summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c16
-rw-r--r--kernel/bpf/hashtab.c2
-rw-r--r--kernel/bpf/preload/bpf_preload_kern.c1
-rw-r--r--kernel/bpf/syscall.c6
-rw-r--r--kernel/cgroup/cgroup.c31
-rw-r--r--kernel/dma/coherent.c12
-rw-r--r--kernel/dma/contiguous.c3
-rw-r--r--kernel/dma/mapping.c25
-rw-r--r--kernel/events/core.c4
-rw-r--r--kernel/irq/msi.c2
-rw-r--r--kernel/params.c51
-rw-r--r--kernel/sched/cpufreq_schedutil.c49
-rw-r--r--kernel/sched/ext.c50
-rw-r--r--kernel/sched/fair.c4
-rw-r--r--kernel/time/timekeeping.c50
-rw-r--r--kernel/time/vsyscall.c4
-rw-r--r--kernel/trace/ftrace.c29
-rw-r--r--kernel/trace/trace.c9
-rw-r--r--kernel/trace/trace_entries.h4
-rw-r--r--kernel/trace/trace_events_filter.c4
-rw-r--r--kernel/trace/trace_output.c4
-rw-r--r--kernel/vhost_task.c2
22 files changed, 227 insertions, 135 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 367eaf2c78b7..0ebbbe37a60f 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -347,12 +347,17 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
/* Get path information necessary for adding watches. */
static int audit_get_nd(struct audit_watch *watch, struct path *parent)
{
- struct dentry *d = kern_path_locked(watch->path, parent);
+ struct dentry *d;
+
+ d = kern_path_locked_negative(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
- /* update watch filter fields */
- watch->dev = d->d_sb->s_dev;
- watch->ino = d_backing_inode(d)->i_ino;
+
+ if (d_is_positive(d)) {
+ /* update watch filter fields */
+ watch->dev = d->d_sb->s_dev;
+ watch->ino = d_backing_inode(d)->i_ino;
+ }
inode_unlock(d_backing_inode(parent->dentry));
dput(d);
@@ -418,11 +423,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- if (ret && ret != -ENOENT) {
+ if (ret) {
audit_put_watch(watch);
return ret;
}
- ret = 0;
/* either find an old parent or attach a new one */
parent = audit_find_parent(d_backing_inode(parent_path.dentry));
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5a5adc66b8e2..92b606d60020 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2189,7 +2189,7 @@ static long bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_
b = &htab->buckets[i];
rcu_read_lock();
head = &b->head;
- hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+ hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
key = elem->key;
if (is_percpu) {
/* current cpu value for percpu map */
diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c
index 2fdf3c978db1..774e5a538811 100644
--- a/kernel/bpf/preload/bpf_preload_kern.c
+++ b/kernel/bpf/preload/bpf_preload_kern.c
@@ -89,5 +89,6 @@ static void __exit fini(void)
}
late_initcall(load);
module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9794446bc8c6..64c3393e8270 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1583,7 +1583,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
return map;
}
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
@@ -3364,7 +3364,7 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
bpf_link_inc(link);
return link;
}
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
static void bpf_tracing_link_release(struct bpf_link *link)
{
@@ -6020,7 +6020,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
return ____bpf_sys_bpf(cmd, attr, size);
}
}
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
static const struct bpf_func_proto bpf_sys_bpf_proto = {
.func = bpf_sys_bpf,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3caf2cd86e65..63e5b90da1f3 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -90,7 +90,7 @@
DEFINE_MUTEX(cgroup_mutex);
DEFINE_SPINLOCK(css_set_lock);
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
EXPORT_SYMBOL_GPL(cgroup_mutex);
EXPORT_SYMBOL_GPL(css_set_lock);
#endif
@@ -2353,9 +2353,37 @@ static struct file_system_type cgroup2_fs_type = {
};
#ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+ Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+ fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+ {}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_cpuset_v2_mode:
+ ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+ return 0;
