linux/arch/x86/kernel/process_64.c

938 lines
22 KiB
C
Raw Normal View History

/*
* Copyright (C) 1995 Linus Torvalds
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*
* X86-64 port
* Andi Kleen.
*
* CPU hotplug support - ashok.raj@intel.com
*/
/*
* This file handles the architecture-dependent parts of process handling..
*/
#include <stdarg.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/random.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/tick.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
asmlinkage extern void ret_from_fork(void);
unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);
/*
* Powermanagement idle function, if any..
*/
void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
[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 09:16:30 +00:00
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
void idle_notifier_register(struct notifier_block *n)
{
[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 09:16:30 +00:00
atomic_notifier_chain_register(&idle_notifier, n);
}
void enter_idle(void)
{
write_pda(isidle, 1);
[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 09:16:30 +00:00
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
static void __exit_idle(void)
{
if (test_and_clear_bit_pda(0, isidle) == 0)
return;
[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 09:16:30 +00:00
atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}
/* Called from interrupts to signify idle end */
void exit_idle(void)
{
/* idle loop has pid 0 */
if (current->pid)
return;
__exit_idle();
}
/*
* We use this if we don't have any better
* idle routine..
*/
void default_idle(void)
{
current_thread_info()->status &= ~TS_POLLING;
[PATCH] sched: fix bad missed wakeups in the i386, x86_64, ia64, ACPI and APM idle code Fernando Lopez-Lezcano reported frequent scheduling latencies and audio xruns starting at the 2.6.18-rt kernel, and those problems persisted all until current -rt kernels. The latencies were serious and unjustified by system load, often in the milliseconds range. After a patient and heroic multi-month effort of Fernando, where he tested dozens of kernels, tried various configs, boot options, test-patches of mine and provided latency traces of those incidents, the following 'smoking gun' trace was captured by him: _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup (try_to_wake_up) IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup <<...>-5856> (37 0) IRQ_19-1479 1D..1 0us : __trace_start_sched_wakeup (c01262ba 0 0) IRQ_19-1479 1D..1 0us : resched_task (try_to_wake_up) IRQ_19-1479 1D..1 0us : __spin_unlock_irqrestore (try_to_wake_up) ... <idle>-0 1...1 11us!: default_idle (cpu_idle) ... <idle>-0 0Dn.1 602us : smp_apic_timer_interrupt (c0103baf 1 0) ... <...>-5856 0D..2 618us : __switch_to (__schedule) <...>-5856 0D..2 618us : __schedule <<idle>-0> (20 162) <...>-5856 0D..2 619us : __spin_unlock_irq (__schedule) <...>-5856 0...1 619us : trace_stop_sched_switched (__schedule) <...>-5856 0D..1 619us : trace_stop_sched_switched <<...>-5856> (37 0) what is visible in this trace is that CPU#1 ran try_to_wake_up() for PID:5856, it placed PID:5856 on CPU#0's runqueue and ran resched_task() for CPU#0. But it decided to not send an IPI that no CPU - due to TS_POLLING. But CPU#0 never woke up after its NEED_RESCHED bit was set, and only rescheduled to PID:5856 upon the next lapic timer IRQ. The result was a 600+ usecs latency and a missed wakeup! the bug turned out to be an idle-wakeup bug introduced into the mainline kernel this summer via an optimization in the x86_64 tree: commit 495ab9c045e1b0e5c82951b762257fe1c9d81564 Author: Andi Kleen <ak@suse.de> Date: Mon Jun 26 13:59:11 2006 +0200 [PATCH] i386/x86-64/ia64: Move polling flag into thread_info_status During some profiling I noticed that default_idle causes a lot of memory traffic. I think that is caused by the atomic operations to clear/set the polling flag in thread_info. There is actually no reason to make this atomic - only the idle thread does it to itself, other CPUs only read it. So I moved it into ti->status. the problem is this type of change: if (!hlt_counter && boot_cpu_data.hlt_works_ok) { - clear_thread_flag(TIF_POLLING_NRFLAG); + current_thread_info()->status &= ~TS_POLLING; smp_mb__after_clear_bit(); while (!need_resched()) { local_irq_disable(); this changes clear_thread_flag() to an explicit clearing of TS_POLLING. clear_thread_flag() is