summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2021-11-18 13:13:16 -0800
committerJakub Kicinski <kuba@kernel.org>2021-11-18 13:13:16 -0800
commit50fc24944a2a0ef5aab571dcac17f6c5f2613f56 (patch)
tree32477b48cc10073e948eb7b85877dc5a0746749d /kernel
parentbb8cecf8ba127abca8ccd102207a59c55fdae515 (diff)
parent8d0112ac6fd001f95aabb084ec2ccaa3637bc344 (diff)
downloadlinux-50fc24944a2a0ef5aab571dcac17f6c5f2613f56.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.preempt42
-rw-r--r--kernel/bpf/cgroup.c2
-rw-r--r--kernel/bpf/helpers.c2
-rw-r--r--kernel/bpf/syscall.c57
-rw-r--r--kernel/bpf/verifier.c27
-rw-r--r--kernel/events/core.c10
-rw-r--r--kernel/fork.c1
-rw-r--r--kernel/irq/msi.c4
-rw-r--r--kernel/printk/printk.c5
-rw-r--r--kernel/sched/autogroup.c2
-rw-r--r--kernel/sched/core.c53
-rw-r--r--kernel/sched/fair.c4
-rw-r--r--kernel/sched/rt.c12
-rw-r--r--kernel/sched/sched.h3
-rw-r--r--kernel/time/posix-cpu-timers.c19
-rw-r--r--kernel/trace/bpf_trace.c2
-rw-r--r--kernel/trace/trace_events_hist.c17
-rw-r--r--kernel/trace/trace_osnoise.c3
18 files changed, 183 insertions, 82 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 60f1bfc3c7b2..ce77f0265660 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,12 +1,23 @@
# SPDX-License-Identifier: GPL-2.0-only
+config PREEMPT_NONE_BUILD
+ bool
+
+config PREEMPT_VOLUNTARY_BUILD
+ bool
+
+config PREEMPT_BUILD
+ bool
+ select PREEMPTION
+ select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
+
choice
prompt "Preemption Model"
- default PREEMPT_NONE_BEHAVIOUR
+ default PREEMPT_NONE
-config PREEMPT_NONE_BEHAVIOUR
+config PREEMPT_NONE
bool "No Forced Preemption (Server)"
- select PREEMPT_NONE if !PREEMPT_DYNAMIC
+ select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC
help
This is the traditional Linux preemption model, geared towards
throughput. It will still provide good latencies most of the
@@ -18,10 +29,10 @@ config PREEMPT_NONE_BEHAVIOUR
raw processing power of the kernel, irrespective of scheduling
latencies.
-config PREEMPT_VOLUNTARY_BEHAVIOUR
+config PREEMPT_VOLUNTARY
bool "Voluntary Kernel Preemption (Desktop)"
depends on !ARCH_NO_PREEMPT
- select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC
+ select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC
help
This option reduces the latency of the kernel by adding more
"explicit preemption points" to the kernel code. These new
@@ -37,10 +48,10 @@ config PREEMPT_VOLUNTARY_BEHAVIOUR
Select this if you are building a kernel for a desktop system.
-config PREEMPT_BEHAVIOUR
+config PREEMPT
bool "Preemptible Kernel (Low-Latency Desktop)"
depends on !ARCH_NO_PREEMPT
- select PREEMPT
+ select PREEMPT_BUILD
help
This option reduces the latency of the kernel by making
all kernel code (that is not executing in a critical section)
@@ -58,7 +69,7 @@ config PREEMPT_BEHAVIOUR
config PREEMPT_RT
bool "Fully Preemptible Kernel (Real-Time)"
- depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC
+ depends on EXPERT && ARCH_SUPPORTS_RT
select PREEMPTION
help
This option turns the kernel into a real-time kernel by replacing
@@ -75,17 +86,6 @@ config PREEMPT_RT
endchoice
-config PREEMPT_NONE
- bool
-
-config PREEMPT_VOLUNTARY
- bool
-
-config PREEMPT
- bool
- select PREEMPTION
- select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
-
config PREEMPT_COUNT
bool
@@ -95,8 +95,8 @@ config PREEMPTION
config PREEMPT_DYNAMIC
bool "Preemption behaviour defined on boot"
- depends on HAVE_PREEMPT_DYNAMIC
- select PREEMPT
+ depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT
+ select PREEMPT_BUILD
default y
help
This option allows to define the preemption model on the kernel
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 2ca643af9a54..43eb3501721b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sysctl_get_new_value_proto;
case BPF_FUNC_sysctl_set_new_value:
return &bpf_sysctl_set_new_value_proto;
+ case BPF_FUNC_ktime_get_coarse_ns:
+ return &bpf_ktime_get_coarse_ns_proto;
default:
return cgroup_base_func_proto(func_id, prog);
}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1ffd469c217f..649f07623df6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_ringbuf_output:
return &bpf_ringbuf_output_proto;
case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50f96ea4452a..1033ee8c0caf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+ atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+ atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+ return atomic64_read(&map->writecnt) != 0;
+}
+
static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt++;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_inc(map);
}
/* called for all unmapped memory region (including initial) */