+ }
+ return -EINVAL;
+}
+
static const struct fs_context_operations cpuset_fs_context_ops = {
.get_tree = cgroup1_get_tree,
.free = cgroup_fs_context_free,
+ .parse_param = cpuset_parse_param,
};
/*
@@ -2392,6 +2420,7 @@ static int cpuset_init_fs_context(struct fs_context *fc)
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
.init_fs_context = cpuset_init_fs_context,
+ .parameters = cpuset_fs_parameters,
.fs_flags = FS_USERNS_MOUNT,
};
#endif
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 3b2bdca9f1d4..77c8d9487a9a 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -336,16 +336,22 @@ static phys_addr_t dma_reserved_default_memory_size __initdata;
static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
{
- if (!rmem->priv) {
- struct dma_coherent_mem *mem;
+ struct dma_coherent_mem *mem = rmem->priv;
+ if (!mem) {
mem = dma_init_coherent_memory(rmem->base, rmem->base,
rmem->size, true);
if (IS_ERR(mem))
return PTR_ERR(mem);
rmem->priv = mem;
}
- dma_assign_coherent_memory(dev, rmem->priv);
+
+ /* Warn if the device potentially can't use the reserved memory */
+ if (mem->device_base + rmem->size - 1 >
+ min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+ dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+ dma_assign_coherent_memory(dev, mem);
return 0;
}
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 055da410ac71..8df0dfaaca18 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -64,8 +64,7 @@ struct cma *dma_contiguous_default_area;
* Users, who want to set the size of global CMA area for their system
* should use cma= kernel parameter.
*/
-static const phys_addr_t size_bytes __initconst =
- (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
static phys_addr_t size_cmdline __initdata = -1;
static phys_addr_t base_cmdline __initdata;
static phys_addr_t limit_cmdline __initdata;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index cda127027e48..051a32988040 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -910,6 +910,19 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
}
EXPORT_SYMBOL(dma_set_coherent_mask);
+static bool __dma_addressing_limited(struct device *dev)
+{
+ const struct dma_map_ops *ops = get_dma_ops(dev);
+
+ if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
+ dma_get_required_mask(dev))
+ return true;
+
+ if (unlikely(ops) || use_dma_iommu(dev))
+ return false;
+ return !dma_direct_all_ram_mapped(dev);
+}
+
/**
* dma_addressing_limited - return if the device is addressing limited
* @dev: device to check
@@ -920,15 +933,11 @@ EXPORT_SYMBOL(dma_set_coherent_mask);
*/
bool dma_addressing_limited(struct device *dev)
{
- const struct dma_map_ops *ops = get_dma_ops(dev);
-
- if (min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
- dma_get_required_mask(dev))
- return true;
-
- if (unlikely(ops) || use_dma_iommu(dev))
+ if (!__dma_addressing_limited(dev))
return false;
- return !dma_direct_all_ram_mapped(dev);
+
+ dev_dbg(dev, "device is DMA addressing limited\n");
+ return true;
}
EXPORT_SYMBOL_GPL(dma_addressing_limited);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e93c19565914..95e703891b24 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3943,7 +3943,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
if (*perf_event_fasync(event))
- event->pending_kill = POLL_HUP;
+ event->pending_kill = POLL_ERR;
perf_event_wakeup(event);
} else {
@@ -6075,7 +6075,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
event->attr.pinned))
- return events;
+ return EPOLLERR;
/*
* Pin the event->rb by taking event->mmap_mutex; otherwise
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 5c8d43cdb0a3..c05ba7ca00fa 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -761,7 +761,7 @@ static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fw
static void msi_domain_debug_show(struct seq_file *m, struct irq_domain *d,
struct irq_data *irqd, int ind)
{
- struct msi_desc *desc = irq_data_get_msi_desc(irqd);
+ struct msi_desc *desc = irqd ? irq_data_get_msi_desc(irqd) : NULL;
if (!desc)
return;