defined as: clear_bit(flag, &ti->flags); and clear_bit() is a LOCK-ed atomic instruction on all x86 platforms: static inline void clear_bit(int nr, volatile unsigned long * addr) { __asm__ __volatile__( LOCK_PREFIX "btrl %1,%0" hence smp_mb__after_clear_bit() is defined as a simple compile barrier: #define smp_mb__after_clear_bit() barrier() but the explicit TS_POLLING clearing introduced by the patch: + current_thread_info()->status &= ~TS_POLLING; is not an atomic op! So the clearing of the TS_POLLING bit is freely reorderable with the reading of the NEED_RESCHED bit - and both now reside in different memory addresses. CPU idle wakeup very much depends on ordered memory ops, the clearing of the TS_POLLING flag must always be done before we test need_resched() and hit the idle instruction(s). [Symmetrically, the wakeup code needs to set NEED_RESCHED before it tests the TS_POLLING flag, so memory ordering is paramount.] Fernando's dual-core Athlon64 system has a sufficiently advanced memory ordering model so that it triggered this scenario very often. ( And it also turned out that the reason why these latencies never triggered on my testsystems is that i routinely use idle=poll, which was the only idle variant not affected by this bug. ) The fix is to change the smp_mb__after_clear_bit() to an smp_mb(), to act as an absolute barrier between the TS_POLLING write and the NEED_RESCHED read. This affects almost all idling methods (default, ACPI, APM), on all 3 x86 architectures: i386, x86_64, ia64. Signed-off-by: Ingo Molnar <mingo@elte.hu> Tested-by: Fernando Lopez-Lezcano <nando@ccrma.Stanford.EDU> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-22 09:11:56 +00:00
/*
* TS_POLLING-cleared state must be visible before we
* test NEED_RESCHED:
*/
smp_mb();
local_irq_disable();
if (!need_resched()) {
ktime_t t0, t1;
u64 t0n, t1n;
t0 = ktime_get();
t0n = ktime_to_ns(t0);
safe_halt(); /* enables interrupts racelessly */
local_irq_disable();
t1 = ktime_get();
t1n = ktime_to_ns(t1);
sched_clock_idle_wakeup_event(t1n - t0n);
}
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
}
/*
* On SMP it's slightly faster (but much more power-consuming!)
* to poll the ->need_resched flag instead of waiting for the
* cross-CPU IPI to arrive. Use this option with caution.
*/
static void poll_idle(void)
{
local_irq_enable();
cpu_relax();
}
#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);
#include <asm/nmi.h>
/* We halt the CPU with physical CPU hotplug */
static inline void play_dead(void)
{
idle_task_exit();
wbinvd();
mb();
/* Ack it */
__get_cpu_var(cpu_state) = CPU_DEAD;
local_irq_disable();
while (1)
halt();
}
#else
static inline void play_dead(void)
{
BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */
/*
* The idle thread. There's no useful work to be
* done, so just try to conserve power and have a
* low exit latency (ie sit in a loop waiting for
* somebody to say that they'd like to reschedule)
*/
void cpu_idle(void)
{
current_thread_info()->status |= TS_POLLING;
/* endless idle loop with no priority at all */
while (1) {
while (!need_resched()) {
void (*idle)(void);
if (__get_cpu_var(cpu_idle_state))
__get_cpu_var(cpu_idle_state) = 0;
tick_nohz_stop_sched_tick();
rmb();
idle = pm_idle;
if (!idle)
idle = default_idle;
if (cpu_is_offline(smp_processor_id()))
play_dead();
/*
* Idle routines should keep interrupts disabled
* from here on, until they go to idle.
* Otherwise, idle callbacks can misfire.
*/
local_irq_disable();
enter_idle();
idle();
/* In many cases the interrupt that ended idle
has already called exit_idle. But some idle
loops can be woken up without interrupt. */
__exit_idle();
}
tick_nohz_restart_sched_tick();
preempt_enable_no_resched();
schedule();
preempt_disable();
}
}
static void do_nothing(void *unused)
{
}
void cpu_idle_wait(void)
{
unsigned int cpu, this_cpu = get_cpu();
cpumask_t map, tmp = current->cpus_allowed;
set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
put_cpu();
cpus_clear(map);
for_each_online_cpu(cpu) {
per_cpu(cpu_idle_state, cpu) = 1;
cpu_set(cpu, map);
}
__get_cpu_var(cpu_idle_state) = 0;
wmb();
do {
ssleep(1);
for_each_online_cpu(cpu) {
if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
cpu_clear(cpu, map);
}
cpus_and(map, map, cpu_online_map);
/*
* We waited 1 sec, if a CPU still did not call idle
* it may be because it is in idle and not waking up
* because it has nothing to do.
