aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/cgroup.c2
-rw-r--r--kernel/fork.c11
-rw-r--r--kernel/futex.c53
-rw-r--r--kernel/kexec.c7
-rw-r--r--kernel/posix-cpu-timers.c60
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/console.c6
-rw-r--r--kernel/power/disk.c22
-rw-r--r--kernel/power/main.c8
-rw-r--r--kernel/power/swap.c5
-rw-r--r--kernel/power/user.c8
-rw-r--r--kernel/printk.c15
-rw-r--r--kernel/rcuclassic.c4
-rw-r--r--kernel/rcupdate.c12
-rw-r--r--kernel/rcupreempt.c3
-rw-r--r--kernel/rcutree.c4
-rw-r--r--kernel/sched.c30
-rw-r--r--kernel/seccomp.c7
-rw-r--r--kernel/softirq.c1
-rw-r--r--kernel/sys.c31
-rw-r--r--kernel/trace/Kconfig25
-rw-r--r--kernel/trace/ftrace.c6
-rw-r--r--kernel/trace/trace_mmiotrace.c14
-rw-r--r--kernel/trace/trace_selftest.c19
-rw-r--r--kernel/tsacct.c6
-rw-r--r--kernel/user.c21
-rw-r--r--kernel/user_namespace.c21
28 files changed, 291 insertions, 113 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 170a9213c1b..e4791b3ba55 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_UID16) += uid16.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_KALLSYMS) += kallsyms.o
obj-$(CONFIG_PM) += power/
+obj-$(CONFIG_FREEZER) += power/
obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
obj-$(CONFIG_KEXEC) += kexec.o
obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e14db9c089b..9edb5c4b79b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1122,8 +1122,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
mutex_unlock(&cgroup_mutex);
- kfree(root);
kill_litter_super(sb);
+ kfree(root);
}
static struct file_system_type cgroup_fs_type = {
diff --git a/kernel/fork.c b/kernel/fork.c
index a66fbde2071..4854c2c4a82 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1179,10 +1179,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
clear_all_latency_tracing(p);
- /* Our parent execution domain becomes current domain
- These must match for thread signalling to apply */
- p->parent_exec_id = p->self_exec_id;
-
/* ok, now we should be set up.. */
p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL);
p->pdeath_signal = 0;
@@ -1220,10 +1216,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
set_task_cpu(p, smp_processor_id());
/* CLONE_PARENT re-uses the old parent */
- if (clone_flags & (CLONE_PARENT|CLONE_THREAD))
+ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
- else
+ p->parent_exec_id = current->parent_exec_id;
+ } else {
p->real_parent = current;
+ p->parent_exec_id = current->self_exec_id;
+ }
spin_lock(&current->sighand->siglock);
diff --git a/kernel/futex.c b/kernel/futex.c
index f89d373a9c6..438701adce2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1165,6 +1165,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
{
struct task_struct *curr = current;
+ struct restart_block *restart;
DECLARE_WAITQUEUE(wait, curr);
struct futex_hash_bucket *hb;
struct futex_q q;
@@ -1216,11 +1217,13 @@ retry:
if (!ret)
goto retry;
- return ret;
+ goto out;
}
ret = -EWOULDBLOCK;
- if (uval != val)
- goto out_unlock_put_key;
+ if (unlikely(uval != val)) {
+ queue_unlock(&q, hb);
+ goto out_put_key;
+ }
/* Only actually queue if *uaddr contained val. */
queue_me(&q, hb);
@@ -1284,38 +1287,38 @@ retry:
*/
/* If we were woken (and unqueued), we succeeded, whatever. */
+ ret = 0;
if (!unqueue_me(&q))
- return 0;
+ goto out_put_key;
+ ret = -ETIMEDOUT;
if (rem)
- return -ETIMEDOUT;
+ goto out_put_key;
/*
* We expect signal_pending(current), but another thread may
* have handled it for us already.
