summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c12
-rw-r--r--kernel/bpf/verifier.c5
-rw-r--r--kernel/cpuset.c2
-rw-r--r--kernel/events/core.c60
-rw-r--r--kernel/extable.c2
-rw-r--r--kernel/gcov/base.c6
-rw-r--r--kernel/gcov/gcc_4_7.c4
-rw-r--r--kernel/irq/manage.c4
-rw-r--r--kernel/locking/locktorture.c4
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/pid.c11
-rw-r--r--kernel/resource.c13
-rw-r--r--kernel/sched/core.c37
-rw-r--r--kernel/sched/loadavg.c4
-rw-r--r--kernel/sched/sched.h13
-rw-r--r--kernel/signal.c24
-rw-r--r--kernel/sysctl.c5
-rw-r--r--kernel/time/alarmtimer.c15
-rw-r--r--kernel/time/timekeeping.c47
-rw-r--r--kernel/trace/ftrace.c2
-rw-r--r--kernel/trace/trace.c3
-rw-r--r--kernel/trace/trace_events_filter.c4
-rw-r--r--kernel/trace/trace_kprobe.c21
-rw-r--r--kernel/workqueue.c23
24 files changed, 199 insertions, 124 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 939945a5649c..a162661c9d60 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule)
list_del(&krule->rlist);
if (list_empty(&watch->rules)) {
+ /*
+ * audit_remove_watch() drops our reference to 'parent' which
+ * can get freed. Grab our own reference to be safe.
+ */
+ audit_get_parent(parent);
audit_remove_watch(watch);
-
- if (list_empty(&parent->watches)) {
- audit_get_parent(parent);
+ if (list_empty(&parent->watches))
fsnotify_destroy_mark(&parent->mark, audit_watch_group);
- audit_put_parent(parent);
- }
+ audit_put_parent(parent);
}
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2cbfba78d3db..863e24f1e62e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -754,6 +754,11 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose("R%d leaks addr into mem\n", insn->src_reg);
+ return -EACCES;
+ }
+
/* check whether atomic_add can read the memory */
err = check_mem_access(env, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3b5e5430f5d0..2924b6faa469 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -60,6 +60,7 @@
#include <linux/cgroup.h>
#include <linux/wait.h>
+struct static_key cpusets_pre_enable_key __read_mostly = STATIC_KEY_INIT_FALSE;
struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
/* See "Frequency meter" comments, below. */
@@ -1909,6 +1910,7 @@ static struct cftype files[] = {
{
.name = "memory_pressure",
.read_u64 = cpuset_read_u64,
+ .private = FILE_MEMORY_PRESSURE,
},
{
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 22350b15b4e7..3697063dd09a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6410,21 +6410,6 @@ static void perf_log_itrace_start(struct perf_event *event)
perf_output_end(&handle);
}
-static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
-{
- /*
- * Due to interrupt latency (AKA "skid"), we may enter the
- * kernel before taking an overflow, even if the PMU is only
- * counting user events.
- * To avoid leaking information to userspace, we must always
- * reject kernel samples when exclude_kernel is set.
- */
- if (event->attr.exclude_kernel && !user_mode(regs))
- return false;
-
- return true;
-}
-
/*
* Generic event overflow handling, sampling.
*/
@@ -6472,12 +6457,6 @@ static int __perf_event_overflow(struct perf_event *event,
}
/*
- * For security, drop the skid kernel samples if necessary.
- */
- if (!sample_is_allowed(event, regs))
- return ret;
-
- /*
* XXX event_limit might not quite work as expected on inherited
* events
*/
@@ -8494,28 +8473,27 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
/*
- * Do not allow to attach to a group in a different
- * task or CPU context:
+ * Make sure we're both events for the same CPU;
+ * grouping events for different CPUs is broken; since
+ * you can never concurrently schedule them anyhow.
*/
- if (move_group) {
- /*
- * Make sure we're both on the same task, or both
- * per-cpu events.
- */
- if (group_leader->ctx->task != ctx->task)
- goto err_context;
+ if (group_leader->cpu != event->cpu)
+ goto err_context;
- /*
- * Make sure we're both events for the same CPU;
- * grouping events for different CPUs is broken; since
- * you can never concurrently schedule them anyhow.
- */
- if (group_leader->cpu != event->cpu)
- goto err_context;
- } else {
- if (group_leader->ctx != ctx)
- goto err_context;
- }
+ /*
+ * Make sure we're both on the same task, or both
+ * per-CPU events.
