2005-04-16 15:20:36 -07:00
|
|
|
/*
|
|
|
|
* linux/arch/x86-64/kernel/process.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
|
|
*
|
|
|
|
* Pentium III FXSR, SSE support
|
|
|
|
* Gareth Hughes <gareth@valinux.com>, May 2000
|
|
|
|
*
|
|
|
|
* X86-64 port
|
|
|
|
* Andi Kleen.
|
2005-06-25 14:55:00 -07:00
|
|
|
*
|
|
|
|
* CPU hotplug support - ashok.raj@intel.com
|
2005-04-16 15:20:36 -07:00
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This file handles the architecture-dependent parts of process handling..
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdarg.h>
|
|
|
|
|
2005-06-25 14:55:00 -07:00
|
|
|
#include <linux/cpu.h>
|
2005-04-16 15:20:36 -07:00
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/sched.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/module.h>
|
|
|
|
#include <linux/a.out.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/delay.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/utsname.h>
|
|
|
|
#include <linux/random.h>
|
2006-01-11 14:44:36 -07:00
|
|
|
#include <linux/notifier.h>
|
2006-03-26 02:38:20 -07:00
|
|
|
#include <linux/kprobes.h>
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
#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/kdebug.h>
|
|
|
|
#include <asm/desc.h>
|
|
|
|
#include <asm/proto.h>
|
|
|
|
#include <asm/ia32.h>
|
2006-01-11 14:44:36 -07:00
|
|
|
#include <asm/idle.h>
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
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);
|
|
|
|
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 02:16:30 -07:00
|
|
|
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
|
2006-01-11 14:44:36 -07:00
|
|
|
|
|
|
|
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 02:16:30 -07:00
|
|
|
atomic_notifier_chain_register(&idle_notifier, n);
|
2006-01-11 14:44:36 -07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(idle_notifier_register);
|
|
|
|
|
|
|
|
void idle_notifier_unregister(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 02:16:30 -07:00
|
|
|
atomic_notifier_chain_unregister(&idle_notifier, n);
|
2006-01-11 14:44:36 -07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(idle_notifier_unregister);
|
|
|
|
|
|
|
|
enum idle_state { CPU_IDLE, CPU_NOT_IDLE };
|
|
|
|
static DEFINE_PER_CPU(enum idle_state, idle_state) = CPU_NOT_IDLE;
|
|
|
|
|
|
|
|
void enter_idle(void)
|
|
|
|
{
|
|
|
|
__get_cpu_var(idle_state) = CPU_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 02:16:30 -07:00
|
|
|
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
|
2006-01-11 14:44:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit_idle(void)
|
|
|
|
{
|
|
|
|
__get_cpu_var(idle_state) = CPU_NOT_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 02:16:30 -07:00
|
|
|
atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
|
2006-01-11 14:44:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Called from interrupts to signify idle end */
|
|
|
|
void exit_idle(void)
|
|
|
|
{
|
|
|
|
if (current->pid | read_pda(irqcount))
|
|
|
|
return;
|
|
|
|
__exit_idle();
|
|
|
|
}
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
/*
|
|
|
|
* We use this if we don't have any better
|
|
|
|
* idle routine..