* Give all the remaining CPUS a kick.
*/
smp_call_function_mask(map, do_nothing, 0, 0);
} while (!cpus_empty(map));
set_cpus_allowed(current, tmp);
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);
/*
* This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
* which can obviate IPI to trigger checking of need_resched.
* We execute MONITOR against need_resched and enter optimized wait state
* through MWAIT. Whenever someone changes need_resched, we would be woken
* up from MWAIT (without an IPI).
*
* New with Core Duo processors, MWAIT can take some hints based on CPU
* capability.
*/
void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
{
if (!need_resched()) {
[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 05:39:04 +00:00
__monitor((void *)&current_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__mwait(ax, cx);
}
}
/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
if (!need_resched()) {
__monitor((void *)&current_thread_info()->flags, 0, 0);
smp_mb();
if (!need_resched())
__sti_mwait(0, 0);
else
local_irq_enable();
} else {
local_irq_enable();
}
}
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
static int printed;
if (cpu_has(c, X86_FEATURE_MWAIT)) {
/*
* Skip, if setup has overridden idle.
* One CPU supports mwait => All CPUs supports mwait
*/
if (!pm_idle) {
if (!printed) {
printk(KERN_INFO "using mwait in idle threads.\n");
printed = 1;
}
pm_idle = mwait_idle;
}
}
}
static int __init idle_setup(char *str)
{
if (!strcmp(str, "poll")) {
printk("using polling idle threads.\n");
pm_idle = poll_idle;
} else if (!strcmp(str, "mwait"))
force_mwait = 1;
else
return -1;
boot_option_idle_override = 1;
return 0;
}
early_param("idle", idle_setup);
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs * regs)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
unsigned long d0, d1, d2, d3, d6, d7;
unsigned int fsindex, gsindex;
unsigned int ds, cs, es;
printk("\n");
print_modules();
printk("Pid: %d, comm: %.20s %s %s %.*s\n",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
printk_address(regs->ip);
printk("RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp,
regs->flags);
printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
regs->ax, regs->bx, regs->cx);
printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
regs->dx, regs->si, regs->di);
printk("RBP: %016lx R08: %016lx R09: %016lx\n",
regs->bp, regs->r8, regs->r9);
printk("R10: %016lx R11: %016lx R12: %016lx\n",
regs->r10, regs->r11, regs->r12);
printk("R13: %016lx R14: %016lx R15: %016lx\n",
regs->r13, regs->r14, regs->r15);
asm("movl %%ds,%0" : "=r" (ds));
asm("movl %%cs,%0" : "=r" (cs));
asm("movl %%es,%0" : "=r" (es));
asm("movl %%fs,%0" : "=r" (fsindex));
asm("movl %%gs,%0" : "=r" (gsindex));
rdmsrl(MSR_FS_BASE, fs);
rdmsrl(MSR_GS_BASE, gs);
rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
cr4 = read_cr4();
printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
fs,fsindex,gs,gsindex,shadowgs);
printk("CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0);
printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
get_debugreg(d0, 0);
get_debugreg(d1, 1);
get_debugreg(d2, 2);
printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
get_debugreg(d3, 3);
get_debugreg(d6, 6);
get_debugreg(d7, 7);
printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}
void show_regs(struct pt_regs *regs)
{
printk("CPU %d:", smp_processor_id());
__show_regs(regs);
show_trace(NULL, regs, (void *)(regs + 1));
}
/*
* Free current thread data structures etc..