+ */
+ if (group_leader->ctx->task != ctx->task)
+ goto err_context;
+
+ /*
+ * Do not allow to attach to a group in a different task
+ * or CPU context. If we're moving SW events, we'll fix
+ * this up later, so allow that.
+ */
+ if (!move_group && group_leader->ctx != ctx)
+ goto err_context;
/*
* Only a group leader can be exclusive or pinned
diff --git a/kernel/extable.c b/kernel/extable.c
index e820ccee9846..4f06fc34313f 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr)
return 0;
}
-int core_kernel_text(unsigned long addr)
+int notrace core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
addr < (unsigned long)_etext)
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 7080ae1eb6c1..f850e906564b 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
}
EXPORT_SYMBOL(__gcov_merge_icall_topn);
+void __gcov_exit(void)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_exit);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index e25e92fb44fa..46a18e72bce6 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include "gcov.h"
-#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#if (__GNUC__ >= 7)
+#define GCOV_COUNTERS 9
+#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
#define GCOV_COUNTERS 10
#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
#define GCOV_COUNTERS 9
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 6ead200370da..a079ed14f230 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1287,8 +1287,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
ret = __irq_set_trigger(desc,
new->flags & IRQF_TRIGGER_MASK);
- if (ret)
+ if (ret) {
+ irq_release_resources(desc);
goto out_mask;
+ }
}
desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8ef1919d63b2..d580b7d6ee6d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -776,6 +776,8 @@ static void lock_torture_cleanup(void)
else
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
+ kfree(cxt.lwsa);
+ kfree(cxt.lrsa);
torture_cleanup_end();
}
@@ -917,6 +919,8 @@ static int __init lock_torture_init(void)
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+ kfree(writer_tasks);
+ writer_tasks = NULL;
firsterr = -ENOMEM;
goto unwind;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index 41e2b54f36b5..1d07cf9af849 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -167,7 +167,7 @@ void panic(const char *fmt, ...)
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
- pr_emerg("Rebooting in %d seconds..", panic_timeout);
+ pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
diff --git a/kernel/pid.c b/kernel/pid.c
index 78b3d9f80d44..b17263be9082 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -526,8 +526,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
if (!ns)
ns = task_active_pid_ns(current);
if (likely(pid_alive(task))) {
- if (type != PIDTYPE_PID)
+ if (type != PIDTYPE_PID) {
+ if (type == __PIDTYPE_TGID)
+ type = PIDTYPE_PID;
task = task->group_leader;
+ }
nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
}
rcu_read_unlock();
@@ -536,12 +539,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
}
EXPORT_SYMBOL(__task_pid_nr_ns);
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
- return pid_nr_ns(task_tgid(tsk), ns);
-}
-EXPORT_SYMBOL(task_tgid_nr_ns);
-
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{
return ns_of_pid(task_pid(tsk));
diff --git a/kernel/resource.c b/kernel/resource.c
index 249b1eb1e6e1..a4a94e700fb9 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -105,16 +105,25 @@ static int r_show(struct seq_file *m, void *v)
{
struct resource *root = m->private;
struct resource *r = v, *p;
+ unsigned long long start, end;
int width = root->end < 0x10000 ? 4 : 8;
int depth;
for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
if (p->parent == root)
break;
+
+ if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) {
+ start = r->start;
+ end = r->end;
+ } else {
+ start = end = 0;
+ }
+
seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
depth * 2, "",
- width, (unsigned long long) r->start,
- width, (unsigned long long) r->end,
+ width, start,
+ width, end,
r->name ? r->name : "<BAD>");
return 0;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20253dbc8610..dece705b7f8c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5553,7 +5553,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
case CPU_UP_PREPARE:
rq->calc_load_update = calc_load_update;
- account_reset_rq(rq);
break;
case CPU_ONLINE:
@@ -6123,6 +6122,9 @@ enum s_alloc {
* Build an iteration mask that can exclude certain CPUs from the upwards
* domain traversal.
*
+ * Only CPUs that can arrive at this group should be considered to continue
+ * balancing.
+ *
* Asymmetric node setups can result in situations where the domain tree is of
* unequal depth, make sure to skip domains that already cover the entire
* range.