|
|
|
|
*/
|
2006-03-24 04:15:57 -07:00
|
|
|
static void default_idle(void)
|
2005-04-16 15:20:36 -07:00
|
|
|
{
|
[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>
2005-11-08 22:39:04 -07:00
|
|
|
local_irq_enable();
|
|
|
|
|
2006-06-26 04:59:11 -07:00
|
|
|
current_thread_info()->status &= ~TS_POLLING;
|
2006-01-11 14:42:42 -07:00
|
|
|
smp_mb__after_clear_bit();
|
|
|
|
while (!need_resched()) {
|
|
|
|
local_irq_disable();
|
|
|
|
if (!need_resched())
|
|
|
|
safe_halt();
|
|
|
|
else
|
|
|
|
local_irq_enable();
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
2006-06-26 04:59:11 -07:00
|
|
|
current_thread_info()->status |= TS_POLLING;
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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();
|
|
|
|
|
[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>
2005-11-08 22:39:04 -07:00
|
|
|
asm volatile(
|
|
|
|
"2:"
|
|
|
|
"testl %0,%1;"
|
|
|
|
"rep; nop;"
|
|
|
|
"je 2b;"
|
|
|
|
: :
|
|
|
|
"i" (_TIF_NEED_RESCHED),
|
|
|
|
"m" (current_thread_info()->flags));
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
void cpu_idle_wait(void)
|
|
|
|
{
|
|
|
|
unsigned int cpu, this_cpu = get_cpu();
|
|
|
|
cpumask_t map;
|
|
|
|
|
|
|
|
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) {
|
2005-11-05 09:25:54 -07:00
|
|
|
if (cpu_isset(cpu, map) &&
|
|
|
|
!per_cpu(cpu_idle_state, cpu))
|
2005-04-16 15:20:36 -07:00
|
|
|
cpu_clear(cpu, map);
|
|
|
|
}
|
|
|
|
cpus_and(map, map, cpu_online_map);
|
|
|
|
} while (!cpus_empty(map));
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(cpu_idle_wait);
|
|
|
|
|
2005-06-25 14:55:00 -07:00
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
DECLARE_PER_CPU(int, cpu_state);
|
|
|
|
|
|
|
|
#include <asm/nmi.h>
|
2006-01-06 01:12:20 -07:00
|
|
|
/* We halt the CPU with physical CPU hotplug */
|
2005-06-25 14:55:00 -07:00
|
|
|
static inline void play_dead(void)
|
|
|
|
{
|
|
|
|
idle_task_exit();
|
|
|
|
wbinvd();
|
|
|
|
mb();
|
|
|
|
/* Ack it */
|
|
|
|
__get_cpu_var(cpu_state) = CPU_DEAD;
|
|
|
|
|
2006-01-06 01:12:20 -07:00
|
|
|
local_irq_disable();
|
2005-06-25 14:55:00 -07:00
|
|
|
while (1)
|
2006-01-06 01:12:20 -07:00
|
|
|
halt();
|
2005-06-25 14:55:00 -07:00
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void play_dead(void)
|
|
|
|
{
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
{
|
2006-06-26 04:59:11 -07:00
|
|
|
current_thread_info()->status |= TS_POLLING;
|
2005-04-16 15:20:36 -07:00
|
|
|
/* 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;
|
|
|
|
|
|
|
|
rmb();
|
|
|
|
idle = pm_idle;
|
|
|
|
if (!idle)
|
|
|
|
idle = default_idle;
|
2005-06-25 14:55:00 -07:00
|
|
|
if (cpu_is_offline(smp_processor_id()))
|
|
|
|
play_dead();
|
2006-01-11 14:44:36 -07:00
|
|
|
enter_idle();
|
2005-04-16 15:20:36 -07:00
|
|
|
idle();
|
2006-01-11 14:44:36 -07:00
|
|
|
__exit_idle();
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
|
2005-11-08 22:39:01 -07:00
|
|
|
preempt_enable_no_resched();
|
2005-04-16 15:20:36 -07:00
|
|
|
schedule();
|
2005-11-08 22:39:01 -07:00
|
|
|
preempt_disable();
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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).
|
|
|
|
*/
|
|
|
|
static void mwait_idle(void)
|
|
|
|
{
|
|
|
|
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>
2005-11-08 22:39:04 -07:00
|
|
|
while (!need_resched()) {
|
|
|
|
__monitor((void *)¤t_thread_info()->flags, 0, 0);
|
|
|
|
smp_mb();
|
|
|
|
if (need_resched())
|
|
|
|
break;
|
|
|
|
__mwait(0, 0);
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[PATCH] x86_64: Change init sections for CPU hotplug support
This patch adds __cpuinit and __cpuinitdata sections that need to exist past
boot to support cpu hotplug.