*/
void exit_thread(void)
{
struct task_struct *me = current;
struct thread_struct *t = &me->thread;
[PATCH] x86_64 specific function return probes The following patch adds the x86_64 architecture specific implementation for function return probes. Function return probes is a mechanism built on top of kprobes that allows a caller to register a handler to be called when a given function exits. For example, to instrument the return path of sys_mkdir: static int sys_mkdir_exit(struct kretprobe_instance *i, struct pt_regs *regs) { printk("sys_mkdir exited\n"); return 0; } static struct kretprobe return_probe = { .handler = sys_mkdir_exit, }; <inside setup function> return_probe.kp.addr = (kprobe_opcode_t *) kallsyms_lookup_name("sys_mkdir"); if (register_kretprobe(&return_probe)) { printk(KERN_DEBUG "Unable to register return probe!\n"); /* do error path */ } <inside cleanup function> unregister_kretprobe(&return_probe); The way this works is that: * At system initialization time, kernel/kprobes.c installs a kprobe on a function called kretprobe_trampoline() that is implemented in the arch/x86_64/kernel/kprobes.c (More on this later) * When a return probe is registered using register_kretprobe(), kernel/kprobes.c will install a kprobe on the first instruction of the targeted function with the pre handler set to arch_prepare_kretprobe() which is implemented in arch/x86_64/kernel/kprobes.c. * arch_prepare_kretprobe() will prepare a kretprobe instance that stores: - nodes for hanging this instance in an empty or free list - a pointer to the return probe - the original return address - a pointer to the stack address With all this stowed away, arch_prepare_kretprobe() then sets the return address for the targeted function to a special trampoline function called kretprobe_trampoline() implemented in arch/x86_64/kernel/kprobes.c * The kprobe completes as normal, with control passing back to the target function that executes as normal, and eventually returns to our trampoline function. * Since a kprobe was installed on kretprobe_trampoline() during system initialization, control passes back to kprobes via the architecture specific function trampoline_probe_handler() which will lookup the instance in an hlist maintained by kernel/kprobes.c, and then call the handler function. * When trampoline_probe_handler() is done, the kprobes infrastructure single steps the original instruction (in this case just a top), and then calls trampoline_post_handler(). trampoline_post_handler() then looks up the instance again, puts the instance back on the free list, and then makes a long jump back to the original return instruction. So to recap, to instrument the exit path of a function this implementation will cause four interruptions: - A breakpoint at the very beginning of the function allowing us to switch out the return address - A single step interruption to execute the original instruction that we replaced with the break instruction (normal kprobe flow) - A breakpoint in the trampoline function where our instrumented function returned to - A single step interruption to execute the original instruction that we replaced with the break instruction (normal kprobe flow) Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:09:23 +00:00
if (me->thread.io_bitmap_ptr) {
struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
kfree(t->io_bitmap_ptr);
t->io_bitmap_ptr = NULL;
clear_thread_flag(TIF_IO_BITMAP);
/*
* Careful, clear this in the TSS too:
*/
memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
t->io_bitmap_max = 0;
put_cpu();
}
}
void flush_thread(void)
{
struct task_struct *tsk = current;
if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
if (test_tsk_thread_flag(tsk, TIF_IA32)) {
clear_tsk_thread_flag(tsk, TIF_IA32);
} else {
set_tsk_thread_flag(tsk, TIF_IA32);
current_thread_info()->status |= TS_COMPAT;
}
}
clear_tsk_thread_flag(tsk, TIF_DEBUG);
tsk->thread.debugreg0 = 0;
tsk->thread.debugreg1 = 0;
tsk->thread.debugreg2 = 0;
tsk->thread.debugreg3 = 0;
tsk->thread.debugreg6 = 0;
tsk->thread.debugreg7 = 0;
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
/*
* Forget coprocessor state..
*/
clear_fpu(tsk);
clear_used_math();
}
void release_thread(struct task_struct *dead_task)
{
if (dead_task->mm) {
if (dead_task->mm->context.size) {
printk("WARNING: dead process %8s still has LDT? <%p/%d>\n",
dead_task->comm,
dead_task->mm->context.ldt,
dead_task->mm->context.size);
BUG();
}
}
}
static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
{
struct user_desc ud = {
.base_addr = addr,
.limit = 0xfffff,
.seg_32bit = 1,
.limit_in_pages = 1,
.useable = 1,
};
struct n_desc_struct *desc = (void *)t->thread.tls_array;
desc += tls;
desc->a = LDT_entry_a(&ud);
desc->b = LDT_entry_b(&ud);
}
static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
return get_desc_base(&t->thread.tls_array[tls]);
}
/*
* This gets called before we allocate a new thread and copy
* the current task into it.