diff --git a/kernel/params.c b/kernel/params.c
index 2509f216c9f3..b92d64161b75 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -760,38 +760,35 @@ void destroy_params(const struct kernel_param *params, unsigned num)
params[i].ops->free(params[i].arg);
}
-static struct module_kobject * __init locate_module_kobject(const char *name)
+struct module_kobject __modinit * lookup_or_create_module_kobject(const char *name)
{
struct module_kobject *mk;
struct kobject *kobj;
int err;
kobj = kset_find_obj(module_kset, name);
- if (kobj) {
- mk = to_module_kobject(kobj);
- } else {
- mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
- BUG_ON(!mk);
-
- mk->mod = THIS_MODULE;
- mk->kobj.kset = module_kset;
- err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
- "%s", name);
-#ifdef CONFIG_MODULES
- if (!err)
- err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
-#endif
- if (err) {
- kobject_put(&mk->kobj);
- pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
- name, err);
- return NULL;
- }
+ if (kobj)
+ return to_module_kobject(kobj);
- /* So that we hold reference in both cases. */
- kobject_get(&mk->kobj);
+ mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+ if (!mk)
+ return NULL;
+
+ mk->mod = THIS_MODULE;
+ mk->kobj.kset = module_kset;
+ err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
+ if (IS_ENABLED(CONFIG_MODULES) && !err)
+ err = sysfs_create_file(&mk->kobj, &module_uevent.attr);
+ if (err) {
+ kobject_put(&mk->kobj);
+ pr_crit("Adding module '%s' to sysfs failed (%d), the system may be unstable.\n",
+ name, err);
+ return NULL;
}
+ /* So that we hold reference in both cases. */
+ kobject_get(&mk->kobj);
+
return mk;
}
@@ -802,7 +799,7 @@ static void __init kernel_add_sysfs_param(const char *name,
struct module_kobject *mk;
int err;
- mk = locate_module_kobject(name);
+ mk = lookup_or_create_module_kobject(name);
if (!mk)
return;
@@ -873,7 +870,7 @@ static void __init version_sysfs_builtin(void)
int err;
for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
- mk = locate_module_kobject(vattr->module_name);
+ mk = lookup_or_create_module_kobject(vattr->module_name);
if (mk) {
err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
WARN_ON_ONCE(err);
@@ -946,7 +943,9 @@ struct kset *module_kset;
static void module_kobj_release(struct kobject *kobj)
{
struct module_kobject *mk = to_module_kobject(kobj);
- complete(mk->kobj_completion);
+
+ if (mk->kobj_completion)
+ complete(mk->kobj_completion);
}
const struct kobj_type module_ktype = {
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1a19d69b91ed..816f07f9d30f 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -81,9 +81,23 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
if (!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (unlikely(sg_policy->limits_changed)) {
- sg_policy->limits_changed = false;
- sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+ if (unlikely(READ_ONCE(sg_policy->limits_changed))) {
+ WRITE_ONCE(sg_policy->limits_changed, false);
+ sg_policy->need_freq_update = true;
+
+ /*
+ * The above limits_changed update must occur before the reads
+ * of policy limits in cpufreq_driver_resolve_freq() or a policy
+ * limits update might be missed, so use a memory barrier to
+ * ensure it.
+ *
+ * This pairs with the write memory barrier in sugov_limits().
+ */
+ smp_mb();
+
+ return true;
+ } else if (sg_policy->need_freq_update) {
+ /* ignore_dl_rate_limit() wants a new frequency to be found. */
return true;
}
@@ -95,10 +109,22 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
unsigned int next_freq)
{
- if (sg_policy->need_freq_update)
+ if (sg_policy->need_freq_update) {
sg_policy->need_freq_update = false;
- else if (sg_policy->next_freq == next_freq)
+ /*
+ * The policy limits have changed, but if the return value of
+ * cpufreq_driver_resolve_freq() after applying the new limits
+ * is still equal to the previously selected frequency, the
+ * driver callback need not be invoked unless the driver
+ * specifically wants that to happen on every update of the
+ * policy limits.
