summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cpu.c38
-rw-r--r--kernel/events/core.c14
-rw-r--r--kernel/exit.c14
-rw-r--r--kernel/futex.c13
-rw-r--r--kernel/irq/affinity.c121
-rw-r--r--kernel/irq/chip.c12
-rw-r--r--kernel/irq/debugfs.c2
-rw-r--r--kernel/irq/handle.c2
-rw-r--r--kernel/irq/internals.h8
-rw-r--r--kernel/irq/irqdesc.c9
-rw-r--r--kernel/irq/irqdomain.c2
-rw-r--r--kernel/irq/manage.c4
-rw-r--r--kernel/kthread.c8
-rw-r--r--kernel/locking/rwsem-xadd.c11
-rw-r--r--kernel/sched/core.c19
-rw-r--r--kernel/sched/fair.c1
-rw-r--r--kernel/sched/psi.c21
-rw-r--r--kernel/smp.c2
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/time/posix-cpu-timers.c1
-rw-r--r--kernel/trace/trace_uprobe.c9
-rw-r--r--kernel/workqueue.c23
-rw-r--r--kernel/workqueue_internal.h6
23 files changed, 219 insertions, 124 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 91d5c38eb7e5..d1c6d152da89 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { }
#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
-EXPORT_SYMBOL_GPL(cpu_smt_control);
-
-static bool cpu_smt_available __read_mostly;
void __init cpu_smt_disable(bool force)
{
@@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force)
/*
* The decision whether SMT is supported can only be done after the full
- * CPU identification. Called from architecture code before non boot CPUs
- * are brought up.
- */
-void __init cpu_smt_check_topology_early(void)
-{
- if (!topology_smt_supported())
- cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
-}
-
-/*
- * If SMT was disabled by BIOS, detect it here, after the CPUs have been
- * brought online. This ensures the smt/l1tf sysfs entries are consistent
- * with reality. cpu_smt_available is set to true during the bringup of non
- * boot CPUs when a SMT sibling is detected. Note, this may overwrite
- * cpu_smt_control's previous setting.
+ * CPU identification. Called from architecture code.
*/
void __init cpu_smt_check_topology(void)
{
- if (!cpu_smt_available)
+ if (!topology_smt_supported())
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
}
@@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable);
static inline bool cpu_smt_allowed(unsigned int cpu)
{
- if (topology_is_primary_thread(cpu))
+ if (cpu_smt_control == CPU_SMT_ENABLED)
return true;
- /*
- * If the CPU is not a 'primary' thread and the booted_once bit is
- * set then the processor has SMT support. Store this information
- * for the late check of SMT support in cpu_smt_check_topology().
- */
- if (per_cpu(cpuhp_state, cpu).booted_once)
- cpu_smt_available = true;
-
- if (cpu_smt_control == CPU_SMT_ENABLED)
+ if (topology_is_primary_thread(cpu))
return true;
/*
@@ -2090,10 +2065,8 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
*/
cpuhp_offline_cpu_device(cpu);
}
- if (!ret) {
+ if (!ret)
cpu_smt_control = ctrlval;
- arch_smt_update();
- }
cpu_maps_update_done();
return ret;
}
@@ -2104,7 +2077,6 @@ static int cpuhp_smt_enable(void)
cpu_maps_update_begin();
cpu_smt_control = CPU_SMT_ENABLED;
- arch_smt_update();
for_each_present_cpu(cpu) {
/* Skip online CPUs and CPUs on offline nodes */
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cd13a30f732..e5ede6918050 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-
- if (ret || !write)
- return ret;
-
+ int ret;
+ int perf_cpu = sysctl_perf_cpu_time_max_percent;
/*
* If throttling is disabled don't allow the write:
*/
- if (sysctl_perf_cpu_time_max_percent == 100 ||
- sysctl_perf_cpu_time_max_percent == 0)
+ if (write && (perf_cpu == 100 || perf_cpu == 0))
return -EINVAL;
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
update_perf_cpu_limits();
diff --git a/kernel/exit.c b/kernel/exit.c
index 284f2fe9a293..2639a30a8aa5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -307,7 +307,7 @@ void rcuwait_wake_up(struct rcuwait *w)
* MB (A) MB (B)
* [L] cond [L] tsk
*/
- smp_rmb(); /* (B) */
+ smp_mb(); /* (B) */
/*
* Avoid using task_rcu_dereference() magic as long as we are careful,
@@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p)
return NULL;
}
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+ struct list_head *dead)
__releases(&tasklist_lock)
__acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *reaper = pid_ns->child_reaper;
+ struct task_struct *p, *n;
if (likely(reaper != father))
return reaper;
@@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father)
panic("Attempted to kill init! exitcode=0x%08x\n",
father->signal->group_exit_code ?: father->exit_code);
}
+
+ list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+ list_del_init(&p->ptrace_entry);
+ release_task(p);
+ }
+
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
@@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father,
exit_ptrace(father, dead);
/* Can drop and reacquire tasklist_lock */
- reaper = find_child_reaper(father);
+ reaper = find_child_reaper(father, dead);
if (list_empty(&father->children))
return;
diff --git a/kernel/futex.c b/kernel/futex.c
index be3bff2315ff..fdd312da0992 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1452,11 +1452,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
return;
- /*
- * Queue the task for later wakeup for after we've released
- * the hb->lock. wake_q_add() grabs reference to p.