Caveat: This is done *only* for EM64T CPU Hotplug support, on request from
Andi Kleen. Much of the generic hotplug code in kernel, and none of the other
archs that support CPU hotplug today, i386, ia64, ppc64, s390 and parisc dont
mark sections with __cpuinit, but only mark them as __devinit, and
__devinitdata.
If someone is motivated to change generic code, we need to make sure all
existing hotplug code does not break, on other arch's that dont use __cpuinit,
and __cpudevinit.
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Acked-by: Andi Kleen <ak@muc.de>
Acked-by: Zwane Mwaikambo <zwane@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-25 14:54:58 -07:00
|
|
|
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
|
2005-04-16 15:20:36 -07:00
|
|
|
{
|
|
|
|
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("using mwait in idle threads.\n");
|
|
|
|
printed = 1;
|
|
|
|
}
|
|
|
|
pm_idle = mwait_idle;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __init idle_setup (char *str)
|
|
|
|
{
|
|
|
|
if (!strncmp(str, "poll", 4)) {
|
|
|
|
printk("using polling idle threads.\n");
|
|
|
|
pm_idle = poll_idle;
|
|
|
|
}
|
|
|
|
|
|
|
|
boot_option_idle_override = 1;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
__setup("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 int fsindex,gsindex;
|
|
|
|
unsigned int ds,cs,es;
|
|
|
|
|
|
|
|
printk("\n");
|
|
|
|
print_modules();
|
2005-09-12 09:49:24 -07:00
|
|
|
printk("Pid: %d, comm: %.20s %s %s %.*s\n",
|
|
|
|
current->pid, current->comm, print_tainted(),
|
|
|
|
system_utsname.release,
|
|
|
|
(int)strcspn(system_utsname.version, " "),
|
|
|
|
system_utsname.version);
|
2005-04-16 15:20:36 -07:00
|
|
|
printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
|
|
|
|
printk_address(regs->rip);
|
2005-11-05 09:25:54 -07:00
|
|
|
printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp,
|
|
|
|
regs->eflags);
|
2005-04-16 15:20:36 -07:00
|
|
|
printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
|
|
|
|
regs->rax, regs->rbx, regs->rcx);
|
|
|
|
printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
|
|
|
|
regs->rdx, regs->rsi, regs->rdi);
|
|
|
|
printk("RBP: %016lx R08: %016lx R09: %016lx\n",
|
|
|
|
regs->rbp, 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);
|
|
|
|
|
|
|
|
asm("movq %%cr0, %0": "=r" (cr0));
|
|
|
|
asm("movq %%cr2, %0": "=r" (cr2));
|
|
|
|
asm("movq %%cr3, %0": "=r" (cr3));
|
|
|
|
asm("movq %%cr4, %0": "=r" (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);
|
|
|
|
}
|
|
|
|
|
|
|
|
void show_regs(struct pt_regs *regs)
|
|
|
|
{
|
2005-09-06 15:16:16 -07:00
|
|
|
printk("CPU %d:", smp_processor_id());
|
2005-04-16 15:20:36 -07:00
|
|
|
__show_regs(regs);
|
2006-06-26 04:57:32 -07:00
|
|
|
show_trace(NULL, regs, (void *)(regs + 1));
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 00:09:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
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;
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
struct thread_info *t = current_thread_info();
|
|
|
|
|
2006-06-26 04:57:19 -07:00
|
|
|
if (t->flags & _TIF_ABI_PENDING) {
|
2005-04-16 15:20:36 -07:00
|
|
|
t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);
|
2006-06-26 04:57:19 -07:00
|
|
|
if (t->flags & _TIF_IA32)
|
|
|
|
current_thread_info()->status |= TS_COMPAT;
|
|
|
|
}
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
|
|
|
struct desc_struct *desc = (void *)t->thread.tls_array;
|
|
|
|
desc += tls;
|
|
|
|
return desc->base0 |
|
|
|
|
(((u32)desc->base1) << 16) |
|
|
|
|