@@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt--;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_dec(map);
}
static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
goto out;
if (vma->vm_flags & VM_MAYWRITE)
- map->writecnt++;
+ bpf_map_write_active_inc(map);
out:
mutex_unlock(&map->freeze_mutex);
return err;
@@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1174,6 +1184,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr)
out:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
@@ -1597,6 +1611,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr)
}
mutex_lock(&map->freeze_mutex);
-
- if (map->writecnt) {
+ if (bpf_map_write_active(map)) {
err = -EBUSY;
goto err_put;
}
@@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
union bpf_attr __user *uattr,
int cmd)
{
+ bool has_read = cmd == BPF_MAP_LOOKUP_BATCH ||
+ cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+ bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
struct bpf_map *map;
int err, ufd;
struct fd f;
@@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if ((cmd == BPF_MAP_LOOKUP_BATCH ||
- cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+ if (has_write)
+ bpf_map_write_active_inc(map);
+ if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
-
- if (cmd != BPF_MAP_LOOKUP_BATCH &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+ if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
BPF_DO_BATCH(map->ops->map_update_batch);
else
BPF_DO_BATCH(map->ops->map_delete_batch);
-
err_put:
+ if (has_write)
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0763cca139a7..88fe97d35166 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
/* transfer reg's id which is unique for every map_lookup_elem
* as UID of the inner map.
*/
- reg->map_uid = reg->id;
+ if (map_value_has_timer(map->inner_map_meta))
+ reg->map_uid = reg->id;
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
reg->type = PTR_TO_XDP_SOCK;
} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -4055,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
- return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+ /* A map is considered read-only if the following condition are true:
+ *
+ * 1) BPF program side cannot change any of the map content. The
+ * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+ * and was set at map creation time.
+ * 2) The map value(s) have been initialized from user space by a
+ * loader and then "frozen", such that no new map update/delete
+ * operations from syscall side are possible for the rest of
+ * the map's lifetime from that point onwards.
+ * 3) Any parallel/pending map update/delete operations from syscall
+ * side have been completed. Only after that point, it's safe to
+ * assume that map value(s) are immutable.
+ */
+ return (map->map_flags & BPF_F_RDONLY_PROG) &&
+ READ_ONCE(map->frozen) &&
+ !bpf_map_write_active(map);
}
static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -11665,6 +11681,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
}
+ if (map_value_has_timer(map)) {
+ if (is_tracing_prog_type(prog_type)) {
+ verbose(env, "tracing progs cannot use bpf_timer yet\n");
+ return -EINVAL;
+ }
+ }
+
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f2253ea729a2..523106a506ee 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7154,7 +7154,6 @@ void perf_output_sample(struct perf_output_handle *handle,
static u64 perf_virt_to_phys(u64 virt)
{
u64 phys_addr = 0;
- struct page *p = NULL;
if (!virt)
return 0;
@@ -7173,14 +7172,15 @@ static u64 perf_virt_to_phys(u64 virt)
* If failed, leave phys_addr as 0.
*/
if (current->mm != NULL) {
+ struct page *p;
+
pagefault_disable();
- if (get_user_page_fast_only(virt, 0, &p))
+ if (get_user_page_fast_only(virt, 0, &p)) {
phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+ put_page(p);
+ }
pagefault_enable();
}
-
- if (p)
- put_page(p);
}
return phys_addr;
diff --git a/kernel/fork.c b/kernel/fork.c
index 5de23f3e08bf..3244cc56b697 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2277,6 +2277,7 @@ static __latent_entropy struct task_struct *copy_process(
p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ clear_posix_cputimers_work(p);
#ifdef CONFIG_KRETPROBES
p->kretprobe_instances.first = NULL;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 6a5ecee6e567..7f350ae59c5f 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -529,10 +529,10 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
/*
* Checking the first MSI descriptor is sufficient. MSIX supports
- * masking and MSI does so when the maskbit is set.
+ * masking and MSI does so when the can_mask attribute is set.