- */
- wake_q_add(wake_q, p);
+ get_task_struct(p);
__unqueue_futex(q);
/*
* The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -1466,6 +1462,13 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
* plist_del in __unqueue_futex().
*/
smp_store_release(&q->lock_ptr, NULL);
+
+ /*
+ * Queue the task for later wakeup for after we've released
+ * the hb->lock. wake_q_add() grabs reference to p.
+ */
+ wake_q_add(wake_q, p);
+ put_task_struct(p);
}
/*
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 45b68b4ea48b..f18cd5aa33e8 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -9,7 +9,7 @@
#include <linux/cpu.h>
static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
- int cpus_per_vec)
+ unsigned int cpus_per_vec)
{
const struct cpumask *siblmsk;
int cpu, sibl;
@@ -95,15 +95,17 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
}
static int __irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs, int firstvec,
+ unsigned int startvec,
+ unsigned int numvecs,
+ unsigned int firstvec,
cpumask_var_t *node_to_cpumask,
const struct cpumask *cpu_mask,
struct cpumask *nmsk,
struct irq_affinity_desc *masks)
{
- int n, nodes, cpus_per_vec, extra_vecs, done = 0;
- int last_affv = firstvec + numvecs;
- int curvec = startvec;
+ unsigned int n, nodes, cpus_per_vec, extra_vecs, done = 0;
+ unsigned int last_affv = firstvec + numvecs;
+ unsigned int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
if (!cpumask_weight(cpu_mask))
@@ -117,18 +119,16 @@ static int __irq_build_affinity_masks(const struct irq_affinity *affd,
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_or(&masks[curvec].mask,
- &masks[curvec].mask,
- node_to_cpumask[n]);
+ cpumask_or(&masks[curvec].mask, &masks[curvec].mask,
+ node_to_cpumask[n]);
if (++curvec == last_affv)
curvec = firstvec;
}
- done = numvecs;
- goto out;
+ return numvecs;
}
for_each_node_mask(n, nodemsk) {
- int ncpus, v, vecs_to_assign, vecs_per_node;
+ unsigned int ncpus, v, vecs_to_assign, vecs_per_node;
/* Spread the vectors per node */
vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
@@ -163,8 +163,6 @@ static int __irq_build_affinity_masks(const struct irq_affinity *affd,
curvec = firstvec;
--nodes;
}
-
-out:
return done;
}
@@ -174,19 +172,24 @@ out:
* 2) spread other possible CPUs on these vectors
*/
static int irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs, int firstvec,
- cpumask_var_t *node_to_cpumask,
+ unsigned int startvec, unsigned int numvecs,
+ unsigned int firstvec,
struct irq_affinity_desc *masks)
{
- int curvec = startvec, nr_present, nr_others;
- int ret = -ENOMEM;
+ unsigned int curvec = startvec, nr_present, nr_others;
+ cpumask_var_t *node_to_cpumask;
cpumask_var_t nmsk, npresmsk;
+ int ret = -ENOMEM;
if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
return ret;
if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
- goto fail;
+ goto fail_nmsk;
+
+ node_to_cpumask = alloc_node_to_cpumask();
+ if (!node_to_cpumask)
+ goto fail_npresmsk;
ret = 0;
/* Stabilize the cpumasks */
@@ -217,13 +220,22 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
if (nr_present < numvecs)
WARN_ON(nr_present + nr_others < numvecs);
+ free_node_to_cpumask(node_to_cpumask);
+
+ fail_npresmsk:
free_cpumask_var(npresmsk);
- fail:
+ fail_nmsk:
free_cpumask_var(nmsk);
return ret;
}
+static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
+{
+ affd->nr_sets = 1;
+ affd->set_size[0] = affvecs;
+}
+
/**
* irq_create_affinity_masks - Create affinity masks for multiqueue spreading
* @nvecs: The total number of vectors
@@ -232,50 +244,62 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
* Returns the irq_affinity_desc pointer or NULL if allocation failed.