+ */
+ if (sg_policy->next_freq == next_freq &&
+ !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+ return false;
+ } else if (sg_policy->next_freq == next_freq) {
return false;
+ }
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
@@ -365,7 +391,7 @@ static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
{
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
- sg_cpu->sg_policy->limits_changed = true;
+ sg_cpu->sg_policy->need_freq_update = true;
}
static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
@@ -871,7 +897,16 @@ static void sugov_limits(struct cpufreq_policy *policy)
mutex_unlock(&sg_policy->work_lock);
}
- sg_policy->limits_changed = true;
+ /*
+ * The limits_changed update below must take place before the updates
+ * of policy limits in cpufreq_set_policy() or a policy limits update
+ * might be missed, so use a memory barrier to ensure it.
+ *
+ * This pairs with the memory barrier in sugov_should_update_freq().
+ */
+ smp_wmb();
+
+ WRITE_ONCE(sg_policy->limits_changed, true);
}
struct cpufreq_governor schedutil_gov = {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 66bcd40a28ca..fdbf249d1c68 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -163,7 +163,7 @@ enum scx_ops_flags {
/*
* CPU cgroup support flags
*/
- SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */
+ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */
SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
SCX_OPS_ENQ_LAST |
@@ -3899,35 +3899,6 @@ bool scx_can_stop_tick(struct rq *rq)
DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
- if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
- cgroup_warned_missing_weight)
- return;
-
- if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
- scx_ops.name);
- cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
- if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
- return;
-
- if (!tg->idle)
- return;
-
- pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
- scx_ops.name);
- cgroup_warned_missing_idle = true;
-}
int scx_tg_online(struct task_group *tg)
{
@@ -3937,8 +3908,6 @@ int scx_tg_online(struct task_group *tg)
percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_weight(tg);
-
if (scx_cgroup_enabled) {
if (SCX_HAS_OP(cgroup_init)) {
struct scx_cgroup_init_args args =
@@ -4076,9 +4045,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
void scx_group_set_idle(struct task_group *tg, bool idle)
{
- percpu_down_read(&scx_cgroup_rwsem);
- scx_cgroup_warn_missing_idle(tg);
- percpu_up_read(&scx_cgroup_rwsem);
+ /* TODO: Implement ops->cgroup_set_idle() */
}
static void scx_cgroup_lock(void)
@@ -4272,9 +4239,6 @@ static int scx_cgroup_init(void)
percpu_rwsem_assert_held(&scx_cgroup_rwsem);
- cgroup_warned_missing_weight = false;
- cgroup_warned_missing_idle = false;
-
/*
* scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
* cgroups and init, all online cgroups are initialized.
@@ -4284,9 +4248,6 @@ static int scx_cgroup_init(void)
struct task_group *tg = css_tg(css);
struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
- scx_cgroup_warn_missing_weight(tg);
- scx_cgroup_warn_missing_idle(tg);
-
if ((tg->scx_flags &
(SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
continue;
@@ -4623,7 +4584,7 @@ unlock:
static void free_exit_info(struct scx_exit_info *ei)
{
- kfree(ei->dump);
+ kvfree(ei->dump);
kfree(ei->msg);
kfree(ei->bt);
kfree(ei);
@@ -4639,7 +4600,7 @@ static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
- ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+ ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
if (!ei->bt || !ei->msg || !ei->dump) {
free_exit_info(ei);
@@ -5252,6 +5213,9 @@ static int validate_ops(const struct sched_ext_ops *ops)
return -EINVAL;
}
+ if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+ pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
+
return 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e43993a4e580..0fb9bf995a47 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7081,9 +7081,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
h_nr_idle = task_has_idle_policy(p);
if (task_sleep || task_delayed || !se->sched_delayed)
h_nr_runnable = 1;
- } else {
- cfs_rq = group_cfs_rq(se);