@@ -6134,18 +6136,31 @@ enum s_alloc {
*/
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
{
- const struct cpumask *span = sched_domain_span(sd);
+ const struct cpumask *sg_span = sched_group_cpus(sg);
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
- for_each_cpu(i, span) {
+ for_each_cpu(i, sg_span) {
sibling = *per_cpu_ptr(sdd->sd, i);
- if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+ /*
+ * Can happen in the asymmetric case, where these siblings are
+ * unused. The mask will not be empty because those CPUs that
+ * do have the top domain _should_ span the domain.
+ */
+ if (!sibling->child)
+ continue;
+
+ /* If we would not end up here, we can't continue from here */
+ if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
continue;
cpumask_set_cpu(i, sched_group_mask(sg));
}
+
+ /* We must not have empty masks here */
+ WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg)));
}
/*
@@ -8237,11 +8252,20 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);
- sched_online_group(tg, parent);
-
return &tg->css;
}
+/* Expose task group only after completing cgroup initialization */
+static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+ struct task_group *parent = css_tg(css->parent);
+
+ if (parent)
+ sched_online_group(tg, parent);
+ return 0;
+}
+
static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
@@ -8616,6 +8640,7 @@ static struct cftype cpu_files[] = {
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
+ .css_online = cpu_cgroup_css_online,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.fork = cpu_cgroup_fork,
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index b0b93fd33af9..f8e8d68ed3fd 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -201,8 +201,9 @@ void calc_load_exit_idle(void)
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update))
return;
@@ -211,7 +212,6 @@ void calc_load_exit_idle(void)
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4e5db65d1aab..55d92a1ca070 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1770,16 +1770,3 @@ static inline u64 irq_time_read(int cpu)
}
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-static inline void account_reset_rq(struct rq *rq)
-{
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
- rq->prev_irq_time = 0;
-#endif
-#ifdef CONFIG_PARAVIRT
- rq->prev_steal_time = 0;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
- rq->prev_steal_time_rq = 0;
-#endif
-}
diff --git a/kernel/signal.c b/kernel/signal.c
index f3f1f7a972fd..5d50ea899b6d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task)
* fresh group stop. Read comment in do_signal_stop() for details.
*/
if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
- sig->flags = SIGNAL_STOP_STOPPED;
+ signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED);
return true;
}
return false;
@@ -503,7 +503,8 @@ int unhandled_signal(struct task_struct *tsk, int sig)
return !tsk->ptrace;
}
-static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+static void collect_signal(int sig, struct sigpending *list, siginfo_t *info,
+ bool *resched_timer)
{
struct sigqueue *q, *first = NULL;
@@ -525,6 +526,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
still_pending:
list_del_init(&first->list);
copy_siginfo(info, &first->info);
+
+ *resched_timer =
+ (first->flags & SIGQUEUE_PREALLOC) &&
+ (info->si_code == SI_TIMER) &&
+ (info->si_sys_private);
+
__sigqueue_free(first);
} else {
/*
@@ -541,12 +548,12 @@ still_pending:
}
static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
- siginfo_t *info)
+ siginfo_t *info, bool *resched_timer)
{
int sig = next_signal(pending, mask);
if (sig)
- collect_signal(sig, pending, info);
+ collect_signal(sig, pending, info, resched_timer);
return sig;
}
@@ -558,15 +565,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
*/
int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
+ bool resched_timer = false;
int signr;
/* We only dequeue private signals from ourselves, we don't let
* signalfd steal them
*/
- signr = __dequeue_signal(&tsk->pending, mask, info);
+ signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
if (!signr) {
signr = __dequeue_signal(&tsk->signal->shared_pending,
- mask, info);
+ mask, info, &resched_timer);
/*
* itimer signal ?
*
@@ -611,7 +619,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
*/
current->jobctl |= JOBCTL_STOP_DEQUEUED;
}
- if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
+ if (resched_timer) {
/*
* Release the siglock to ensure proper locking order
* of timer locks outside of siglocks. Note, we leave
@@ -837,7 +845,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
* will take ->siglock, notice SIGNAL_CLD_MASK, and
* notify its parent. See get_signal_to_deliver().