*/
struct irq_affinity_desc *
-irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
+irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
{
- int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
- int curvec, usedvecs;
- cpumask_var_t *node_to_cpumask;
+ unsigned int affvecs, curvec, usedvecs, i;
struct irq_affinity_desc *masks = NULL;
- int i, nr_sets;
/*
- * If there aren't any vectors left after applying the pre/post
- * vectors don't bother with assigning affinity.
+ * Determine the number of vectors which need interrupt affinities
+ * assigned. If the pre/post request exhausts the available vectors
+ * then nothing to do here except for invoking the calc_sets()
+ * callback so the device driver can adjust to the situation. If there
+ * is only a single vector, then managing the queue is pointless as
+ * well.
*/
- if (nvecs == affd->pre_vectors + affd->post_vectors)
+ if (nvecs > 1 && nvecs > affd->pre_vectors + affd->post_vectors)
+ affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
+ else
+ affvecs = 0;
+
+ /*
+ * Simple invocations do not provide a calc_sets() callback. Install
+ * the generic one.
+ */
+ if (!affd->calc_sets)
+ affd->calc_sets = default_calc_sets;
+
+ /* Recalculate the sets */
+ affd->calc_sets(affd, affvecs);
+
+ if (WARN_ON_ONCE(affd->nr_sets > IRQ_AFFINITY_MAX_SETS))
return NULL;
- node_to_cpumask = alloc_node_to_cpumask();
- if (!node_to_cpumask)
+ /* Nothing to assign? */
+ if (!affvecs)
return NULL;
masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
if (!masks)
- goto outnodemsk;
+ return NULL;
/* Fill out vectors at the beginning that don't need affinity */
for (curvec = 0; curvec < affd->pre_vectors; curvec++)
cpumask_copy(&masks[curvec].mask, irq_default_affinity);
+
/*
* Spread on present CPUs starting from affd->pre_vectors. If we
* have multiple sets, build each sets affinity mask separately.
*/
- nr_sets = affd->nr_sets;
- if (!nr_sets)
- nr_sets = 1;
-
- for (i = 0, usedvecs = 0; i < nr_sets; i++) {
- int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
+ unsigned int this_vecs = affd->set_size[i];
int ret;
ret = irq_build_affinity_masks(affd, curvec, this_vecs,
- curvec, node_to_cpumask, masks);
+ curvec, masks);
if (ret) {
kfree(masks);
- masks = NULL;
- goto outnodemsk;
+ return NULL;
}
curvec += this_vecs;
usedvecs += this_vecs;
@@ -293,8 +317,6 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
masks[i].is_managed = 1;
-outnodemsk:
- free_node_to_cpumask(node_to_cpumask);
return masks;
}
@@ -304,25 +326,22 @@ outnodemsk:
* @maxvec: The maximum number of vectors available
* @affd: Description of the affinity requirements
*/
-int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd)
+unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
+ const struct irq_affinity *affd)
{
- int resv = affd->pre_vectors + affd->post_vectors;
- int vecs = maxvec - resv;
- int set_vecs;
+ unsigned int resv = affd->pre_vectors + affd->post_vectors;
+ unsigned int set_vecs;
if (resv > minvec)
return 0;
- if (affd->nr_sets) {
- int i;
-
- for (i = 0, set_vecs = 0; i < affd->nr_sets; i++)
- set_vecs += affd->sets[i];
+ if (affd->calc_sets) {
+ set_vecs = maxvec - resv;
} else {
get_online_cpus();
set_vecs = cpumask_weight(cpu_possible_mask);
put_online_cpus();
}
- return resv + min(set_vecs, vecs);
+ return resv + min(set_vecs, maxvec - resv);
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index c32d5f386f68..99b7dd6982a4 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -886,7 +886,11 @@ void handle_percpu_irq(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -915,7 +919,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
unsigned int irq = irq_desc_get_irq(desc);
irqreturn_t res;
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 59a04d2a66df..516c00a5e867 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -258,8 +258,6 @@ static int __init irq_debugfs_init(void)
int irq;
root_dir = debugfs_create_dir("irq", NULL);
- if (!root_dir)
- return -ENOMEM;
irq_domain_debugfs_init(root_dir);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 38554bc35375..6df5ddfdb0f8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -166,7 +166,7 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags
__irq_wake_thread(desc, action);
- /* Fall through to add to randomness */
+ /* Fall through - to add to randomness */
case IRQ_HANDLED:
*flags |= action->flags;
break;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 2a77cdd27ca9..70c3053bc1f6 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -244,12 +244,18 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
#undef __irqd_to_state
