summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c9
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/futex_compat.c4
-rw-r--r--kernel/kmod.c2
-rw-r--r--kernel/ptrace.c1
-rw-r--r--kernel/sched.c25
-rw-r--r--kernel/sched_debug.c1
-rw-r--r--kernel/sched_fair.c122
-rw-r--r--kernel/signal.c8
-rw-r--r--kernel/sysctl.c8
-rw-r--r--kernel/time/ntp.c2
-rw-r--r--kernel/time/tick-broadcast.c17
-rw-r--r--kernel/time/tick-sched.c12
-rw-r--r--kernel/time/timekeeping.c10
-rw-r--r--kernel/user.c45
-rw-r--r--kernel/user_namespace.c4
-rw-r--r--kernel/utsname.c2
17 files changed, 181 insertions, 93 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 06b24b3aa37..993369ee94d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -24,7 +24,6 @@
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
-#include <linux/signalfd.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
#include <linux/kthread.h>
@@ -86,14 +85,6 @@ static void __exit_signal(struct task_struct *tsk)
sighand = rcu_dereference(tsk->sighand);
spin_lock(&sighand->siglock);
- /*
- * Notify that this sighand has been detached. This must
- * be called with the tsk->sighand lock held. Also, this
- * access tsk->sighand internally, so it must be called
- * before tsk->sighand is reset.
- */
- signalfd_detach_locked(tsk);
-
posix_cpu_timers_exit(tsk);
if (atomic_dec_and_test(&sig->count))
posix_cpu_timers_exit_group(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 7332e236d36..33f12f48684 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1438,7 +1438,7 @@ static void sighand_ctor(void *data, struct kmem_cache *cachep,
struct sighand_struct *sighand = data;
spin_lock_init(&sighand->siglock);
- INIT_LIST_HEAD(&sighand->signalfd_list);
+ init_waitqueue_head(&sighand->signalfd_wqh);
}
void __init proc_caches_init(void)
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f7921360efa..7e52eb051f2 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -61,10 +61,10 @@ void compat_exit_robust_list(struct task_struct *curr)
if (fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
- if (upending)
+ if (pending)
handle_futex_death((void __user *)pending + futex_offset, curr, pip);
- while (compat_ptr(uentry) != &head->list) {
+ while (entry != (struct robust_list __user *) &head->list) {
/*
* A pending lock might already be on the list, so
* dont process it twice:
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9809cc1f33d..c6a4f8aebeb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -505,7 +505,7 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp,
if (ret < 0)
goto out;
- return call_usermodehelper_exec(sub_info, 1);
+ return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
out:
call_usermodehelper_freeinfo(sub_info);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 82a558b655d..3eca7a55f2e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -233,6 +233,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
/* Architecture-specific hardware disable .. */
ptrace_disable(child);
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
write_lock_irq(&tasklist_lock);
/* protect against de_thread()->release_task() */
diff --git a/kernel/sched.c b/kernel/sched.c
index b533d6db78a..6107a0cd632 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -668,7 +668,7 @@ static u64 div64_likely32(u64 divident, unsigned long divisor)
/*
* Shift right and round:
*/
-#define RSR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
@@ -684,10 +684,10 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
* Check whether we'd overflow the 64-bit multiplication:
*/
if (unlikely(tmp > WMULT_CONST))
- tmp = RSR(RSR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
+ tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
WMULT_SHIFT/2);
else
- tmp = RSR(tmp * lw->inv_weight, WMULT_SHIFT);
+ tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}
@@ -858,7 +858,6 @@ static void dec_nr_running(struct task_struct *p, struct rq *rq)
static void set_load_weight(struct task_struct *p)
{
- task_rq(p)->cfs.wait_runtime -= p->se.wait_runtime;
p->se.wait_runtime = 0;
if (task_has_rt_policy(p)) {
@@ -1683,6 +1682,11 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
p->prio = effective_prio(p);
+ if (rt_prio(p->prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