(((u32)desc->base2) << 24);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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 rsp,
|
|
|
|
unsigned long unused,
|
|
|
|
struct task_struct * p, struct pt_regs * regs)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct pt_regs * childregs;
|
|
|
|
struct task_struct *me = current;
|
|
|
|
|
2005-11-05 09:25:54 -07:00
|
|
|
childregs = ((struct pt_regs *)
|
2006-01-12 02:05:39 -07:00
|
|
|
(THREAD_SIZE + task_stack_page(p))) - 1;
|
2005-04-16 15:20:36 -07:00
|
|
|
*childregs = *regs;
|
|
|
|
|
|
|
|
childregs->rax = 0;
|
|
|
|
childregs->rsp = rsp;
|
2005-11-05 09:25:54 -07:00
|
|
|
if (rsp == ~0UL)
|
2005-04-16 15:20:36 -07:00
|
|
|
childregs->rsp = (unsigned long)childregs;
|
|
|
|
|
|
|
|
p->thread.rsp = (unsigned long) childregs;
|
|
|
|
p->thread.rsp0 = (unsigned long) (childregs+1);
|
|
|
|
p->thread.userrsp = me->thread.userrsp;
|
|
|
|
|
2006-01-12 02:05:38 -07:00
|
|
|
set_tsk_thread_flag(p, TIF_FORK);
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
p->thread.fs = me->thread.fs;
|
|
|
|
p->thread.gs = me->thread.gs;
|
|
|
|
|
[PATCH] i386/x86_64 segment register access update
The new i386/x86_64 assemblers no longer accept instructions for moving
between a segment register and a 32bit memory location, i.e.,
movl (%eax),%ds
movl %ds,(%eax)
To generate instructions for moving between a segment register and a
16bit memory location without the 16bit operand size prefix, 0x66,
mov (%eax),%ds
mov %ds,(%eax)
should be used. It will work with both new and old assemblers. The
assembler starting from 2.16.90.0.1 will also support
movw (%eax),%ds
movw %ds,(%eax)
without the 0x66 prefix. I am enclosing patches for 2.4 and 2.6 kernels
here. The resulting kernel binaries should be unchanged as before, with
old and new assemblers, if gcc never generates memory access for
unsigned gsindex;
asm volatile("movl %%gs,%0" : "=g" (gsindex));
If gcc does generate memory access for the code above, the upper bits
in gsindex are undefined and the new assembler doesn't allow it.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 08:58:48 -07:00
|
|
|
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));
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
if (unlikely(me->thread.io_bitmap_ptr != NULL)) {
|
|
|
|
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;
|
|
|
|
}
|
2005-11-05 09:25:54 -07:00
|
|
|
memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr,
|
|
|
|
IO_BITMAP_BYTES);
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set a new TLS for the child thread?
|
|
|
|
*/
|
|
|
|
if (clone_flags & CLONE_SETTLS) {
|
|
|
|
#ifdef CONFIG_IA32_EMULATION
|
|
|
|
if (test_thread_flag(TIF_IA32))
|
|
|
|
err = ia32_child_tls(p, childregs);
|
|
|
|
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
|
|
|
|
*/
|
2006-03-25 08:29:22 -07:00
|
|
|
#define loaddebug(thread,r) set_debugreg(thread->debugreg ## r, r)
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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
|
2006-02-03 13:51:38 -07:00
|
|
|
*
|
|
|
|
* Kprobes not supported here. Set the probe on schedule instead.
|
2005-04-16 15:20:36 -07:00
|
|
|
*/
|
2006-02-03 13:51:38 -07:00
|
|
|
__kprobes struct task_struct *
|
2005-11-05 09:25:54 -07:00
|
|
|
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
|
2005-04-16 15:20:36 -07:00
|
|
|
{
|
|
|
|
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);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reload esp0, LDT and the page table pointer:
|
|
|
|
*/
|
|
|
|
tss->rsp0 = next->rsp0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Switch DS and ES.