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__this_cpu_inc(*desc->kstat_irqs);
__this_cpu_inc(kstat.irqs_sum);
}
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+ __kstat_incr_irqs_this_cpu(desc);
+ desc->tot_count++;
+}
+
static inline int irq_desc_get_node(struct irq_desc *desc)
{
return irq_common_data_get_node(&desc->irq_common_data);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a1d7a7d484e0..13539e12cd80 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
desc->depth = 1;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
+ desc->tot_count = 0;
desc->name = NULL;
desc->owner = owner;
for_each_possible_cpu(cpu)
@@ -457,7 +458,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
/* Validate affinity mask(s) */
if (affinity) {
- for (i = 0; i < cnt; i++, i++) {
+ for (i = 0; i < cnt; i++) {
if (cpumask_empty(&affinity[i].mask))
return -EINVAL;
}
@@ -954,11 +955,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
unsigned int kstat_irqs(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- int cpu;
unsigned int sum = 0;
+ int cpu;
if (!desc || !desc->kstat_irqs)
return 0;
+ if (!irq_settings_is_per_cpu_devid(desc) &&
+ !irq_settings_is_per_cpu(desc))
+ return desc->tot_count;
+
for_each_possible_cpu(cpu)
sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
return sum;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 80818764643d..3bf9793d8825 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1763,8 +1763,6 @@ void __init irq_domain_debugfs_init(struct dentry *root)
struct irq_domain *d;
domain_dir = debugfs_create_dir("domains", root);
- if (!domain_dir)
- return;
debugfs_create_file("default", 0444, domain_dir, NULL,
&irq_domain_debug_fops);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5b570050b9b6..9ec34a2a6638 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -393,6 +393,9 @@ int irq_setup_affinity(struct irq_desc *desc)
}
cpumask_and(&mask, cpu_online_mask, set);
+ if (cpumask_empty(&mask))
+ cpumask_copy(&mask, cpu_online_mask);
+
if (node != NUMA_NO_NODE) {
const struct cpumask *nodemask = cpumask_of_node(node);
@@ -760,6 +763,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
case IRQ_SET_MASK_OK_DONE:
irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
irqd_set(&desc->irq_data, flags);
+ /* fall through */
case IRQ_SET_MASK_OK_NOCOPY:
flags = irqd_get_trigger_type(&desc->irq_data);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 087d18d771b5..65234c89d85b 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,6 +101,12 @@ bool kthread_should_stop(void)
}
EXPORT_SYMBOL(kthread_should_stop);
+bool __kthread_should_park(struct task_struct *k)
+{
+ return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags);
+}
+EXPORT_SYMBOL_GPL(__kthread_should_park);
+
/**
* kthread_should_park - should this kthread park now?
*
@@ -114,7 +120,7 @@ EXPORT_SYMBOL(kthread_should_stop);
*/
bool kthread_should_park(void)
{
- return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+ return __kthread_should_park(current);
}
EXPORT_SYMBOL_GPL(kthread_should_park);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09b180063ee1..50d9af615dc4 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -198,15 +198,22 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
woken++;
tsk = waiter->task;
- wake_q_add(wake_q, tsk);
+ get_task_struct(tsk);
list_del(&waiter->list);
/*
- * Ensure that the last operation is setting the reader
+ * Ensure calling get_task_struct() before setting the reader
* waiter to nil such that rwsem_down_read_failed() cannot
* race with do_exit() by always holding a reference count
* to the task to wakeup.
*/
smp_store_release(&waiter->task, NULL);
+ /*
+ * Ensure issuing the wakeup (either by us or someone else)
+ * after setting the reader waiter to nil.
+ */
+ wake_q_add(wake_q, tsk);
+ /* wake_q_add() already take the task ref */
+ put_task_struct(tsk);
}
adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a674c7db2f29..d8d76a65cfdd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,6 +396,18 @@ static bool set_nr_if_polling(struct task_struct *p)
#endif
#endif
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
struct wake_q_node *node = &task->wake_q;
@@ -405,10 +417,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
* its already queued (either by us or someone else) and will get the
* wakeup due to that.
*
- * This cmpxchg() executes a full barrier, which pairs with the full
- * barrier executed by the wakeup in wake_up_q().
+ * In order to ensure that a pending wakeup will observe our pending
+ * state, even in the failed case, an explicit smp_mb() must be used.