*/
+ ret = -ERESTARTSYS;
if (!abs_time)
- return -ERESTARTSYS;
- else {
- struct restart_block *restart;
- restart = &current_thread_info()->restart_block;
- restart->fn = futex_wait_restart;
- restart->futex.uaddr = (u32 *)uaddr;
- restart->futex.val = val;
- restart->futex.time = abs_time->tv64;
- restart->futex.bitset = bitset;
- restart->futex.flags = 0;
-
- if (fshared)
- restart->futex.flags |= FLAGS_SHARED;
- if (clockrt)
- restart->futex.flags |= FLAGS_CLOCKRT;
- return -ERESTART_RESTARTBLOCK;
- }
+ goto out_put_key;
-out_unlock_put_key:
- queue_unlock(&q, hb);
- put_futex_key(fshared, &q.key);
+ restart = &current_thread_info()->restart_block;
+ restart->fn = futex_wait_restart;
+ restart->futex.uaddr = (u32 *)uaddr;
+ restart->futex.val = val;
+ restart->futex.time = abs_time->tv64;
+ restart->futex.bitset = bitset;
+ restart->futex.flags = 0;
+
+ if (fshared)
+ restart->futex.flags |= FLAGS_SHARED;
+ if (clockrt)
+ restart->futex.flags |= FLAGS_CLOCKRT;
+ ret = -ERESTART_RESTARTBLOCK;
+
+out_put_key:
+ put_futex_key(fshared, &q.key);
out:
return ret;
}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 8a6d7b08864..48389957825 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1465,6 +1465,11 @@ int kernel_kexec(void)
error = device_power_down(PMSG_FREEZE);
if (error)
goto Enable_irqs;
+
+ /* Suspend system devices */
+ error = sysdev_suspend(PMSG_FREEZE);
+ if (error)
+ goto Power_up_devices;
} else
#endif
{
@@ -1477,6 +1482,8 @@ int kernel_kexec(void)
#ifdef CONFIG_KEXEC_JUMP
if (kexec_image->preserve_context) {
+ sysdev_resume();
+ Power_up_devices:
device_power_up(PMSG_RESTORE);
Enable_irqs:
local_irq_enable();
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 2313a4cc14e..e976e505648 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -681,6 +681,33 @@ static void cpu_timer_fire(struct k_itimer *timer)
}
/*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with tasklist_lock held for reading.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+ struct task_struct *p,
+ union cpu_time_count *cpu)
+{
+ struct task_cputime cputime;
+
+ thread_group_cputimer(p, &cputime);
+ switch (CPUCLOCK_WHICH(which_clock)) {
+ default:
+ return -EINVAL;
+ case CPUCLOCK_PROF:
+ cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+ break;
+ case CPUCLOCK_VIRT:
+ cpu->cpu = cputime.utime;
+ break;
+ case CPUCLOCK_SCHED:
+ cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+ break;
+ }
+ return 0;
+}
+
+/*
* Guts of sys_timer_settime for CPU timers.
* This is called with the timer locked and interrupts disabled.
* If we return TIMER_RETRY, it's necessary to release the timer's lock
@@ -741,7 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
cpu_clock_sample(timer->it_clock, p, &val);
} else {
- cpu_clock_sample_group(timer->it_clock, p, &val);
+ cpu_timer_sample_group(timer->it_clock, p, &val);
}
if (old) {
@@ -889,7 +916,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
read_unlock(&tasklist_lock);
goto dead;
} else {
- cpu_clock_sample_group(timer->it_clock, p, &now);
+ cpu_timer_sample_group(timer->it_clock, p, &now);
clear_dead = (unlikely(p->exit_state) &&
thread_group_empty(p));
}
@@ -1244,7 +1271,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
clear_dead_task(timer, now);
goto out_unlock;
}
- cpu_clock_sample_group(timer->it_clock, p, &now);
+ cpu_timer_sample_group(timer->it_clock, p, &now);
bump_cpu_timer(timer, now);
/* Leave the tasklist_lock locked for the call below. */
}
@@ -1409,33 +1436,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
}
/*
- * Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_timer_sample_group(const clockid_t which_clock,
- struct task_struct *p,
- union cpu_time_count *cpu)
-{
- struct task_cputime cputime;
-
- thread_group_cputimer(p, &cputime);
- switch (CPUCLOCK_WHICH(which_clock)) {
- default:
- return -EINVAL;
- case CPUCLOCK_PROF:
- cpu->cpu = cputime_add(cputime.utime, cputime.stime);
- break;
- case CPUCLOCK_VIRT:
- cpu->cpu = cputime.utime;
- break;
- case CPUCLOCK_SCHED:
- cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
- break;
- }
- return 0;
-}
-
-/*
* Set one of the process-wide special case CPU timers.