*/
desc = first_msi_entry(dev);
- return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
+ return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask;
}
int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 013bfd6dcc34..57b132b658e1 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3253,6 +3253,11 @@ void defer_console_output(void)
preempt_enable();
}
+void printk_trigger_flush(void)
+{
+ defer_console_output();
+}
+
int vprintk_deferred(const char *fmt, va_list args)
{
int r;
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 2067080bb235..8629b37d118e 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -31,7 +31,7 @@ static inline void autogroup_destroy(struct kref *kref)
ag->tg->rt_se = NULL;
ag->tg->rt_rq = NULL;
#endif
- sched_offline_group(ag->tg);
+ sched_release_group(ag->tg);
sched_destroy_group(ag->tg);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 523fd602ea90..3c9b0fda64ac 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3726,6 +3726,9 @@ out:
bool cpus_share_cache(int this_cpu, int that_cpu)
{
+ if (this_cpu == that_cpu)
+ return true;
+
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
@@ -6625,13 +6628,13 @@ __setup("preempt=", setup_preempt_mode);
static void __init preempt_dynamic_init(void)
{
if (preempt_dynamic_mode == preempt_dynamic_undefined) {
- if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) {
+ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
sched_dynamic_update(preempt_dynamic_none);
- } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) {
+ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
sched_dynamic_update(preempt_dynamic_voluntary);
} else {
/* Default static call setting, nothing to do */
- WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR));
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
preempt_dynamic_mode = preempt_dynamic_full;
pr_info("Dynamic Preempt: full\n");
}
@@ -9716,6 +9719,22 @@ static void sched_free_group(struct task_group *tg)
kmem_cache_free(task_group_cache, tg);
}
+static void sched_free_group_rcu(struct rcu_head *rcu)
+{
+ sched_free_group(container_of(rcu, struct task_group, rcu));
+}
+
+static void sched_unregister_group(struct task_group *tg)
+{
+ unregister_fair_sched_group(tg);
+ unregister_rt_sched_group(tg);
+ /*
+ * We have to wait for yet another RCU grace period to expire, as
+ * print_cfs_stats() might run concurrently.
+ */
+ call_rcu(&tg->rcu, sched_free_group_rcu);
+}
+
/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(struct task_group *parent)
{
@@ -9759,25 +9778,35 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
}
/* rcu callback to free various structures associated with a task group */
-static void sched_free_group_rcu(struct rcu_head *rhp)
+static void sched_unregister_group_rcu(struct rcu_head *rhp)
{
/* Now it should be safe to free those cfs_rqs: */
- sched_free_group(container_of(rhp, struct task_group, rcu));
+ sched_unregister_group(container_of(rhp, struct task_group, rcu));
}
void sched_destroy_group(struct task_group *tg)
{
/* Wait for possible concurrent references to cfs_rqs complete: */
- call_rcu(&tg->rcu, sched_free_group_rcu);
+ call_rcu(&tg->rcu, sched_unregister_group_rcu);
}
-void sched_offline_group(struct task_group *tg)
+void sched_release_group(struct task_group *tg)
{
unsigned long flags;
- /* End participation in shares distribution: */
- unregister_fair_sched_group(tg);
-
+ /*
+ * Unlink first, to avoid walk_tg_tree_from() from finding us (via
+ * sched_cfs_period_timer()).
+ *
+ * For this to be effective, we have to wait for all pending users of
+ * this task group to leave their RCU critical section to ensure no new
+ * user will see our dying task group any more. Specifically ensure
+ * that tg_unthrottle_up() won't add decayed cfs_rq's to it.
+ *
+ * We therefore defer calling unregister_fair_sched_group() to
+ * sched_unregister_group() which is guarantied to get called only after the
+ * current RCU grace period has expired.
+ */
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
list_del_rcu(&tg->siblings);
@@ -9896,7 +9925,7 @@ static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
- sched_offline_group(tg);
+ sched_release_group(tg);
}
static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
@@ -9906,7 +9935,7 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
/*
* Relies on the RCU grace period between css_released() and this.