- slice = cfs_rq_min_slice(cfs_rq);
}
for_each_sched_entity(se) {
@@ -7093,6 +7090,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
if (p && &p->se == se)
return -1;
+ slice = cfs_rq_min_slice(cfs_rq);
break;
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1e67d076f195..a009c91f7b05 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
return ts;
}
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+ struct timespec64 ts;
+
+ ts.tv_sec = tk->xtime_sec;
+ ts.tv_nsec = tk->coarse_nsec;
+ return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+ tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+ tk_update_coarse_nsecs(tk);
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
@@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
tk->xtime_sec += ts->tv_sec;
tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
tk_normalize_xtime(tk);
+ tk_update_coarse_nsecs(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
tk_normalize_xtime(tk);
delta -= incr;
}
+ tk_update_coarse_nsecs(tk);
}
/**
@@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
{
struct timekeeper *tk = &tk_core.timekeeper;
- unsigned int seq;
ktime_t base, *offset = offsets[offs];
+ unsigned int seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
@@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
do {
seq = read_seqcount_begin(&tk_core.seq);
base = ktime_add(tk->tkr_mono.base, *offset);
- nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsecs = tk->coarse_nsec;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
struct timekeeper *real_tk = &tk_core.timekeeper;
unsigned int clock_set = 0;
int shift = 0, maxshift;
- u64 offset;
+ u64 offset, orig_offset;
guard(raw_spinlock_irqsave)(&tk_core.lock);
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
tk->tkr_mono.clock->max_raw_delta);
-
+ orig_offset = offset;
/* Check if there's really nothing to do */
if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
*/
clock_set |= accumulate_nsecs_to_secs(tk);
+ /*
+ * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+ * making small negative adjustments to the base xtime_nsec
+ * value, only update the coarse clocks if we accumulated time
+ */
+ if (orig_offset != offset)
+ tk_update_coarse_nsecs(tk);
+
timekeeping_update_from_shadow(&tk_core, clock_set);
return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
} while (read_seqcount_retry(&tk_core.seq, seq));
}
EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- *ts = tk_xtime(tk);
+ *ts = tk_xtime_coarse(tk);
offset = tk_core.timekeeper.offs_real;
} while (read_seqcount_retry(&tk_core.seq, seq));
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tk_xtime(tk);
+ now = tk_xtime_coarse(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&tk_core.seq, seq));
set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
- now.tv_nsec + mono.tv_nsec);
+ now.tv_nsec + mono.tv_nsec);
}
EXPORT_SYMBOL(ktime_get_coarse_ts64);
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 01c2ab1e8971..32ef27c71b57 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
/* CLOCK_REALTIME_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
vdso_ts->sec = tk->xtime_sec;
- vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ vdso_ts->nsec = tk->coarse_nsec;
/* CLOCK_MONOTONIC_COARSE */
vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+ nsec = tk->coarse_nsec;
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a8a02868b435..6981830c3128 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1297,6 +1297,8 @@ void ftrace_free_filter(struct ftrace_ops *ops)
return;
free_ftrace_hash(ops->func_hash->filter_hash);
free_ftrace_hash(ops->func_hash->notrace_hash);
+ ops->func_hash->filter_hash = EMPTY_HASH;
+ ops->func_hash->notrace_hash = EMPTY_HASH;
}
EXPORT_SYMBOL_GPL(ftrace_free_filter);
@@ -3434,7 +3436,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
/* Copy the subops hash */
*filter_hash = alloc_and_copy_ftrace_hash(size_bits, subops_hash->filter_hash);
- if (!filter_hash)
+ if (!*filter_hash)
return -ENOMEM;
/* Remove any notrace functions from the copy */
remove_hash(*filter_hash, subops_hash->notrace_hash);
@@ -3443,6 +3445,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
size_bits);
if (ret < 0) {
free_ftrace_hash(*filter_hash);