*/
- signal->flags = why | SIGNAL_STOP_CONTINUED;
+ signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
signal->group_stop_count = 0;
signal->group_exit_code = 0;
}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 300d64162aff..002ec084124b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -174,7 +174,7 @@ extern int no_unaligned_warning;
#define SYSCTL_WRITES_WARN 0
#define SYSCTL_WRITES_STRICT 1
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -2067,9 +2067,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
if (write) {
if (*negp)
return -EINVAL;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
+ *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 7fbba635a549..6fcc367ad531 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -339,7 +339,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start)
{
struct alarm_base *base = &alarm_bases[alarm->type];
- start = ktime_add(start, base->gettime());
+ start = ktime_add_safe(start, base->gettime());
alarm_start(alarm, start);
}
EXPORT_SYMBOL_GPL(alarm_start_relative);
@@ -425,7 +425,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
overrun++;
}
- alarm->node.expires = ktime_add(alarm->node.expires, interval);
+ alarm->node.expires = ktime_add_safe(alarm->node.expires, interval);
return overrun;
}
EXPORT_SYMBOL_GPL(alarm_forward);
@@ -611,13 +611,22 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
/* start the timer */
timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
+
+ /*
+ * Rate limit to the tick as a hot fix to prevent DOS. Will be
+ * mopped up later.
+ */
+ if (timr->it.alarm.interval.tv64 &&
+ ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC)
+ timr->it.alarm.interval = ktime_set(0, TICK_NSEC);
+
exp = timespec_to_ktime(new_setting->it_value);
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now;
now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
- exp = ktime_add(now, exp);
+ exp = ktime_add_safe(now, exp);
}
alarm_start(&timr->it.alarm.alarmtimer, exp);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 738012d68117..6e4866834d26 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -116,6 +116,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
tk->offs_boot = ktime_add(tk->offs_boot, delta);
}
+/*
+ * tk_clock_read - atomic clocksource read() helper
+ *
+ * This helper is necessary to use in the read paths because, while the
+ * seqlock ensures we don't return a bad value while structures are updated,
+ * it doesn't protect from potential crashes. There is the possibility that
+ * the tkr's clocksource may change between the read reference, and the
+ * clock reference passed to the read function. This can cause crashes if
+ * the wrong clocksource is passed to the wrong read function.
+ * This isn't necessary to use when holding the timekeeper_lock or doing
+ * a read of the fast-timekeeper tkrs (which is protected by its own locking
+ * and update logic).
+ */
+static inline u64 tk_clock_read(struct tk_read_base *tkr)
+{
+ struct clocksource *clock = READ_ONCE(tkr->clock);
+
+ return clock->read(clock);
+}
+
#ifdef CONFIG_DEBUG_TIMEKEEPING
#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
@@ -173,7 +193,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
*/
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tkr->read(tkr->clock);
+ now = tk_clock_read(tkr);
last = tkr->cycle_last;
mask = tkr->mask;
max = tkr->clock->max_cycles;
@@ -207,7 +227,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
cycle_t cycle_now, delta;
/* read clocksource */
- cycle_now = tkr->read(tkr->clock);
+ cycle_now = tk_clock_read(tkr);
/* calculate the delta since the last update_wall_time */
delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
@@ -235,12 +255,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
old_clock = tk->tkr_mono.clock;
tk->tkr_mono.clock = clock;
- tk->tkr_mono.read = clock->read;
tk->tkr_mono.mask = clock->mask;
- tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+ tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);
tk->tkr_raw.clock = clock;
- tk->tkr_raw.read = clock->read;
tk->tkr_raw.mask = clock->mask;
tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
@@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
now += timekeeping_delta_to_ns(tkr,
clocksource_delta(
- tkr->read(tkr->clock),
+ tk_clock_read(tkr),
tkr->cycle_last,
tkr->mask));
} while (read_seqcount_retry(&tkf->seq, seq));
@@ -432,6 +450,10 @@ static cycle_t dummy_clock_read(struct clocksource *cs)
return cycles_at_suspend;
}
+static struct clocksource dummy_clock = {
+ .read = dummy_clock_read,
+};
+
/**
* halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
* @tk: Timekeeper to snapshot.
@@ -448,13 +470,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk)
struct tk_read_base *tkr = &tk->tkr_mono;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
- cycles_at_suspend = tkr->read(tkr->clock);
- tkr_dummy.read = dummy_clock_read;
+ cycles_at_suspend = tk_clock_read(tkr);
+ tkr_dummy.clock = &dummy_clock;
update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
tkr = &tk->tkr_raw;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
- tkr_dummy.read = dummy_clock_read;
+ tkr_dummy.clock = &dummy_clock;
update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
}
@@ -618,11 +640,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
*/
static void timekeeping_forward_now(struct timekeeper *tk)
{
- struct clocksource *clock = tk->tkr_mono.clock;
cycle_t cycle_now, delta;
s64 nsec;
- cycle_now = tk->tkr_mono.read(clock);
+ cycle_now = tk_clock_read(&tk->tkr_mono);
delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
tk->tkr_mono.cycle_last = cycle_now;
tk->tkr_raw.cycle_last = cycle_now;
@@ -1405,7 +1426,7 @@ void timekeeping_resume(void)
* The less preferred source will only be tried if there is no better
* usable source. The rtc part is handled separately in rtc core code.