|
|
|
|
* This won't pick up thread selector changes, but I guess that is ok.
|
|
|
|
*/
|
[PATCH] i386/x86_64 segment register access update
The new i386/x86_64 assemblers no longer accept instructions for moving
between a segment register and a 32bit memory location, i.e.,
movl (%eax),%ds
movl %ds,(%eax)
To generate instructions for moving between a segment register and a
16bit memory location without the 16bit operand size prefix, 0x66,
mov (%eax),%ds
mov %ds,(%eax)
should be used. It will work with both new and old assemblers. The
assembler starting from 2.16.90.0.1 will also support
movw (%eax),%ds
movw %ds,(%eax)
without the 0x66 prefix. I am enclosing patches for 2.4 and 2.6 kernels
here. The resulting kernel binaries should be unchanged as before, with
old and new assemblers, if gcc never generates memory access for
unsigned gsindex;
asm volatile("movl %%gs,%0" : "=g" (gsindex));
If gcc does generate memory access for the code above, the upper bits
in gsindex are undefined and the new assembler doesn't allow it.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 08:58:48 -07:00
|
|
|
asm volatile("mov %%es,%0" : "=m" (prev->es));
|
2005-04-16 15:20:36 -07:00
|
|
|
if (unlikely(next->es | prev->es))
|
|
|
|
loadsegment(es, next->es);
|
|
|
|
|
[PATCH] i386/x86_64 segment register access update
The new i386/x86_64 assemblers no longer accept instructions for moving
between a segment register and a 32bit memory location, i.e.,
movl (%eax),%ds
movl %ds,(%eax)
To generate instructions for moving between a segment register and a
16bit memory location without the 16bit operand size prefix, 0x66,
mov (%eax),%ds
mov %ds,(%eax)
should be used. It will work with both new and old assemblers. The
assembler starting from 2.16.90.0.1 will also support
movw (%eax),%ds
movw %ds,(%eax)
without the 0x66 prefix. I am enclosing patches for 2.4 and 2.6 kernels
here. The resulting kernel binaries should be unchanged as before, with
old and new assemblers, if gcc never generates memory access for
unsigned gsindex;
asm volatile("movl %%gs,%0" : "=g" (gsindex));
If gcc does generate memory access for the code above, the upper bits
in gsindex are undefined and the new assembler doesn't allow it.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 08:58:48 -07:00
|
|
|
asm volatile ("mov %%ds,%0" : "=m" (prev->ds));
|
2005-04-16 15:20:36 -07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2006-03-25 08:29:25 -07:00
|
|
|
* Switch the PDA and FPU contexts.
|
2005-04-16 15:20:36 -07:00
|
|
|
*/
|
|
|
|
prev->userrsp = read_pda(oldrsp);
|
|
|
|
write_pda(oldrsp, next->userrsp);
|
|
|
|
write_pda(pcurrent, next_p);
|
2006-04-19 17:36:45 -07:00
|
|
|
|
2006-03-25 08:29:25 -07:00
|
|
|
/* This must be here to ensure both math_state_restore() and
|
2006-04-19 17:36:45 -07:00
|
|
|
kernel_fpu_begin() work consistently.