*/
- if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
+ smp_mb__before_atomic();
+ if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))
return;
get_task_struct(task);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 50aa2aba69bd..310d0637fe4b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
#ifdef CONFIG_SCHED_SMT
DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
static inline void set_idle_cores(int cpu, int val)
{
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index fe24de3fbc93..c3484785b179 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -124,6 +124,7 @@
* sampling of the aggregate task states would be.
*/
+#include "../workqueue_internal.h"
#include <linux/sched/loadavg.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
@@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
groupc->tasks[t]++;
write_seqcount_end(&groupc->seq);
-
- if (!delayed_work_pending(&group->clock_work))
- schedule_delayed_work(&group->clock_work, PSI_FREQ);
}
static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set)
{
int cpu = task_cpu(task);
struct psi_group *group;
+ bool wake_clock = true;
void *iter = NULL;
if (!task->pid)
@@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set)
task->psi_flags &= ~clear;
task->psi_flags |= set;
- while ((group = iterate_groups(task, &iter)))
+ /*
+ * Periodic aggregation shuts off if there is a period of no
+ * task changes, so we wake it back up if necessary. However,
+ * don't do this if the task change is the aggregation worker
+ * itself going to sleep, or we'll ping-pong forever.
+ */
+ if (unlikely((clear & TSK_RUNNING) &&
+ (task->flags & PF_WQ_WORKER) &&
+ wq_worker_last_func(task) == psi_update_work))
+ wake_clock = false;
+
+ while ((group = iterate_groups(task, &iter))) {
psi_group_change(group, cpu, clear, set);
+ if (wake_clock && !delayed_work_pending(&group->clock_work))
+ schedule_delayed_work(&group->clock_work, PSI_FREQ);
+ }
}
void psi_memstall_tick(struct task_struct *task, int cpu)
diff --git a/kernel/smp.c b/kernel/smp.c
index 163c451af42e..f4cf1b0bb3b8 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,8 +584,6 @@ void __init smp_init(void)
num_nodes, (num_nodes > 1 ? "s" : ""),
num_cpus, (num_cpus > 1 ? "s" : ""));
- /* Final decision about SMT support */
- cpu_smt_check_topology();
/* Any cleanup work */
smp_cpus_done(setup_max_cpus);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d28813306b2c..10277429ed84 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -89,7 +89,8 @@ static bool ksoftirqd_running(unsigned long pending)
if (pending & SOFTIRQ_NOW_MASK)
return false;
- return tsk && (tsk->state == TASK_RUNNING);
+ return tsk && (tsk->state == TASK_RUNNING) &&
+ !__kthread_should_park(tsk);
}
/*
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 8f0644af40be..80f955210861 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -685,6 +685,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
* set up the signal and overrun bookkeeping.
*/
timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
+ timer->it_interval = ns_to_ktime(timer->it.cpu.incr);
/*
* This acts as a modification timestamp for the timer,
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index e335576b9411..9bde07c06362 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -5,7 +5,7 @@
* Copyright (C) IBM Corporation, 2010-2012
* Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
*/
-#define pr_fmt(fmt) "trace_kprobe: " fmt
+#define pr_fmt(fmt) "trace_uprobe: " fmt
#include <linux/ctype.h>
#include <linux/module.h>
@@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
if (ret >= 0) {
if (ret == maxlen)
dst[ret - 1] = '\0';
+ else
+ /*
+ * Include the terminating null byte. In this case it
+ * was copied by strncpy_from_user but not accounted
+ * for in ret.
+ */
+ ret++;
*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 392be4b252f6..fc5d23d752a5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -910,6 +910,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
}
/**
+ * wq_worker_last_func - retrieve worker's last work function
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+ struct worker *worker = kthread_data(task);
+
+ return worker->last_func;
+}
+
+/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
@@ -2184,6 +2204,9 @@ __acquires(&pool->lock)
if (unlikely(cpu_intensive))
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
+ /* tag the worker for identification in schedule() */
+ worker->last_func = worker->current_func;
+
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 66fbb5a9e633..cb68b03ca89a 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -53,6 +53,9 @@ struct worker {
/* used only by rescuers to point to the target workqueue */
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
+
+ /* used by the scheduler to determine a worker's last known identity */
+ work_func_t last_func;
};
/**
@@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void)
/*
* Scheduler hooks for concurrency managed workqueue. Only to be used from
- * sched/core.c and workqueue.c.
+ * sched/ and workqueue.c.
*/
void wq_worker_waking_up(struct task_struct *task, int cpu);
struct task_struct *wq_worker_sleeping(struct task_struct *task);
+work_func_t wq_worker_last_func(struct task_struct *task);
#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
OpenPOWER on IntegriCloud