*/
- cycle_now = tk->tkr_mono.read(clock);
+ cycle_now = tk_clock_read(&tk->tkr_mono);
if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
cycle_now > tk->tkr_mono.cycle_last) {
u64 num, max = ULLONG_MAX;
@@ -1800,7 +1821,7 @@ void update_wall_time(void)
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
offset = real_tk->cycle_interval;
#else
- offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+ offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
#endif
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 34b2a0d5cf1a..eba904bae48c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3535,7 +3535,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
int exclude_mod = 0;
int found = 0;
int ret;
- int clear_filter;
+ int clear_filter = 0;
if (func) {
func_g.type = filter_parse_regex(func, len, &func_g.search,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4c21c0b7dc91..d59ebd9d21df 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1660,7 +1660,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
TRACE_FLAG_IRQS_NOSUPPORT |
#endif
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
- ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+ ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
}
@@ -6737,6 +6737,7 @@ static int instance_rmdir(const char *name)
}
kfree(tr->topts);
+ free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 6816302542b2..f0e5408499b6 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1979,6 +1979,10 @@ static int create_filter(struct trace_event_call *call,
if (err && set_str)
append_filter_err(ps, filter);
}
+ if (err && !set_str) {
+ free_event_filter(filter);
+ filter = NULL;
+ }
create_filter_finish(ps);
*filterp = filter;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 12ea4ea619ee..e9092a0247bf 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -659,30 +659,25 @@ static int create_trace_kprobe(int argc, char **argv)
pr_info("Probe point is not specified.\n");
return -EINVAL;
}
- if (isdigit(argv[1][0])) {
- if (is_return) {
- pr_info("Return probe point must be a symbol.\n");
- return -EINVAL;
- }
- /* an address specified */
- ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
- if (ret) {
- pr_info("Failed to parse address.\n");
- return ret;
- }
- } else {
+
+ /* try to parse an address. if that fails, try to read the
+ * input as a symbol. */
+ if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
/* a symbol specified */
symbol = argv[1];
/* TODO: support .init module functions */
ret = traceprobe_split_symbol_offset(symbol, &offset);
if (ret) {
- pr_info("Failed to parse symbol.\n");
+ pr_info("Failed to parse either an address or a symbol.\n");
return ret;
}
if (offset && is_return) {
pr_info("Return probe must be used without offset.\n");
return -EINVAL;
}
+ } else if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
+ return -EINVAL;
}
argc -= 2; argv += 2;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2c2f971f3e75..23231237f2e2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3647,8 +3647,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
return -EINVAL;
/* creating multiple pwqs breaks ordering guarantee */
- if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
- return -EINVAL;
+ if (!list_empty(&wq->pwqs)) {
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+ return -EINVAL;
+
+ wq->flags &= ~__WQ_ORDERED;
+ }
ctx = apply_wqattrs_prepare(wq, attrs);
@@ -3834,6 +3838,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
+ /*
+ * Unbound && max_active == 1 used to imply ordered, which is no
+ * longer the case on NUMA machines due to per-node pools. While
+ * alloc_ordered_workqueue() is the right way to create an ordered
+ * workqueue, keep the previous behavior to avoid subtle breakages
+ * on NUMA.
+ */
+ if ((flags & WQ_UNBOUND) && max_active == 1)
+ flags |= __WQ_ORDERED;
+
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
flags |= WQ_UNBOUND;
@@ -4022,13 +4036,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
struct pool_workqueue *pwq;
/* disallow meddling with max_active for ordered workqueues */
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return;
max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
mutex_lock(&wq->mutex);
+ wq->flags &= ~__WQ_ORDERED;
wq->saved_max_active = max_active;
for_each_pwq(pwq, wq)
@@ -5154,7 +5169,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
* attributes breaks ordering guarantee. Disallow exposing ordered
* workqueues.
*/
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return -EINVAL;
wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-12 14:51:20 +0000