Revision f17a5194859a82afe4164e938b92035b86c55794 authored by Steven Rostedt (Red Hat) on 31 May 2013, 01:10:37 UTC, committed by Steven Rostedt on 06 June 2013, 16:35:30 UTC
The irqsoff tracer records the max time that interrupts are disabled. There are hooks in the assembly code that calls back into the tracer when interrupts are disabled or enabled. When they are enabled, the tracer checks if the amount of time they were disabled is larger than the previous recorded max interrupts off time. If it is, it creates a snapshot of the currently running trace to store where the last largest interrupts off time was held and how it happened. During testing, this RCU lockdep dump appeared: [ 1257.829021] =============================== [ 1257.829021] [ INFO: suspicious RCU usage. ] [ 1257.829021] 3.10.0-rc1-test+ #171 Tainted: G W [ 1257.829021] ------------------------------- [ 1257.829021] /home/rostedt/work/git/linux-trace.git/include/linux/rcupdate.h:780 rcu_read_lock() used illegally while idle! [ 1257.829021] [ 1257.829021] other info that might help us debug this: [ 1257.829021] [ 1257.829021] [ 1257.829021] RCU used illegally from idle CPU! [ 1257.829021] rcu_scheduler_active = 1, debug_locks = 0 [ 1257.829021] RCU used illegally from extended quiescent state! [ 1257.829021] 2 locks held by trace-cmd/4831: [ 1257.829021] #0: (max_trace_lock){......}, at: [<ffffffff810e2b77>] stop_critical_timing+0x1a3/0x209 [ 1257.829021] #1: (rcu_read_lock){.+.+..}, at: [<ffffffff810dae5a>] __update_max_tr+0x88/0x1ee [ 1257.829021] [ 1257.829021] stack backtrace: [ 1257.829021] CPU: 3 PID: 4831 Comm: trace-cmd Tainted: G W 3.10.0-rc1-test+ #171 [ 1257.829021] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 [ 1257.829021] 0000000000000001 ffff880065f49da8 ffffffff8153dd2b ffff880065f49dd8 [ 1257.829021] ffffffff81092a00 ffff88006bd78680 ffff88007add7500 0000000000000003 [ 1257.829021] ffff88006bd78680 ffff880065f49e18 ffffffff810daebf ffffffff810dae5a [ 1257.829021] Call Trace: [ 1257.829021] [<ffffffff8153dd2b>] dump_stack+0x19/0x1b [ 1257.829021] [<ffffffff81092a00>] lockdep_rcu_suspicious+0x109/0x112 [ 1257.829021] [<ffffffff810daebf>] __update_max_tr+0xed/0x1ee [ 1257.829021] [<ffffffff810dae5a>] ? __update_max_tr+0x88/0x1ee [ 1257.829021] [<ffffffff811002b9>] ? user_enter+0xfd/0x107 [ 1257.829021] [<ffffffff810dbf85>] update_max_tr_single+0x11d/0x12d [ 1257.829021] [<ffffffff811002b9>] ? user_enter+0xfd/0x107 [ 1257.829021] [<ffffffff810e2b15>] stop_critical_timing+0x141/0x209 [ 1257.829021] [<ffffffff8109569a>] ? trace_hardirqs_on+0xd/0xf [ 1257.829021] [<ffffffff811002b9>] ? user_enter+0xfd/0x107 [ 1257.829021] [<ffffffff810e3057>] time_hardirqs_on+0x2a/0x2f [ 1257.829021] [<ffffffff811002b9>] ? user_enter+0xfd/0x107 [ 1257.829021] [<ffffffff8109550c>] trace_hardirqs_on_caller+0x16/0x197 [ 1257.829021] [<ffffffff8109569a>] trace_hardirqs_on+0xd/0xf [ 1257.829021] [<ffffffff811002b9>] user_enter+0xfd/0x107 [ 1257.829021] [<ffffffff810029b4>] do_notify_resume+0x92/0x97 [ 1257.829021] [<ffffffff8154bdca>] int_signal+0x12/0x17 What happened was entering into the user code, the interrupts were enabled and a max interrupts off was recorded. The trace buffer was saved along with various information about the task: comm, pid, uid, priority, etc. The uid is recorded with task_uid(tsk). But this is a macro that uses rcu_read_lock() to retrieve the data, and this happened to happen where RCU is blind (user_enter). As only the preempt and irqs off tracers can have this happen, and they both only have the tsk == current, if tsk == current, use current_uid() instead of task_uid(), as current_uid() does not use RCU as only current can change its uid. This fixes the RCU suspicious splat. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
1 parent 0184d50
mmu_notifier.c
/*
* linux/mm/mmu_notifier.c
*
* Copyright (C) 2008 Qumranet, Inc.