+
if (!p->sched_class->task_new || !sysctl_sched_child_runs_first ||
(clone_flags & CLONE_VM) || task_cpu(p) != this_cpu ||
!current->se.on_rq) {
@@ -2512,7 +2516,7 @@ group_next:
* a think about bumping its value to force at least one task to be
* moved
*/
- if (*imbalance + SCHED_LOAD_SCALE_FUZZ < busiest_load_per_task) {
+ if (*imbalance < busiest_load_per_task) {
unsigned long tmp, pwr_now, pwr_move;
unsigned int imbn;
@@ -2564,10 +2568,8 @@ small_imbalance:
pwr_move /= SCHED_LOAD_SCALE;
/* Move if we gain throughput */
- if (pwr_move <= pwr_now)
- goto out_balanced;
-
- *imbalance = busiest_load_per_task;
+ if (pwr_move > pwr_now)
+ *imbalance = busiest_load_per_task;
}
return busiest;
@@ -4553,10 +4555,7 @@ asmlinkage long sys_sched_yield(void)
struct rq *rq = this_rq_lock();
schedstat_inc(rq, yld_cnt);
- if (unlikely(rq->nr_running == 1))
- schedstat_inc(rq, yld_act_empty);
- else
- current->sched_class->yield_task(rq, current);
+ current->sched_class->yield_task(rq, current);
/*
* Since we are going to call schedule() anyway, there's
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index ab18f45f2ab..c3ee38bd342 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -283,4 +283,5 @@ void proc_sched_set_task(struct task_struct *p)
p->se.wait_runtime_overruns = p->se.wait_runtime_underruns = 0;
#endif
p->se.sum_exec_runtime = 0;
+ p->se.prev_sum_exec_runtime = 0;
}
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ce39282d9c0..c9fbe8e73a4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -43,6 +43,14 @@ unsigned int sysctl_sched_latency __read_mostly = 20000000ULL;
unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
/*
+ * sys_sched_yield() compat mode
+ *
+ * This option switches the agressive yield implementation of the
+ * old scheduler back on.
+ */
+unsigned int __read_mostly sysctl_sched_compat_yield;
+
+/*
* SCHED_BATCH wake-up granularity.
* (default: 25 msec, units: nanoseconds)
*
@@ -194,6 +202,8 @@ __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_add(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
+
+ schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}
static inline void
@@ -205,6 +215,8 @@ __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_sub(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
+
+ schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
}
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
@@ -291,7 +303,7 @@ niced_granularity(struct sched_entity *curr, unsigned long granularity)
/*
* It will always fit into 'long':
*/
- return (long) (tmp >> WMULT_SHIFT);
+ return (long) (tmp >> (WMULT_SHIFT-NICE_0_SHIFT));
}
static inline void
@@ -574,7 +586,6 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
prev_runtime = se->wait_runtime;
__add_wait_runtime(cfs_rq, se, delta_fair);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
delta_fair = se->wait_runtime - prev_runtime;
/*
@@ -662,7 +673,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->block_start = rq_of(cfs_rq)->clock;
}
- cfs_rq->wait_runtime -= se->wait_runtime;
#endif
}
__dequeue_entity(cfs_rq, se);
@@ -671,22 +681,39 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
/*
* Preempt the current task with a newly woken task if needed:
*/
-static int
+static void
__check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
struct sched_entity *curr, unsigned long granularity)
{
s64 __delta = curr->fair_key - se->fair_key;
+ unsigned long ideal_runtime, delta_exec;
+
+ /*
+ * ideal_runtime is compared against sum_exec_runtime, which is
+ * walltime, hence do not scale.
+ */
+ ideal_runtime = max(sysctl_sched_latency / cfs_rq->nr_running,
+ (unsigned long)sysctl_sched_min_granularity);
+
+ /*
+ * If we executed more than what the latency constraint suggests,
+ * reduce the rescheduling granularity. This way the total latency
+ * of how much a task is not scheduled converges to
+ * sysctl_sched_latency:
+ */
+ delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+ if (delta_exec > ideal_runtime)
+ granularity = 0;
/*
* Take scheduling granularity into account - do not
* preempt the current task unless the best task has
* a larger than sched_granularity fairness advantage:
+ *
+ * scale granularity as key space is in fair_clock.