|
|
|
|
And the AMD workaround requires it to be after DS reload. */
|
2006-03-25 08:29:25 -07:00
|
|
|
unlazy_fpu(prev_p);
|
2005-11-05 09:25:54 -07:00
|
|
|
write_pda(kernelstack,
|
2006-01-12 02:05:39 -07:00
|
|
|
task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Now maybe reload the debug registers
|
|
|
|
*/
|
|
|
|
if (unlikely(next->debugreg7)) {
|
|
|
|
loaddebug(next, 0);
|
|
|
|
loaddebug(next, 1);
|
|
|
|
loaddebug(next, 2);
|
|
|
|
loaddebug(next, 3);
|
|
|
|
/* no 4 and 5 */
|
|
|
|
loaddebug(next, 6);
|
|
|
|
loaddebug(next, 7);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle the IO bitmap
|
|
|
|
*/
|
|
|
|
if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) {
|
|
|
|
if (next->io_bitmap_ptr)
|
|
|
|
/*
|
|
|
|
* 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 {
|
|
|
|
/*
|
|
|
|
* Clear any possible leftover bits:
|
|
|
|
*/
|
|
|
|
memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
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, ®s);
|
|
|
|
if (error == 0) {
|
|
|
|
task_lock(current);
|
|
|
|
current->ptrace &= ~PT_DTRACE;
|
|
|
|
task_unlock(current);
|
|
|
|
}
|
|
|
|
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->rsp, regs, 0, NULL, NULL);
|
|
|
|
}
|
|
|
|
|
2005-11-05 09:25:54 -07:00
|
|
|
asmlinkage long
|
|
|
|
sys_clone(unsigned long clone_flags, unsigned long newsp,
|
|
|
|
void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
|
2005-04-16 15:20:36 -07:00
|
|
|
{
|
|
|
|
if (!newsp)
|
|
|
|
newsp = regs->rsp;
|
|
|
|
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->rsp, regs, 0,
|
|
|
|
NULL, NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long get_wchan(struct task_struct *p)
|
|
|
|
{
|
|
|
|
unsigned long stack;
|
|
|
|
u64 fp,rip;
|
|
|
|
int count = 0;
|
|
|
|
|
|
|
|
if (!p || p == current || p->state==TASK_RUNNING)
|
|
|
|
return 0;
|
2006-01-12 02:05:39 -07:00
|
|
|
stack = (unsigned long)task_stack_page(p);
|
2005-04-16 15:20:36 -07:00
|
|
|
if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE)
|
|
|
|
return 0;
|
|
|
|
fp = *(u64 *)(p->thread.rsp);
|
|
|
|
do {
|
2005-11-05 09:25:54 -07:00
|
|
|
if (fp < (unsigned long)stack ||
|
|
|
|
fp > (unsigned long)stack+THREAD_SIZE)
|
2005-04-16 15:20:36 -07:00
|
|
|
return 0;
|
|
|
|
rip = *(u64 *)(fp+8);
|
|
|
|
if (!in_sched_functions(rip))
|
|
|
|
return rip;
|
|
|
|
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:
|
[PATCH] x86_64: TASK_SIZE fixes for compatibility mode processes
Appended patch will setup compatibility mode TASK_SIZE properly. This will
fix atleast three known bugs that can be encountered while running
compatibility mode apps.
a) A malicious 32bit app can have an elf section at 0xffffe000. During
exec of this app, we will have a memory leak as insert_vm_struct() is
not checking for return value in syscall32_setup_pages() and thus not
freeing the vma allocated for the vsyscall page. And instead of exec
failing (as it has addresses > TASK_SIZE), we were allowing it to
succeed previously.
b) With a 32bit app, hugetlb_get_unmapped_area/arch_get_unmapped_area
may return addresses beyond 32bits, ultimately causing corruption
because of wrap-around and resulting in SEGFAULT, instead of returning
ENOMEM.
c) 32bit app doing this below mmap will now fail.