*/
void prepare_to_copy(struct task_struct *tsk)
{
unlazy_fpu(tsk);
}
int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
unsigned long unused,
struct task_struct * p, struct pt_regs * regs)
{
int err;
struct pt_regs * childregs;
struct task_struct *me = current;
childregs = ((struct pt_regs *)
(THREAD_SIZE + task_stack_page(p))) - 1;
*childregs = *regs;
childregs->ax = 0;
childregs->sp = sp;
if (sp == ~0UL)
childregs->sp = (unsigned long)childregs;
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
p->thread.usersp = me->thread.usersp;
set_tsk_thread_flag(p, TIF_FORK);
p->thread.fs = me->thread.fs;
p->thread.gs = me->thread.gs;
asm("mov %%gs,%0" : "=m" (p->thread.gsindex));
asm("mov %%fs,%0" : "=m" (p->thread.fsindex));
asm("mov %%es,%0" : "=m" (p->thread.es));
asm("mov %%ds,%0" : "=m" (p->thread.ds));
if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
if (!p->thread.io_bitmap_ptr) {
p->thread.io_bitmap_max = 0;
return -ENOMEM;
}
memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
IO_BITMAP_BYTES);
set_tsk_thread_flag(p, TIF_IO_BITMAP);
}
/*
* Set a new TLS for the child thread?
*/
if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
if (test_thread_flag(TIF_IA32))
err = do_set_thread_area(p, -1,
(struct user_desc __user *)childregs->si, 0);
else
#endif
err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8);
if (err)
goto out;
}
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
/*
* This special macro can be used to load a debugging register
*/
#define loaddebug(thread, r) set_debugreg(thread->debugreg ## r, r)
/*
* Capture the user space registers if the task is not running (in user space)
*/
int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
{
struct pt_regs *pp, ptregs;
pp = task_pt_regs(tsk);
ptregs = *pp;
ptregs.cs &= 0xffff;
ptregs.ss &= 0xffff;
elf_core_copy_regs(regs, &ptregs);
return 1;
}
static inline void __switch_to_xtra(struct task_struct *prev_p,
struct task_struct *next_p,
struct tss_struct *tss)
{
struct thread_struct *prev, *next;
unsigned long debugctl;
prev = &prev_p->thread,
next = &next_p->thread;
debugctl = prev->debugctlmsr;
if (next->ds_area_msr != prev->ds_area_msr) {
/* we clear debugctl to make sure DS
* is not in use when we change it */
debugctl = 0;
wrmsrl(MSR_IA32_DEBUGCTLMSR, 0);
wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr);
}
if (next->debugctlmsr != debugctl)
wrmsrl(MSR_IA32_DEBUGCTLMSR, next->debugctlmsr);
if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
loaddebug(next, 0);
loaddebug(next, 1);
loaddebug(next, 2);
loaddebug(next, 3);
/* no 4 and 5 */
loaddebug(next, 6);
loaddebug(next, 7);
}
if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
/*
* Copy the relevant range of the IO bitmap.
* Normally this is 128 bytes or less:
*/
memcpy(tss->io_bitmap, next->io_bitmap_ptr,
max(prev->io_bitmap_max, next->io_bitmap_max));
} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
/*
* Clear any possible leftover bits:
*/
memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
}
/*
* Last branch recording recofiguration of trace hardware and
* disentangling of trace data per task.
*/
if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS))
ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS);
if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS))
ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES);
}
/*
* switch_to(x,y) should switch tasks from x to y.
*
* This could still be optimized:
* - fold all the options into a flag word and test it with a single test.
* - could test fs/gs bitsliced
*
* Kprobes not supported here. Set the probe on schedule instead.
*/
struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
/* we're going to use this soon, after a few expensive things */
if (next_p->fpu_counter>5)
prefetch(&next->i387.fxsave);
/*
* Reload esp0, LDT and the page table pointer:
*/
tss->sp0 = next->sp0;
/*
* Switch DS and ES.
* This won't pick up thread selector changes, but I guess that is ok.