* The tsk->sighand->siglock must be held by the caller.
* The *newval argument is relative and we update it to be absolute, *oldval
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index d7a10167a25..720ea4f781b 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -3,7 +3,7 @@ ifeq ($(CONFIG_PM_DEBUG),y)
EXTRA_CFLAGS += -DDEBUG
endif
-obj-y := main.o
+obj-$(CONFIG_PM) += main.o
obj-$(CONFIG_PM_SLEEP) += console.o
obj-$(CONFIG_FREEZER) += process.o
obj-$(CONFIG_HIBERNATION) += swsusp.o disk.o snapshot.o swap.o user.o
diff --git a/kernel/power/console.c b/kernel/power/console.c
index b8628be2a46..a3961b205de 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -78,6 +78,12 @@ void pm_restore_console(void)
}
set_console(orig_fgconsole);
release_console_sem();
+
+ if (vt_waitactive(orig_fgconsole)) {
+ pr_debug("Resume: Can't switch VCs.");
+ return;
+ }
+
kmsg_redirect = orig_kmsg;
}
#endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 432ee575c9e..4a4a206b197 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -227,6 +227,12 @@ static int create_image(int platform_mode)
"aborting hibernation\n");
goto Enable_irqs;
}
+ sysdev_suspend(PMSG_FREEZE);
+ if (error) {
+ printk(KERN_ERR "PM: Some devices failed to power down, "
+ "aborting hibernation\n");
+ goto Power_up_devices;
+ }
if (hibernation_test(TEST_CORE))
goto Power_up;
@@ -242,9 +248,11 @@ static int create_image(int platform_mode)
if (!in_suspend)
platform_leave(platform_mode);
Power_up:
+ sysdev_resume();
/* NOTE: device_power_up() is just a resume() for devices
* that suspended with irqs off ... no overall powerup.
*/
+ Power_up_devices:
device_power_up(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
Enable_irqs:
@@ -335,6 +343,7 @@ static int resume_target_kernel(void)
"aborting resume\n");
goto Enable_irqs;
}
+ sysdev_suspend(PMSG_QUIESCE);
/* We'll ignore saved state, but this gets preempt count (etc) right */
save_processor_state();
error = restore_highmem();
@@ -357,6 +366,7 @@ static int resume_target_kernel(void)
swsusp_free();
restore_processor_state();
touch_softlockup_watchdog();
+ sysdev_resume();
device_power_up(PMSG_RECOVER);
Enable_irqs:
local_irq_enable();
@@ -440,6 +450,7 @@ int hibernation_platform_enter(void)
local_irq_disable();
error = device_power_down(PMSG_HIBERNATE);
if (!error) {
+ sysdev_suspend(PMSG_HIBERNATE);
hibernation_ops->enter();
/* We should never get here */
while (1);
@@ -595,6 +606,12 @@ static int software_resume(void)
unsigned int flags;
/*
+ * If the user said "noresume".. bail out early.
+ */
+ if (noresume)
+ return 0;
+
+ /*
* name_to_dev_t() below takes a sysfs buffer mutex when sysfs
* is configured into the kernel. Since the regular hibernate
* trigger path is via sysfs which takes a buffer mutex before
@@ -610,6 +627,11 @@ static int software_resume(void)
mutex_unlock(&pm_mutex);
return -ENOENT;
}
+ /*
+ * Some device discovery might still be in progress; we need
+ * to wait for this to finish.