mmap((void *)(0xFFFFE000UL), 0x10000UL, PROT_READ|PROT_WRITE,
MAP_FIXED|MAP_PRIVATE|MAP_ANON, 0, 0);
Signed-off-by: Zou Nan hai <nanhai.zou@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-21 17:14:32 -07:00
|
|
|
if (addr >= TASK_SIZE_OF(task))
|
2005-04-16 15:20:36 -07:00
|
|
|
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) {
|
2005-11-05 09:25:54 -07:00
|
|
|
load_gs_index(0);
|
|
|
|
ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr);
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
put_cpu();
|
|
|
|
break;
|
|
|
|
case ARCH_SET_FS:
|
|
|
|
/* Not strictly needed for fs, but do it for symmetry
|
|
|
|
with gs */
|
[PATCH] x86_64: TASK_SIZE fixes for compatibility mode processes
Appended patch will setup compatibility mode TASK_SIZE properly. This will
fix atleast three known bugs that can be encountered while running
compatibility mode apps.
a) A malicious 32bit app can have an elf section at 0xffffe000. During
exec of this app, we will have a memory leak as insert_vm_struct() is
not checking for return value in syscall32_setup_pages() and thus not
freeing the vma allocated for the vsyscall page. And instead of exec
failing (as it has addresses > TASK_SIZE), we were allowing it to
succeed previously.
b) With a 32bit app, hugetlb_get_unmapped_area/arch_get_unmapped_area
may return addresses beyond 32bits, ultimately causing corruption
because of wrap-around and resulting in SEGFAULT, instead of returning
ENOMEM.
c) 32bit app doing this below mmap will now fail.
mmap((void *)(0xFFFFE000UL), 0x10000UL, PROT_READ|PROT_WRITE,
MAP_FIXED|MAP_PRIVATE|MAP_ANON, 0, 0);
Signed-off-by: Zou Nan hai <nanhai.zou@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-21 17:14:32 -07:00
|
|
|
if (addr >= TASK_SIZE_OF(task))
|
2005-04-16 15:20:36 -07:00
|
|
|
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);
|
2005-11-05 09:25:54 -07:00
|
|
|
asm volatile("movl %0,%%fs" :: "r"(FS_TLS_SEL));
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
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 */
|
2005-11-05 09:25:54 -07:00
|
|
|
asm volatile("movl %0,%%fs" :: "r" (0));
|
|
|
|
ret = checking_wrmsrl(MSR_FS_BASE, addr);
|
2005-04-16 15:20:36 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
put_cpu();
|
|
|
|
break;
|
|
|
|
case ARCH_GET_FS: {
|
|
|
|
unsigned long base;
|
|
|
|
if (task->thread.fsindex == FS_TLS_SEL)
|
|
|
|
base = read_32bit_tls(task, FS_TLS);
|
2005-11-05 09:25:54 -07:00
|
|
|
else if (doit)
|
2005-04-16 15:20:36 -07:00
|
|
|
rdmsrl(MSR_FS_BASE, base);
|
2005-11-05 09:25:54 -07:00
|
|
|
else
|
2005-04-16 15:20:36 -07:00
|
|
|
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 10:50:25 -07:00
|
|
|
unsigned gsindex;
|
2005-04-16 15:20:36 -07:00
|
|
|
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 10:50:25 -07:00
|
|
|
else if (doit) {
|
|
|
|
asm("movl %%gs,%0" : "=r" (gsindex));
|
|
|
|
if (gsindex)
|
|
|
|
rdmsrl(MSR_KERNEL_GS_BASE, base);
|
|
|
|
else
|
|
|
|
base = task->thread.gs;
|
|
|
|
}
|
2005-11-05 09:25:54 -07:00
|
|
|
else
|
2005-04-16 15:20:36 -07:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2006-01-12 02:05:38 -07:00
|
|
|
pp = task_pt_regs(tsk);
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
ptregs = *pp;
|
|
|
|
ptregs.cs &= 0xffff;
|
|
|
|
ptregs.ss &= 0xffff;
|
|
|
|
|
|
|
|
elf_core_copy_regs(regs, &ptregs);
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned long arch_align_stack(unsigned long sp)
|
|
|
|
{
|
|
|
|
if (randomize_va_space)
|
|
|
|
sp -= get_random_int() % 8192;
|
|
|
|
return sp & ~0xf;
|
|
|
|
}
|