*/
asm volatile("mov %%es,%0" : "=m" (prev->es));
if (unlikely(next->es | prev->es))
loadsegment(es, next->es);
asm volatile ("mov %%ds,%0" : "=m" (prev->ds));
if (unlikely(next->ds | prev->ds))
loadsegment(ds, next->ds);
load_TLS(next, cpu);
/*
* Switch FS and GS.
*/
{
unsigned fsindex;
asm volatile("movl %%fs,%0" : "=r" (fsindex));
/* segment register != 0 always requires a reload.
also reload when it has changed.
when prev process used 64bit base always reload
to avoid an information leak. */
if (unlikely(fsindex | next->fsindex | prev->fs)) {
loadsegment(fs, next->fsindex);
/* check if the user used a selector != 0
* if yes clear 64bit base, since overloaded base
* is always mapped to the Null selector
*/
if (fsindex)
prev->fs = 0;
}
/* when next process has a 64bit base use it */
if (next->fs)
wrmsrl(MSR_FS_BASE, next->fs);
prev->fsindex = fsindex;
}
{
unsigned gsindex;
asm volatile("movl %%gs,%0" : "=r" (gsindex));
if (unlikely(gsindex | next->gsindex | prev->gs)) {
load_gs_index(next->gsindex);
if (gsindex)
prev->gs = 0;
}
if (next->gs)
wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
prev->gsindex = gsindex;
}
/* Must be after DS reload */
unlazy_fpu(prev_p);
/*
* Switch the PDA and FPU contexts.
*/
prev->usersp = read_pda(oldrsp);
write_pda(oldrsp, next->usersp);
write_pda(pcurrent, next_p);
write_pda(kernelstack,
(unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
#ifdef CONFIG_CC_STACKPROTECTOR
write_pda(stack_canary, next_p->stack_canary);
/*
* Build time only check to make sure the stack_canary is at
* offset 40 in the pda; this is a gcc ABI requirement
*/
BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
#endif
/*
* Now maybe reload the debug registers and handle I/O bitmaps
*/
if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT ||
task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
__switch_to_xtra(prev_p, next_p, tss);
/* If the task has used fpu the last 5 timeslices, just do a full
* restore of the math state immediately to avoid the trap; the
* chances of needing FPU soon are obviously high now
*/
if (next_p->fpu_counter>5)
math_state_restore();
return prev_p;
}
/*
* sys_execve() executes a new program.
*/
asmlinkage
long sys_execve(char __user *name, char __user * __user *argv,
char __user * __user *envp, struct pt_regs regs)
{
long error;
char * filename;
filename = getname(name);
error = PTR_ERR(filename);
if (IS_ERR(filename))
return error;
error = do_execve(filename, argv, envp, &regs);
putname(filename);
return error;
}
void set_personality_64bit(void)
{
/* inherit personality from parent */
/* Make sure to be in 64bit mode */
clear_thread_flag(TIF_IA32);
/* TBD: overwrites user setup. Should have two bits.
But 64bit processes have always behaved this way,
so it's not too bad. The main problem is just that
32bit childs are affected again. */
current->personality &= ~READ_IMPLIES_EXEC;
}
asmlinkage long sys_fork(struct pt_regs *regs)
{
return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL);
}
asmlinkage long
sys_clone(unsigned long clone_flags, unsigned long newsp,
void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
{
if (!newsp)
newsp = regs->sp;
return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
}
/*
* 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(struct pt_regs *regs)
{
return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0,
NULL, NULL);
}
unsigned long get_wchan(struct task_struct *p)
{
unsigned long stack;
u64 fp,ip;
int count = 0;
if (!p || p == current || p->state==TASK_RUNNING)
return 0;
stack = (unsigned long)task_stack_page(p);
if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE)
return 0;
fp = *(u64 *)(p->thread.sp);
do {
if (fp < (unsigned long)stack ||
fp > (unsigned long)stack+THREAD_SIZE)
return 0;
ip = *(u64 *)(fp+8);
if (!in_sched_functions(ip))
return ip;
fp = *(u64 *)fp;
} while (count++ < 16);
return 0;
}
long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
{
int ret = 0;
int doit = task == current;
int cpu;
switch (code) {
case ARCH_SET_GS:
if (addr >= TASK_SIZE_OF(task))
return -EPERM;
cpu = get_cpu();
/* handle small bases via the GDT because that's faster to
switch. */
if (addr <= 0xffffffff) {
set_32bit_tls(task, GS_TLS, addr);
if (doit) {