+ */
+ wait_for_device_probe();
swsusp_resume_device = name_to_dev_t(resume_file);
pr_debug("PM: Resume from partition %s\n", resume_file);
} else {
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b4d219016b6..c9632f841f6 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state)
goto Done;
}
- if (!suspend_test(TEST_CORE))
- error = suspend_ops->enter(state);
+ error = sysdev_suspend(PMSG_SUSPEND);
+ if (!error) {
+ if (!suspend_test(TEST_CORE))
+ error = suspend_ops->enter(state);
+ sysdev_resume();
+ }
device_power_up(PMSG_RESUME);
Done:
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 6da14358537..505f319e489 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -60,6 +60,7 @@ static struct block_device *resume_bdev;
static int submit(int rw, pgoff_t page_off, struct page *page,
struct bio **bio_chain)
{
+ const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
struct bio *bio;
bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
@@ -80,7 +81,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
bio_get(bio);
if (bio_chain == NULL) {
- submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+ submit_bio(bio_rw, bio);
wait_on_page_locked(page);
if (rw == READ)
bio_set_pages_dirty(bio);
@@ -90,7 +91,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
get_page(page); /* These pages are freed later */
bio->bi_private = *bio_chain;
*bio_chain = bio;
- submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+ submit_bio(bio_rw, bio);
}
return 0;
}
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 005b93d839b..6c85359364f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
data->swap = swsusp_resume_device ?
swap_type_of(swsusp_resume_device, 0, NULL) : -1;
data->mode = O_RDONLY;
- error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+ error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
if (error)
- pm_notifier_call_chain(PM_POST_RESTORE);
+ pm_notifier_call_chain(PM_POST_HIBERNATION);
} else {
data->swap = -1;
data->mode = O_WRONLY;
- error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+ error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
if (error)
- pm_notifier_call_chain(PM_POST_HIBERNATION);
+ pm_notifier_call_chain(PM_POST_RESTORE);
}
if (error)
atomic_inc(&snapshot_device_available);
diff --git a/kernel/printk.c b/kernel/printk.c
index 69188f226a9..e3602d0755b 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress);
* driver system.
*/
static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
struct console *console_drivers;
EXPORT_SYMBOL_GPL(console_drivers);
@@ -891,12 +890,14 @@ void suspend_console(void)
printk("Suspending console(s) (use no_console_suspend to debug)\n");
acquire_console_sem();
console_suspended = 1;
+ up(&console_sem);
}
void resume_console(void)
{
if (!console_suspend_enabled)
return;
+ down(&console_sem);
console_suspended = 0;
release_console_sem();
}
@@ -912,11 +913,9 @@ void resume_console(void)
void acquire_console_sem(void)
{
BUG_ON(in_interrupt());
- if (console_suspended) {
- down(&secondary_console_sem);
- return;
- }
down(&console_sem);
+ if (console_suspended)
+ return;
console_locked = 1;
console_may_schedule = 1;
}
@@ -926,6 +925,10 @@ int try_acquire_console_sem(void)
{
if (down_trylock(&console_sem))
return -1;
+ if (console_suspended) {
+ up(&console_sem);
+ return -1;
+ }
console_locked = 1;
console_may_schedule = 0;
return 0;
@@ -979,7 +982,7 @@ void release_console_sem(void)
unsigned wake_klogd = 0;
if (console_suspended) {
- up(&secondary_console_sem);
+ up(&console_sem);
return;
}
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index bd5a9003497..654c640a6b9 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
void rcu_check_callbacks(int cpu, int user)
{
if (user ||
- (idle_cpu(cpu) && !in_softirq() &&
- hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+ (idle_cpu(cpu) && rcu_scheduler_active &&
+ !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
/*
* Get here if this CPU took its interrupt from user
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a881a..cae8a059cf4 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/module.h>
+#include <linux/kernel_stat.h>
enum rcu_barrier {
RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
static atomic_t rcu_barrier_cpu_count;
static DEFINE_MUTEX(rcu_barrier_mutex);
static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
/*
* Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head *head)
void synchronize_rcu(void)
{
struct rcu_synchronize rcu;
+
+ if (rcu_blocking_is_gp())
+ return;
+
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
__rcu_init();
}
+void rcu_scheduler_starting(void)
+{
+ WARN_ON(num_online_cpus() != 1);
+ WARN_ON(nr_context_switches() > 0);
+ rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50781f..5d59e850fb7 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
{
struct rcu_synchronize rcu;
+ if (num_online_cpus() == 1)
+ return; /* blocking is gp if only one CPU! */
+
init_completion(&rcu.completion);
/* Will wake me after RCU finished. */
call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b2fd602a6f6..97ce31579ec 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
void rcu_check_callbacks(int cpu, int user)
{
if (user ||
- (idle_cpu(cpu) && !in_softirq() &&
- hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+ (idle_cpu(cpu) && rcu_scheduler_active &&
+ !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
/*
* Get here if this CPU took its interrupt from user
diff --git a/kernel/sched.c b/kernel/sched.c
index c1d0ed36008..8e2558c2ba6 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
ktime_t now;
- if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+ if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
return;
if (hrtimer_active(&rt_b->rt_period_timer))
@@ -6944,20 +6944,26 @@ static void free_rootdomain(struct root_domain *rd)
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
+ struct root_domain *old_rd = NULL;
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
- struct root_domain *old_rd = rq->rd;
+ old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, old_rd->online))
set_rq_offline(rq);
cpumask_clear_cpu(rq->cpu, old_rd->span);
- if (atomic_dec_and_test(&old_rd->refcount))
- free_rootdomain(old_rd);
+ /*
+ * If we dont want to free the old_rt yet then
+ * set old_rd to NULL to skip the freeing later
+ * in this function:
+ */
+ if (!atomic_dec_and_test(&old_rd->refcount))
+ old_rd = NULL;
}
atomic_inc(&rd->refcount);
@@ -6968,6 +6974,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
set_rq_online(rq);
spin_unlock_irqrestore(&rq->lock, flags);
+
+ if (old_rd)
+ free_rootdomain(old_rd);
}
static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
@@ -9215,6 +9224,16 @@ static int sched_rt_global_constraints(void)
return ret;
}
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+ /* Don't accept realtime tasks when there is no way for them to run */
+ if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+ return 0;
+
+ return 1;
+}
+
#else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
@@ -9308,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct task_struct *tsk)
{
#ifdef CONFIG_RT_GROUP_SCHED
- /* Don't accept realtime tasks when there is no way for them to run */
- if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+ if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
return -EINVAL;
#else
/* We don't support RT-tasks being in separate groups */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb731f..57d4b13b631 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
#include <linux/seccomp.h>
#include <linux/sched.h>
+#include <linux/compat.h>
/* #define SECCOMP_DEBUG 1 */
#define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
0, /* null terminated */
};
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
static int mode1_syscalls_32[] = {
__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
switch (mode) {
case 1:
syscall = mode1_syscalls;
-#ifdef TIF_32BIT
- if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+ if (is_compat_task())
syscall = mode1_syscalls_32;
#endif
do {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8..9041ea7948f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -626,6 +626,7 @@ static int ksoftirqd(void * __bind_cpu)
preempt_enable_no_resched();
cond_resched();
preempt_disable();
+ rcu_qsctr_inc((long)__bind_cpu);
}
preempt_enable();
set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/sys.c b/kernel/sys.c
index f145c415bc1..37f458e6882 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -559,7 +559,7 @@ error:
abort_creds(new);
return retval;
}
-
+
/*
* change the user struct in a credentials set to match the new UID
*/
@@ -571,6 +571,11 @@ static int set_user(struct cred *new)
if (!new_user)
return -EAGAIN;
+ if (!task_can_switch_user(new_user, current)) {
+ free_uid(new_user);
+ return -EINVAL;
+ }
+
if (atomic_read(&new_user->processes) >=
current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
new_user != INIT_USER) {
@@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
goto error;
}
- retval = -EAGAIN;
- if (new->uid != old->uid && set_user(new) < 0)
- goto error;
-
+ if (new->uid != old->uid) {
+ retval = set_user(new);
+ if (retval < 0)
+ goto error;
+ }
if (ruid != (uid_t) -1 ||
(euid != (uid_t) -1 && euid != old->uid))
new->suid = new->euid;
@@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
retval = -EPERM;
if (capable(CAP_SETUID)) {
new->suid = new->uid = uid;
- if (uid != old->uid && set_user(new) < 0) {
- retval = -EAGAIN;
- goto error;
+ if (uid != old->uid) {
+ retval = set_user(new);
+ if (retval < 0)
+ goto error;
}
} else if (uid != old->uid && uid != new->suid) {
goto error;
@@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
goto error;
}
- retval = -EAGAIN;
if (ruid != (uid_t) -1) {
new->uid = ruid;
- if (ruid != old->uid && set_user(new) < 0)
- goto error;
+ if (ruid != old->uid) {
+ retval = set_user(new);
+ if (retval < 0)
+ goto error;
+ }
}
if (euid != (uid_t) -1)
new->euid = euid;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e2a4ff6fc3a..34e707e5ab8 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -52,6 +52,7 @@ config FUNCTION_TRACER
depends on HAVE_FUNCTION_TRACER
depends on DEBUG_KERNEL
select FRAME_POINTER
+ select KALLSYMS
select TRACING
select CONTEXT_SWITCH_TRACER
help
@@ -238,6 +239,7 @@ config STACK_TRACER
depends on DEBUG_KERNEL
select FUNCTION_TRACER
select STACKTRACE
+ select KALLSYMS
help
This special tracer records the maximum stack footprint of the
kernel and displays it in debugfs/tracing/stack_trace.