*/
- if (__delta > niced_granularity(curr, granularity)) {
+ if (__delta > niced_granularity(curr, granularity))
resched_task(rq_of(cfs_rq)->curr);
- return 1;
- }
- return 0;
}
static inline void
@@ -702,6 +729,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_stats_wait_end(cfs_rq, se);
update_stats_curr_start(cfs_rq, se);
set_cfs_rq_curr(cfs_rq, se);
+ se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
@@ -731,7 +759,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- unsigned long gran, ideal_runtime, delta_exec;
struct sched_entity *next;
/*
@@ -748,22 +775,8 @@ static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
if (next == curr)
return;
- gran = sched_granularity(cfs_rq);
- ideal_runtime = niced_granularity(curr,
- max(sysctl_sched_latency / cfs_rq->nr_running,
- (unsigned long)sysctl_sched_min_granularity));
- /*
- * If we executed more than what the latency constraint suggests,
- * reduce the rescheduling granularity. This way the total latency
- * of how much a task is not scheduled converges to
- * sysctl_sched_latency:
- */
- delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime)
- gran = 0;
-
- if (__check_preempt_curr_fair(cfs_rq, next, curr, gran))
- curr->prev_sum_exec_runtime = curr->sum_exec_runtime;
+ __check_preempt_curr_fair(cfs_rq, next, curr,
+ sched_granularity(cfs_rq));
}
/**************************************************
@@ -892,19 +905,62 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
}
/*
- * sched_yield() support is very simple - we dequeue and enqueue
+ * sched_yield() support is very simple - we dequeue and enqueue.
+ *
+ * If compat_yield is turned on then we requeue to the end of the tree.
*/
static void yield_task_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
+ struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+ struct sched_entity *rightmost, *se = &p->se;
+ struct rb_node *parent;
- __update_rq_clock(rq);
/*
- * Dequeue and enqueue the task to update its
- * position within the tree:
+ * Are we the only task in the tree?
+ */
+ if (unlikely(cfs_rq->nr_running == 1))
+ return;
+
+ if (likely(!sysctl_sched_compat_yield)) {
+ __update_rq_clock(rq);
+ /*
+ * Dequeue and enqueue the task to update its
+ * position within the tree:
+ */
+ dequeue_entity(cfs_rq, &p->se, 0);
+ enqueue_entity(cfs_rq, &p->se, 0);
+
+ return;
+ }
+ /*
+ * Find the rightmost entry in the rbtree:
+ */
+ do {
+ parent = *link;
+ link = &parent->rb_right;
+ } while (*link);
+
+ rightmost = rb_entry(parent, struct sched_entity, run_node);
+ /*
+ * Already in the rightmost position?