load_TLS(&task->thread, cpu);
load_gs_index(GS_TLS_SEL);
}
task->thread.gsindex = GS_TLS_SEL;
task->thread.gs = 0;
} else {
task->thread.gsindex = 0;
task->thread.gs = addr;
if (doit) {
load_gs_index(0);
ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
}
}
put_cpu();
break;
case ARCH_SET_FS:
/* Not strictly needed for fs, but do it for symmetry
with gs */
if (addr >= TASK_SIZE_OF(task))
return -EPERM;
cpu = get_cpu();
/* handle small bases via the GDT because that's faster to
switch. */
if (addr <= 0xffffffff) {
set_32bit_tls(task, FS_TLS, addr);
if (doit) {
load_TLS(&task->thread, cpu);
asm volatile("movl %0,%%fs" :: "r"(FS_TLS_SEL));
}
task->thread.fsindex = FS_TLS_SEL;
task->thread.fs = 0;
} else {
task->thread.fsindex = 0;
task->thread.fs = addr;
if (doit) {
/* set the selector to 0 to not confuse
__switch_to */
asm volatile("movl %0,%%fs" :: "r" (0));
ret = checking_wrmsrl(MSR_FS_BASE, addr);
}
}
put_cpu();
break;
case ARCH_GET_FS: {
unsigned long base;
if (task->thread.fsindex == FS_TLS_SEL)
base = read_32bit_tls(task, FS_TLS);
else if (doit)
rdmsrl(MSR_FS_BASE, base);
else
base = task->thread.fs;
ret = put_user(base, (unsigned long __user *)addr);
break;
}
case ARCH_GET_GS: {
unsigned long base;
[PATCH] x86_64: Plug GS leak in arch_prctl() In linux-2.6.16, we have noticed a problem where the gs base value returned from an arch_prtcl(ARCH_GET_GS, ...) call will be incorrect if: - the current/calling task has NOT set its own gs base yet to a non-zero value, - some other task that ran on the same processor previously set their own gs base to a non-zero value. In this situation, the ARCH_GET_GS code will read and return the MSR_KERNEL_GS_BASE msr register. However, since the __switch_to() code does NOT load/zero the MSR_KERNEL_GS_BASE register when the task that is switched IN has a zero next->gs value, the caller of arch_prctl(ARCH_GET_GS, ...) will get back the value of some previous tasks's gs base value instead of 0. Change the arch_prctl() ARCH_GET_GS code to only read and return the MSR_KERNEL_GS_BASE msr register if the 'gs' register of the calling task is non-zero. Side note: Since in addition to using arch_prctl(ARCH_SET_GS, ...), a task can also setup a gs base value by using modify_ldt() and write an index value into 'gs' from user space, the patch below reads 'gs' instead of using thread.gs, since in the modify_ldt() case, the thread.gs value will be 0, and incorrect value would be returned (the task->thread.gs value). When the user has not set its own gs base value and the 'gs' register is zero, then the MSR_KERNEL_GS_BASE register will not be read and a value of zero will be returned by reading and returning 'task->thread.gs'. The first patch shown below is an attempt at implementing this approach. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-07 17:50:25 +00:00
unsigned gsindex;
if (task->thread.gsindex == GS_TLS_SEL)
base = read_32bit_tls(task, GS_TLS);
[PATCH] x86_64: Plug GS leak in arch_prctl() In linux-2.6.16, we have noticed a problem where the gs base value returned from an arch_prtcl(ARCH_GET_GS, ...) call will be incorrect if: - the current/calling task has NOT set its own gs base yet to a non-zero value, - some other task that ran on the same processor previously set their own gs base to a non-zero value. In this situation, the ARCH_GET_GS code will read and return the MSR_KERNEL_GS_BASE msr register. However, since the __switch_to() code does NOT load/zero the MSR_KERNEL_GS_BASE register when the task that is switched IN has a zero next->gs value, the caller of arch_prctl(ARCH_GET_GS, ...) will get back the value of some previous tasks's gs base value instead of 0. Change the arch_prctl() ARCH_GET_GS code to only read and return the MSR_KERNEL_GS_BASE msr register if the 'gs' register of the calling task is non-zero. Side note: Since in addition to using arch_prctl(ARCH_SET_GS, ...), a task can also setup a gs base value by using modify_ldt() and write an index value into 'gs' from user space, the patch below reads 'gs' instead of using thread.gs, since in the modify_ldt() case, the thread.gs value will be 0, and incorrect value would be returned (the task->thread.gs value). When the user has not set its own gs base value and the 'gs' register is zero, then the MSR_KERNEL_GS_BASE register will not be read and a value of zero will be returned by reading and returning 'task->thread.gs'. The first patch shown below is an attempt at implementing this approach. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-07 17:50:25 +00:00