@@ -302,4 +304,27 @@ config FTRACE_STARTUP_TEST
functioning properly. It will do tests on all the configured
tracers of ftrace.
+config MMIOTRACE
+ bool "Memory mapped IO tracing"
+ depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+ select TRACING
+ help
+ Mmiotrace traces Memory Mapped I/O access and is meant for
+ debugging and reverse engineering. It is called from the ioremap
+ implementation and works via page faults. Tracing is disabled by
+ default and can be enabled at run-time.
+
+ See Documentation/tracers/mmiotrace.txt.
+ If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+ tristate "Test module for mmiotrace"
+ depends on MMIOTRACE && m
+ help
+ This is a dumb module for testing mmiotrace. It is very dangerous
+ as it will write garbage to IO memory starting at a given address.
+ However, it should be safe to use on e.g. unused portion of VRAM.
+
+ Say N, unless you absolutely know what you are doing.
+
endmenu
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9a236ffe2aa..fdf913dfc7e 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2033,7 +2033,7 @@ free:
static int start_graph_tracing(void)
{
struct ftrace_ret_stack **ret_stack_list;
- int ret;
+ int ret, cpu;
ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
sizeof(struct ftrace_ret_stack *),
@@ -2042,6 +2042,10 @@ static int start_graph_tracing(void)
if (!ret_stack_list)
return -ENOMEM;
+ /* The cpu_boot init_task->ret_stack will never be freed */
+ for_each_online_cpu(cpu)
+ ftrace_graph_init_task(idle_task(cpu));
+
do {
ret = alloc_retstack_tasklist(ret_stack_list);
} while (ret == -EAGAIN);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index fffcb069f1d..80e503ef613 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
+#include <asm/atomic.h>
#include "trace.h"
@@ -19,6 +20,7 @@ struct header_iter {
static struct trace_array *mmio_trace_array;
static bool overrun_detected;
static unsigned long prev_overruns;
+static atomic_t dropped_count;
static void mmio_reset_data(struct trace_array *tr)
{
@@ -121,11 +123,11 @@ static void mmio_close(struct trace_iterator *iter)
static unsigned long count_overruns(struct trace_iterator *iter)
{
- unsigned long cnt = 0;
+ unsigned long cnt = atomic_xchg(&dropped_count, 0);
unsigned long over = ring_buffer_overruns(iter->tr->buffer);
if (over > prev_overruns)
- cnt = over - prev_overruns;
+ cnt += over - prev_overruns;
prev_overruns = over;
return cnt;
}
@@ -310,8 +312,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
- if (!event)
+ if (!event) {
+ atomic_inc(&dropped_count);
return;
+ }
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, 0, preempt_count());
entry->ent.type = TRACE_MMIO_RW;
@@ -338,8 +342,10 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
- if (!event)
+ if (!event) {
+ atomic_inc(&dropped_count);
return;
+ }
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, 0, preempt_count());
entry->ent.type = TRACE_MMIO_MAP;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 88c8eb70f54..bc8e80a86bc 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
{
struct ring_buffer_event *event;
struct trace_entry *entry;
+ unsigned int loops = 0;
while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
entry = ring_buffer_event_data(event);
+ /*
+ * The ring buffer is a size of trace_buf_size, if
+ * we loop more than the size, there's something wrong
+ * with the ring buffer.