* Copyright (C) 2008 SGI
* Christoph Lameter <clameter@sgi.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*/
#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/srcu.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/slab.h>
/* global SRCU for all MMs */
static struct srcu_struct srcu;
/*
* This function can't run concurrently against mmu_notifier_register
* because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
* runs with mm_users == 0. Other tasks may still invoke mmu notifiers
* in parallel despite there being no task using this mm any more,
* through the vmas outside of the exit_mmap context, such as with
* vmtruncate. This serializes against mmu_notifier_unregister with
* the mmu_notifier_mm->lock in addition to SRCU and it serializes
* against the other mmu notifiers with SRCU. struct mmu_notifier_mm
* can't go away from under us as exit_mmap holds an mm_count pin
* itself.
*/
void __mmu_notifier_release(struct mm_struct *mm)
{
struct mmu_notifier *mn;
int id;
/*
* srcu_read_lock() here will block synchronize_srcu() in
* mmu_notifier_unregister() until all registered
* ->release() callouts this function makes have
* returned.
*/
id = srcu_read_lock(&srcu);
spin_lock(&mm->mmu_notifier_mm->lock);
while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
mn = hlist_entry(mm->mmu_notifier_mm->list.first,
struct mmu_notifier,
hlist);
/*
* Unlink. This will prevent mmu_notifier_unregister()
* from also making the ->release() callout.
*/
hlist_del_init_rcu(&mn->hlist);
spin_unlock(&mm->mmu_notifier_mm->lock);
/*
* Clear sptes. (see 'release' description in mmu_notifier.h)
*/
if (mn->ops->release)
mn->ops->release(mn, mm);
spin_lock(&mm->mmu_notifier_mm->lock);
}
spin_unlock(&mm->mmu_notifier_mm->lock);
/*
* All callouts to ->release() which we have done are complete.
* Allow synchronize_srcu() in mmu_notifier_unregister() to complete
*/
srcu_read_unlock(&srcu, id);
/*
* mmu_notifier_unregister() may have unlinked a notifier and may
* still be calling out to it. Additionally, other notifiers
* may have been active via vmtruncate() et. al. Block here
* to ensure that all notifier callouts for this mm have been
* completed and the sptes are really cleaned up before returning
* to exit_mmap().
*/
synchronize_srcu(&srcu);
}
/*
* If no young bitflag is supported by the hardware, ->clear_flush_young can
* unmap the address and return 1 or 0 depending if the mapping previously
* existed or not.
*/
int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
unsigned long address)
{
struct mmu_notifier *mn;
int young = 0, id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->clear_flush_young)
young |= mn->ops->clear_flush_young(mn, mm, address);
}
srcu_read_unlock(&srcu, id);
return young;
}
int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
struct mmu_notifier *mn;
int young = 0, id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->test_young) {
young = mn->ops->test_young(mn, mm, address);
if (young)
break;
}
}
srcu_read_unlock(&srcu, id);
return young;
}
void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
pte_t pte)
{
struct mmu_notifier *mn;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->change_pte)
mn->ops->change_pte(mn, mm, address, pte);
}
srcu_read_unlock(&srcu, id);
}
void __mmu_notifier_invalidate_page(struct mm_struct *mm,
unsigned long address)
{
struct mmu_notifier *mn;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->invalidate_page)
mn->ops->invalidate_page(mn, mm, address);
}
srcu_read_unlock(&srcu, id);
}
void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
struct mmu_notifier *mn;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->invalidate_range_start)
mn->ops->invalidate_range_start(mn, mm, start, end);
}
srcu_read_unlock(&srcu, id);
}
EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_start);
void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
struct mmu_notifier *mn;
int id;
id = srcu_read_lock(&srcu);
hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
if (mn->ops->invalidate_range_end)
mn->ops->invalidate_range_end(mn, mm, start, end);
}
srcu_read_unlock(&srcu, id);
}
EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
static int do_mmu_notifier_register(struct mmu_notifier *mn,
struct mm_struct *mm,
int take_mmap_sem)
{
struct mmu_notifier_mm *mmu_notifier_mm;
int ret;
BUG_ON(atomic_read(&mm->mm_users) <= 0);
/*
* Verify that mmu_notifier_init() already run and the global srcu is
* initialized.