else if (doit) {
asm("movl %%gs,%0" : "=r" (gsindex));
[PATCH] x86_64: Plug GS leak in arch_prctl() In linux-2.6.16, we have noticed a problem where the gs base value returned from an arch_prtcl(ARCH_GET_GS, ...) call will be incorrect if: - the current/calling task has NOT set its own gs base yet to a non-zero value, - some other task that ran on the same processor previously set their own gs base to a non-zero value. In this situation, the ARCH_GET_GS code will read and return the MSR_KERNEL_GS_BASE msr register. However, since the __switch_to() code does NOT load/zero the MSR_KERNEL_GS_BASE register when the task that is switched IN has a zero next->gs value, the caller of arch_prctl(ARCH_GET_GS, ...) will get back the value of some previous tasks's gs base value instead of 0. Change the arch_prctl() ARCH_GET_GS code to only read and return the MSR_KERNEL_GS_BASE msr register if the 'gs' register of the calling task is non-zero. Side note: Since in addition to using arch_prctl(ARCH_SET_GS, ...), a task can also setup a gs base value by using modify_ldt() and write an index value into 'gs' from user space, the patch below reads 'gs' instead of using thread.gs, since in the modify_ldt() case, the thread.gs value will be 0, and incorrect value would be returned (the task->thread.gs value). When the user has not set its own gs base value and the 'gs' register is zero, then the MSR_KERNEL_GS_BASE register will not be read and a value of zero will be returned by reading and returning 'task->thread.gs'. The first patch shown below is an attempt at implementing this approach. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-04-07 17:50:25 +00:00
if (gsindex)
rdmsrl(MSR_KERNEL_GS_BASE, base);
else
base = task->thread.gs;
}
else
base = task->thread.gs;
ret = put_user(base, (unsigned long __user *)addr);
break;
}
default:
ret = -EINVAL;
break;
}
return ret;
}
long sys_arch_prctl(int code, unsigned long addr)
{
return do_arch_prctl(current, code, addr);
}
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
sp -= get_random_int() % 8192;
return sp & ~0xf;
}
x86: randomize brk Randomize the location of the heap (brk) for i386 and x86_64. The range is randomized in the range starting at current brk location up to 0x02000000 offset for both architectures. This, together with pie-executable-randomization.patch and pie-executable-randomization-fix.patch, should make the address space randomization on i386 and x86_64 complete. Arjan says: This is known to break older versions of some emacs variants, whose dumper code assumed that the last variable declared in the program is equal to the start of the dynamically allocated memory region. (The dumper is the code where emacs effectively dumps core at the end of it's compilation stage; this coredump is then loaded as the main program during normal use) iirc this was 5 years or so; we found this way back when I was at RH and we first did the security stuff there (including this brk randomization). It wasn't all variants of emacs, and it got fixed as a result (I vaguely remember that emacs already had code to deal with it for other archs/oses, just ifdeffed wrongly). It's a rare and wrong assumption as a general thing, just on x86 it mostly happened to be true (but to be honest, it'll break too if gcc does something fancy or if the linker does a non-standard order). Still its something we should at least document. Note 2: afaik it only broke the emacs *build*. I'm not 100% sure about that (it IS 5 years ago) though. [ akpm@linux-foundation.org: deuglification ] Signed-off-by: Jiri Kosina <jkosina@suse.cz> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Roland McGrath <roland@redhat.com> Cc: Jakub Jelinek <jakub@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:30:40 +00:00
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
unsigned long range_end = mm->brk + 0x02000000;
return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
}