filename;
unsigned long result;
int rc;
filename = getname((char __user *) regs->orig_gpr2);
if (IS_ERR(filename)) {
result = PTR_ERR(filename);
goto out;
}
rc = do_execve(filename, (char __user * __user *) regs->gprs[3],
(char __user * __user *) regs->gprs[4], regs);
if (rc) {
result = rc;
goto out_putname;
}
execve_tail();
result = regs->gprs[2];
out_putname:
putname(filename);
out:
return result;
}
/*
* 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(&current->thread.fp_regs);
memcpy(fpregs, &current->thread.fp_regs, sizeof(s390_fp_regs));
#else /* CONFIG_64BIT */
save_fp_regs(fpregs);
#endif /* CONFIG_64BIT */
return 1;
}
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;
}