*/
BUG_ON(!srcu.per_cpu_ref);
ret = -ENOMEM;
mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
if (unlikely(!mmu_notifier_mm))
goto out;
if (take_mmap_sem)
down_write(&mm->mmap_sem);
ret = mm_take_all_locks(mm);
if (unlikely(ret))
goto out_clean;
if (!mm_has_notifiers(mm)) {
INIT_HLIST_HEAD(&mmu_notifier_mm->list);
spin_lock_init(&mmu_notifier_mm->lock);
mm->mmu_notifier_mm = mmu_notifier_mm;
mmu_notifier_mm = NULL;
}
atomic_inc(&mm->mm_count);
/*
* Serialize the update against mmu_notifier_unregister. A
* side note: mmu_notifier_release can't run concurrently with
* us because we hold the mm_users pin (either implicitly as
* current->mm or explicitly with get_task_mm() or similar).
* We can't race against any other mmu notifier method either
* thanks to mm_take_all_locks().
*/
spin_lock(&mm->mmu_notifier_mm->lock);
hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
spin_unlock(&mm->mmu_notifier_mm->lock);
mm_drop_all_locks(mm);
out_clean:
if (take_mmap_sem)
up_write(&mm->mmap_sem);
kfree(mmu_notifier_mm);
out:
BUG_ON(atomic_read(&mm->mm_users) <= 0);
return ret;
}
/*
* Must not hold mmap_sem nor any other VM related lock when calling
* this registration function. Must also ensure mm_users can't go down
* to zero while this runs to avoid races with mmu_notifier_release,
* so mm has to be current->mm or the mm should be pinned safely such
* as with get_task_mm(). If the mm is not current->mm, the mm_users
* pin should be released by calling mmput after mmu_notifier_register
* returns. mmu_notifier_unregister must be always called to
* unregister the notifier. mm_count is automatically pinned to allow
* mmu_notifier_unregister to safely run at any time later, before or
* after exit_mmap. ->release will always be called before exit_mmap
* frees the pages.
*/
int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
{
return do_mmu_notifier_register(mn, mm, 1);
}
EXPORT_SYMBOL_GPL(mmu_notifier_register);
/*
* Same as mmu_notifier_register but here the caller must hold the
* mmap_sem in write mode.
*/
int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
{
return do_mmu_notifier_register(mn, mm, 0);
}
EXPORT_SYMBOL_GPL(__mmu_notifier_register);
/* this is called after the last mmu_notifier_unregister() returned */
void __mmu_notifier_mm_destroy(struct mm_struct *mm)
{
BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list));
kfree(mm->mmu_notifier_mm);
mm->mmu_notifier_mm = LIST_POISON1; /* debug */
}
/*
* This releases the mm_count pin automatically and frees the mm
* structure if it was the last user of it. It serializes against
* running mmu notifiers with SRCU and against mmu_notifier_unregister
* with the unregister lock + SRCU. All sptes must be dropped before
* calling mmu_notifier_unregister. ->release or any other notifier
* method may be invoked concurrently with mmu_notifier_unregister,
* and only after mmu_notifier_unregister returned we're guaranteed
* that ->release or any other method can't run anymore.
*/
void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
{
BUG_ON(atomic_read(&mm->mm_count) <= 0);
spin_lock(&mm->mmu_notifier_mm->lock);
if (!hlist_unhashed(&mn->hlist)) {
int id;
/*
* Ensure we synchronize up with __mmu_notifier_release().
*/
id = srcu_read_lock(&srcu);
hlist_del_rcu(&mn->hlist);
spin_unlock(&mm->mmu_notifier_mm->lock);
if (mn->ops->release)
mn->ops->release(mn, mm);
/*
* Allow __mmu_notifier_release() to complete.
*/
srcu_read_unlock(&srcu, id);
} else
spin_unlock(&mm->mmu_notifier_mm->lock);
/*
* Wait for any running method to finish, including ->release() if it
* was run by __mmu_notifier_release() instead of us.
*/
synchronize_srcu(&srcu);
BUG_ON(atomic_read(&mm->mm_count) <= 0);
mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
static int __init mmu_notifier_init(void)
{
return init_srcu_struct(&srcu);
}
module_init(mmu_notifier_init);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...