+ */
+ if (loops++ > trace_buf_size) {
+ printk(KERN_CONT ".. bad ring buffer ");
+ goto failed;
+ }
if (!trace_valid_entry(entry)) {
printk(KERN_CONT ".. invalid entry %d ",
entry->type);
@@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
cnt = ring_buffer_entries(tr->buffer);
+ /*
+ * The trace_test_buffer_cpu runs a while loop to consume all data.
+ * If the calling tracer is broken, and is constantly filling
+ * the buffer, this will run forever, and hard lock the box.
+ * We disable the ring buffer while we do this test to prevent
+ * a hard lock up.
+ */
+ tracing_off();
for_each_possible_cpu(cpu) {
ret = trace_test_buffer_cpu(tr, cpu);
if (ret)
break;
}
+ tracing_on();
__raw_spin_unlock(&ftrace_max_lock);
local_irq_restore(flags);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 43f891b05a4..00d59d048ed 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -122,8 +122,10 @@ void acct_update_integrals(struct task_struct *tsk)
if (likely(tsk->mm)) {
cputime_t time, dtime;
struct timeval value;
+ unsigned long flags;
u64 delta;
+ local_irq_save(flags);
time = tsk->stime + tsk->utime;
dtime = cputime_sub(time, tsk->acct_timexpd);
jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
@@ -131,10 +133,12 @@ void acct_update_integrals(struct task_struct *tsk)
delta = delta * USEC_PER_SEC + value.tv_usec;
if (delta == 0)
- return;
+ goto out;
tsk->acct_timexpd = time;
tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
+ out:
+ local_irq_restore(flags);
}
}
diff --git a/kernel/user.c b/kernel/user.c
index 477b6660f44..6a9b696128c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -72,6 +72,7 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
static void uid_hash_remove(struct user_struct *up)
{
hlist_del_init(&up->uidhash_node);
+ put_user_ns(up->user_ns);
}
static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
@@ -334,7 +335,6 @@ static void free_user(struct user_struct *up, unsigned long flags)
atomic_inc(&up->__count);
spin_unlock_irqrestore(&uidhash_lock, flags);
- put_user_ns(up->user_ns);
INIT_WORK(&up->work, remove_user_sysfs_dir);
schedule_work(&up->work);
}
@@ -357,12 +357,29 @@ static void free_user(struct user_struct *up, unsigned long flags)
sched_destroy_user(up);
key_put(up->uid_keyring);
key_put(up->session_keyring);
- put_user_ns(up->user_ns);
kmem_cache_free(uid_cachep, up);
}
#endif
+#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
+/*
+ * We need to check if a setuid can take place. This function should be called
+ * before successfully completing the setuid.
+ */
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+
+ return sched_rt_can_attach(up->tg, tsk);
+
+}
+#else
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+ return 1;
+}
+#endif
+
/*
* Locate the user_struct for the passed UID. If found, take a ref on it. The
* caller must undo that ref with free_uid().
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 79084311ee5..076c7c8215b 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -60,12 +60,25 @@ int create_user_ns(struct cred *new)
return 0;
}
-void free_user_ns(struct kref *kref)
+/*
+ * Deferred destructor for a user namespace. This is required because
+ * free_user_ns() may be called with uidhash_lock held, but we need to call
+ * back to free_uid() which will want to take the lock again.
+ */
+static void free_user_ns_work(struct work_struct *work)
{
- struct user_namespace *ns;
-
- ns = container_of(kref, struct user_namespace, kref);
+ struct user_namespace *ns =
+ container_of(work, struct user_namespace, destroyer);
free_uid(ns->creator);
kfree(ns);
}
+
+void free_user_ns(struct kref *kref)
+{
+ struct user_namespace *ns =
+ container_of(kref, struct user_namespace, kref);
+
+ INIT_WORK(&ns->destroyer, free_user_ns_work);
+ schedule_work(&ns->destroyer);
+}
EXPORT_SYMBOL(free_user_ns);
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-07 23:24:30 +0000