+ */
+ if (unlikely(rightmost == se))
+ return;
+
+ /*
+ * Minimally necessary key value to be last in the tree:
+ */
+ se->fair_key = rightmost->fair_key + 1;
+
+ if (cfs_rq->rb_leftmost == &se->run_node)
+ cfs_rq->rb_leftmost = rb_next(&se->run_node);
+ /*
+ * Relink the task to the rightmost position:
*/
- dequeue_entity(cfs_rq, &p->se, 0);
- enqueue_entity(cfs_rq, &p->se, 0);
+ rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+ rb_link_node(&se->run_node, parent, link);
+ rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
/*
@@ -1121,10 +1177,8 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
* The statistical average of wait_runtime is about
* -granularity/2, so initialize the task with that:
*/
- if (sysctl_sched_features & SCHED_FEAT_START_DEBIT) {
+ if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
se->wait_runtime = -(sched_granularity(cfs_rq) / 2);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
- }
__enqueue_entity(cfs_rq, se);
}
diff --git a/kernel/signal.c b/kernel/signal.c
index 3169bed0b4d..9fb91a32edd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -378,8 +378,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
/* We only dequeue private signals from ourselves, we don't let
* signalfd steal them
*/
- if (likely(tsk == current))
- signr = __dequeue_signal(&tsk->pending, mask, info);
+ signr = __dequeue_signal(&tsk->pending, mask, info);
if (!signr) {
signr = __dequeue_signal(&tsk->signal->shared_pending,
mask, info);
@@ -407,8 +406,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
}
}
}
- if (likely(tsk == current))
- recalc_sigpending();
+ recalc_sigpending();
if (signr && unlikely(sig_kernel_stop(signr))) {
/*
* Set a marker that we have dequeued a stop signal. Our
@@ -425,7 +423,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
}
- if (signr && likely(tsk == current) &&
+ if (signr &&
((info->si_code & __SI_MASK) == __SI_TIMER) &&
info->si_sys_private){
/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6ace893c17c..53a456ebf6d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -303,6 +303,14 @@ static ctl_table kern_table[] = {
.proc_handler = &proc_dointvec,
},
#endif
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "sched_compat_yield",
+ .data = &sysctl_sched_compat_yield,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
#ifdef CONFIG_PROVE_LOCKING
{
.ctl_name = CTL_UNNUMBERED,
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index cd91237dbfe..de6a2d6b3eb 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -226,7 +226,7 @@ static void sync_cmos_clock(unsigned long dummy)
static void notify_cmos_timer(void)
{
- if (no_sync_cmos_clock)
+ if (!no_sync_cmos_clock)
mod_timer(&sync_cmos_timer, jiffies + 1);
}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index db8e0f3d409..0962e057766 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -383,11 +383,7 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-
- if(!cpus_empty(tick_broadcast_oneshot_mask))
- tick_broadcast_set_event(ktime_get(), 1);
-
- return cpu_isset(smp_processor_id(), tick_broadcast_oneshot_mask);
+ return 0;
}
/*
@@ -549,20 +545,17 @@ void tick_broadcast_switch_to_oneshot(void)
*/
void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
{
- struct clock_event_device *bc;
unsigned long flags;
unsigned int cpu = *cpup;
spin_lock_irqsave(&tick_broadcast_lock, flags);
- bc = tick_broadcast_device.evtdev;
+ /*
+ * Clear the broadcast mask flag for the dead cpu, but do not
+ * stop the broadcast device!
+ */
cpu_clear(cpu, tick_broadcast_oneshot_mask);
- if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) {
- if (bc && cpus_empty(tick_broadcast_oneshot_mask))
- clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
- }
-
spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b416995b975..8c3fef1db09 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -160,6 +160,18 @@ void tick_nohz_stop_sched_tick(void)
cpu = smp_processor_id();
ts = &per_cpu(tick_cpu_sched, cpu);
+ /*
+ * If this cpu is offline and it is the one which updates
+ * jiffies, then give up the assignment and let it be taken by
+ * the cpu which runs the tick timer next. If we don't drop
+ * this here the jiffies might be stale and do_timer() never
+ * invoked.
+ */
+ if (unlikely(!cpu_online(cpu))) {
+ if (cpu == tick_do_timer_cpu)
+ tick_do_timer_cpu = -1;
+ }
+
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
goto end;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index acc417b5a9b..4ad79f6bdec 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -217,6 +217,7 @@ static void change_clocksource(void)
}
#else
static inline void change_clocksource(void) { }
+static inline s64 __get_nsec_offset(void) { return 0; }
#endif
/**
@@ -280,6 +281,8 @@ void __init timekeeping_init(void)
static int timekeeping_suspended;
/* time in seconds when suspend began */
static unsigned long timekeeping_suspend_time;
+/* xtime offset when we went into suspend */
+static s64 timekeeping_suspend_nsecs;
/**
* timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -305,6 +308,8 @@ static int timekeeping_resume(struct sys_device *dev)
wall_to_monotonic.tv_sec -= sleep_length;
total_sleep_time += sleep_length;
}
+ /* Make sure that we have the correct xtime reference */
+ timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
/* re-base the last cycle value */
clock->cycle_last = clocksource_read(clock);
clock->error = 0;
@@ -325,9 +330,12 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
{
unsigned long flags;
+ timekeeping_suspend_time = read_persistent_clock();
+
write_seqlock_irqsave(&xtime_lock, flags);
+ /* Get the current xtime offset */
+ timekeeping_suspend_nsecs = __get_nsec_offset();
timekeeping_suspended = 1;
- timekeeping_suspend_time = read_persistent_clock();
write_sequnlock_irqrestore(&xtime_lock, flags);
clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
diff --git a/kernel/user.c b/kernel/user.c
index e7d11cef699..9ca2848fc35 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -55,25 +55,22 @@ struct user_struct root_user = {
/*
* These routines must be called with the uidhash spinlock held!
