linux/arch/x86/kernel/process_64.c

688 lines
16 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 <linux/stackprotector.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/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/tick.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
#include <linux/dmi.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/ds.h>
asmlinkage extern void ret_from_fork(void);
DEFINE_PER_CPU(unsigned long, old_rsp);
static DEFINE_PER_CPU(unsigned char, is_idle);
unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
[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);
}
EXPORT_SYMBOL_GPL(idle_notifier_register);
void idle_notifier_unregister(struct notifier_block *n)
{
atomic_notifier_chain_unregister(&idle_notifier, n);
}
EXPORT_SYMBOL_GPL(idle_notifier_unregister);
void enter_idle(void)
{
percpu_write(is_idle, 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 (x86_test_and_clear_bit_percpu(0, is_idle) == 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();
}
#ifndef CONFIG_SMP
static inline void play_dead(void)
{
BUG();
}
#endif
/*
* 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;
/*
* If we're the non-boot CPU, nothing set the stack canary up
* for us. CPU0 already has it initialized but no harm in
* doing it again. This is a good place for updating it, as
* we wont ever return from this function (so the invalid
* canaries already on the stack wont ever trigger).
*/
boot_init_stack_canary();
/* endless idle loop with no priority at all */
while (1) {
tick_nohz_stop_sched_tick(1);
while (!need_resched()) {
rmb();
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();
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
/* Don't trace irqs off for idle */
stop_critical_timings();
pm_idle();
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
start_critical_timings();
/* 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();
}
}
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
{
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;
const char *board;
printk("\n");
print_modules();
board = dmi_get_system_info(DMI_PRODUCT_NAME);
if (!board)
board = "";
printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n",
current->pid, current->comm, print_tainted(),
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version, board);
printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
printk_address(regs->ip, 1);
printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss,
regs->sp, regs->flags);
printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
regs->ax, regs->bx, regs->cx);
printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n",
regs->dx, regs->si, regs->di);
printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n",
regs->bp, regs->r8, regs->r9);
printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n",
regs->r10, regs->r11, regs->r12);
printk(KERN_INFO "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);
if (!all)
return;
cr0 = read_cr0();
cr2 = read_cr2();
cr3 = read_cr3();
cr4 = read_cr4();
printk(KERN_INFO "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
fs, fsindex, gs, gsindex, shadowgs);
printk(KERN_INFO "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds,
es, cr0);
printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3,
cr4);
get_debugreg(d0, 0);
get_debugreg(d1, 1);
get_debugreg(d2, 2);
printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
get_debugreg(d3, 3);
get_debugreg(d6, 6);
get_debugreg(d7, 7);
printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}
void show_regs(struct pt_regs *regs)
{
printk(KERN_INFO "CPU %d:", smp_processor_id());
__show_regs(regs, 1);
show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
}
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 desc_struct *desc = t->thread.tls_array;
desc += tls;
fill_ldt(desc, &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(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;
savesegment(gs, p->thread.gsindex);
savesegment(fs, p->thread.fsindex);
savesegment(es, p->thread.es);
savesegment(ds, 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;
}
clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
p->thread.ds_ctx = NULL;
clear_tsk_thread_flag(p, TIF_DEBUGCTLMSR);
p->thread.debugctlmsr = 0;
err = 0;
out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
return err;
}
void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
loadsegment(fs, 0);
loadsegment(es, 0);
loadsegment(ds, 0);
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
percpu_write(old_rsp, new_sp);
regs->cs = __USER_CS;
regs->ss = __USER_DS;
regs->flags = X86_EFLAGS_IF;
set_fs(USER_DS);
/*
* Free the old FP and other extended state
*/
free_thread_xstate(current);
}
EXPORT_SYMBOL_GPL(start_thread);
#ifdef CONFIG_IA32_EMULATION
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
loadsegment(fs, 0);
loadsegment(ds, __USER32_DS);
loadsegment(es, __USER32_DS);
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
percpu_write(old_rsp, new_sp);
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
regs->flags = X86_EFLAGS_IF;
set_fs(USER_DS);
/*
* Free the old FP and other extended state
*/
free_thread_xstate(current);
}
#endif
/*
* 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.
* Function graph tracer not supported too.
*/
__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread;
struct thread_struct *next = &next_p->thread;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
unsigned fsindex, gsindex;
bool preload_fpu;
/*
* 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
*/
preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
/* we're going to use this soon, after a few expensive things */
if (preload_fpu)
prefetch(next->xstate);
/*
* Reload esp0, LDT and the page table pointer:
*/
load_sp0(tss, next);
/*
* Switch DS and ES.
* This won't pick up thread selector changes, but I guess that is ok.
*/
savesegment(es, prev->es);
if (unlikely(next->es | prev->es))
loadsegment(es, next->es);
savesegment(ds, prev->ds);
if (unlikely(next->ds | prev->ds))
loadsegment(ds, next->ds);
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
*
* (e.g. xen_load_tls())
*/
savesegment(fs, fsindex);
savesegment(gs, gsindex);
load_TLS(next, cpu);
/* Must be after DS reload */
unlazy_fpu(prev_p);
/* Make sure cpu is ready for new context */
if (preload_fpu)
clts();
/*
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
* the GDT and LDT are properly updated, and must be
* done before math_state_restore, so the TS bit is up
* to date.
*/
arch_end_context_switch(next_p);
/*
* Switch FS and GS.
*
* 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;
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;
/*
* Switch the PDA and FPU contexts.
*/
prev->usersp = percpu_read(old_rsp);
percpu_write(old_rsp, next->usersp);
percpu_write(current_task, next_p);
percpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE - KERNEL_STACK_OFFSET);
/*
* 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);
/*
* Preload the FPU context, now that we've determined that the
* task is likely to be using it.
*/
if (preload_fpu)
__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_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);
}
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);
loadsegment(fs, 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 */
loadsegment(fs, 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) {
savesegment(gs, 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);
}