*/
- sched_free_group(tg);
+ sched_unregister_group(tg);
}
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 13950beb01a2..6e476f6d9435 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11456,8 +11456,6 @@ void free_fair_sched_group(struct task_group *tg)
{
int i;
- destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
-
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
@@ -11534,6 +11532,8 @@ void unregister_fair_sched_group(struct task_group *tg)
struct rq *rq;
int cpu;
+ destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
for_each_possible_cpu(cpu) {
if (tg->se[cpu])
remove_entity_load_avg(tg->se[cpu]);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bb945f8faeca..b48baaba2fc2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -137,13 +137,17 @@ static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
return rt_rq->rq;
}
-void free_rt_sched_group(struct task_group *tg)
+void unregister_rt_sched_group(struct task_group *tg)
{
- int i;
-
if (tg->rt_se)
destroy_rt_bandwidth(&tg->rt_bandwidth);
+}
+
+void free_rt_sched_group(struct task_group *tg)
+{
+ int i;
+
for_each_possible_cpu(i) {
if (tg->rt_rq)
kfree(tg->rt_rq[i]);
@@ -250,6 +254,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
return &rq->rt;
}
+void unregister_rt_sched_group(struct task_group *tg) { }
+
void free_rt_sched_group(struct task_group *tg) { }
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7f1612d26c18..0e66749486e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -488,6 +488,7 @@ extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
+extern void unregister_rt_sched_group(struct task_group *tg);
extern void free_rt_sched_group(struct task_group *tg);
extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
@@ -503,7 +504,7 @@ extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_online_group(struct task_group *tg,
struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
-extern void sched_offline_group(struct task_group *tg);
+extern void sched_release_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 643d412ac623..96b4e7810426 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1159,13 +1159,28 @@ static void posix_cpu_timers_work(struct callback_head *work)
}
/*
+ * Clear existing posix CPU timers task work.
+ */
+void clear_posix_cputimers_work(struct task_struct *p)
+{
+ /*
+ * A copied work entry from the old task is not meaningful, clear it.
+ * N.B. init_task_work will not do this.
+ */
+ memset(&p->posix_cputimers_work.work, 0,
+ sizeof(p->posix_cputimers_work.work));
+ init_task_work(&p->posix_cputimers_work.work,
+ posix_cpu_timers_work);
+ p->posix_cputimers_work.scheduled = false;
+}
+
+/*
* Initialize posix CPU timers task work in init task. Out of line to
* keep the callback static and to avoid header recursion hell.
*/
void __init posix_cputimers_init_work(void)
{
- init_task_work(&current->posix_cputimers_work.work,
- posix_cpu_timers_work);
+ clear_posix_cputimers_work(current);
}
/*
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 25ea521fb8f1..1cd647c010da 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_ktime_get_boot_ns:
return &bpf_ktime_get_boot_ns_proto;
- case BPF_FUNC_ktime_get_coarse_ns:
- return &bpf_ktime_get_coarse_ns_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_get_current_pid_tgid:
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0abc9a413b4d..5ea2c9ec54a6 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1953,9 +1953,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (!hist_field->type)
goto free;
- if (field->filter_type == FILTER_STATIC_STRING)
+ if (field->filter_type == FILTER_STATIC_STRING) {
hist_field->fn = hist_field_string;
- else if (field->filter_type == FILTER_DYN_STRING)
+ hist_field->size = field->size;
+ } else if (field->filter_type == FILTER_DYN_STRING)
hist_field->fn = hist_field_dynstring;
else
hist_field->fn = hist_field_pstring;
@@ -2580,7 +2581,8 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
operand1_str = str;
str = sep+1;
- if (!operand1_str || !str)
+ /* Binary operator requires both operands */
+ if (*operand1_str == '\0' || *str == '\0')
goto free;
operand_flags = 0;
@@ -3024,8 +3026,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
if (val->flags & HIST_FIELD_FL_STRING) {
char *str = elt_data->field_var_str[j++];
char *val_str = (char *)(uintptr_t)var_val;
+ unsigned int size;
- strscpy(str, val_str, STR_VAR_LEN_MAX);
+ size = min(val->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
var_val = (u64)(uintptr_t)str;
}
tracing_map_set_var(elt, var_idx, var_val);
@@ -4912,6 +4916,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
if (hist_field->flags & HIST_FIELD_FL_STRING) {
unsigned int str_start, var_str_idx, idx;
char *str, *val_str;
+ unsigned int size;
str_start = hist_data->n_field_var_str +
hist_data->n_save_var_str;
@@ -4920,7 +4925,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
str = elt_data->field_var_str[idx];
val_str = (char *)(uintptr_t)hist_val;
- strscpy(str, val_str, STR_VAR_LEN_MAX);
+
+ size = min(hist_field->size, STR_VAR_LEN_MAX);
+ strscpy(str, val_str, size);
hist_val = (u64)(uintptr_t)str;
}
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 3e4a1651e329..7520d43aed55 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -55,7 +55,8 @@ struct osnoise_instance {
struct list_head list;
struct trace_array *tr;
};
-struct list_head osnoise_instances;
+
+static struct list_head osnoise_instances;
static bool osnoise_has_registered_instances(void)
{