*/
-static inline void uid_hash_insert(struct user_struct *up, struct list_head *hashent)
+static inline void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
{
- list_add(&up->uidhash_list, hashent);
+ hlist_add_head(&up->uidhash_node, hashent);
}
static inline void uid_hash_remove(struct user_struct *up)
{
- list_del(&up->uidhash_list);
+ hlist_del_init(&up->uidhash_node);
}
-static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *hashent)
+static inline struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
{
- struct list_head *up;
-
- list_for_each(up, hashent) {
- struct user_struct *user;
-
- user = list_entry(up, struct user_struct, uidhash_list);
+ struct user_struct *user;
+ struct hlist_node *h;
+ hlist_for_each_entry(user, h, hashent, uidhash_node) {
if(user->uid == uid) {
atomic_inc(&user->__count);
return user;
@@ -122,7 +119,7 @@ void free_uid(struct user_struct *up)
struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
{
- struct list_head *hashent = uidhashentry(ns, uid);
+ struct hlist_head *hashent = uidhashentry(ns, uid);
struct user_struct *up;
spin_lock_irq(&uidhash_lock);
@@ -202,6 +199,30 @@ void switch_uid(struct user_struct *new_user)
suid_keys(current);
}
+void release_uids(struct user_namespace *ns)
+{
+ int i;
+ unsigned long flags;
+ struct hlist_head *head;
+ struct hlist_node *nd;
+
+ spin_lock_irqsave(&uidhash_lock, flags);
+ /*
+ * collapse the chains so that the user_struct-s will
+ * be still alive, but not in hashes. subsequent free_uid()
+ * will free them.
+ */
+ for (i = 0; i < UIDHASH_SZ; i++) {
+ head = ns->uidhash_table + i;
+ while (!hlist_empty(head)) {
+ nd = head->first;
+ hlist_del_init(nd);
+ }
+ }
+ spin_unlock_irqrestore(&uidhash_lock, flags);
+
+ free_uid(ns->root_user);
+}
static int __init uid_cache_init(void)
{
@@ -211,7 +232,7 @@ static int __init uid_cache_init(void)
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
for(n = 0; n < UIDHASH_SZ; ++n)
- INIT_LIST_HEAD(init_user_ns.uidhash_table + n);
+ INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 85af9422ea6..7af90fc4f0f 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -39,7 +39,7 @@ static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
kref_init(&ns->kref);
for (n = 0; n < UIDHASH_SZ; ++n)
- INIT_LIST_HEAD(ns->uidhash_table + n);
+ INIT_HLIST_HEAD(ns->uidhash_table + n);
/* Insert new root user. */
ns->root_user = alloc_uid(ns, 0);
@@ -81,7 +81,7 @@ void free_user_ns(struct kref *kref)
struct user_namespace *ns;
ns = container_of(kref, struct user_namespace, kref);
- free_uid(ns->root_user);
+ release_uids(ns);
kfree(ns);
}
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 9d8180a0f0d..816d7b24fa0 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -28,7 +28,9 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
if (!ns)
return ERR_PTR(-ENOMEM);
+ down_read(&uts_sem);
memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+ up_read(&uts_sem);
kref_init(&ns->kref);
return ns;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-06-01 04:05:49 +0000