+ *filter_hash = EMPTY_HASH;
return ret;
}
}
@@ -3472,6 +3475,7 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
subops_hash->notrace_hash);
if (ret < 0) {
free_ftrace_hash(*notrace_hash);
+ *notrace_hash = EMPTY_HASH;
return ret;
}
}
@@ -3490,8 +3494,8 @@ static int add_next_hash(struct ftrace_hash **filter_hash, struct ftrace_hash **
*/
int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
{
- struct ftrace_hash *filter_hash;
- struct ftrace_hash *notrace_hash;
+ struct ftrace_hash *filter_hash = EMPTY_HASH;
+ struct ftrace_hash *notrace_hash = EMPTY_HASH;
struct ftrace_hash *save_filter_hash;
struct ftrace_hash *save_notrace_hash;
int ret;
@@ -3605,6 +3609,9 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash *
}
}
+ free_ftrace_hash(temp_hash.filter_hash);
+ free_ftrace_hash(temp_hash.notrace_hash);
+
temp_hash.filter_hash = *filter_hash;
temp_hash.notrace_hash = *notrace_hash;
}
@@ -3625,8 +3632,8 @@ static int rebuild_hashes(struct ftrace_hash **filter_hash, struct ftrace_hash *
*/
int ftrace_shutdown_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int command)
{
- struct ftrace_hash *filter_hash;
- struct ftrace_hash *notrace_hash;
+ struct ftrace_hash *filter_hash = EMPTY_HASH;
+ struct ftrace_hash *notrace_hash = EMPTY_HASH;
int ret;
if (unlikely(ftrace_disabled))
@@ -3699,8 +3706,11 @@ static int ftrace_hash_move_and_update_subops(struct ftrace_ops *subops,
}
ret = rebuild_hashes(&filter_hash, &notrace_hash, ops);
- if (!ret)
+ if (!ret) {
ret = ftrace_update_ops(ops, filter_hash, notrace_hash);
+ free_ftrace_hash(filter_hash);
+ free_ftrace_hash(notrace_hash);
+ }
if (ret) {
/* Put back the original hash */
@@ -5954,9 +5964,10 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
/* Make a copy hash to place the new and the old entries in */
size = hash->count + direct_functions->count;
- if (size > 32)
- size = 32;
- new_hash = alloc_ftrace_hash(fls(size));
+ size = fls(size);
+ if (size > FTRACE_HASH_MAX_BITS)
+ size = FTRACE_HASH_MAX_BITS;
+ new_hash = alloc_ftrace_hash(size);
if (!new_hash)
goto out_unlock;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8ddf6b17215c..5b8db27fb6ef 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6043,8 +6043,10 @@ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr)
tscratch = tr->scratch;
/* if there is no tscrach, module_delta must be NULL. */
module_delta = READ_ONCE(tr->module_delta);
- if (!module_delta || tscratch->entries[0].mod_addr > addr)
+ if (!module_delta || !tscratch->nr_entries ||
+ tscratch->entries[0].mod_addr > addr) {
return addr + tr->text_delta;
+ }
/* Note that entries must be sorted. */
nr_entries = tscratch->nr_entries;
@@ -6821,13 +6823,14 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
/* Copy the data into the page, so we can start over. */
ret = trace_seq_to_buffer(&iter->seq,
page_address(spd.pages[i]),
- trace_seq_used(&iter->seq));
+ min((size_t)trace_seq_used(&iter->seq),
+ PAGE_SIZE));
if (ret < 0) {
__free_page(spd.pages[i]);
break;
}
spd.partial[i].offset = 0;
- spd.partial[i].len = trace_seq_used(&iter->seq);
+ spd.partial[i].len = ret;
trace_seq_init(&iter->seq);
}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ee40d4e6ad1c..4ef4df6623a8 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -80,11 +80,11 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
F_STRUCT(
__field_struct( struct ftrace_graph_ent, graph_ent )
__field_packed( unsigned long, graph_ent, func )
- __field_packed( unsigned long, graph_ent, depth )
+ __field_packed( unsigned int, graph_ent, depth )
__dynamic_array(unsigned long, args )
),
- F_printk("--> %ps (%lu)", (void *)__entry->func, __entry->depth)
+ F_printk("--> %ps (%u)", (void *)__entry->func, __entry->depth)
);
#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0993dfc1c5c1..2048560264bb 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -808,7 +808,7 @@ static __always_inline char *test_string(char *str)
kstr = ubuf->buffer;
/* For safety, do not trust the string pointer */
- if (!strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE))
+ if (strncpy_from_kernel_nofault(kstr, str, USTRING_BUF_SIZE) < 0)
return NULL;
return kstr;
}
@@ -827,7 +827,7 @@ static __always_inline char *test_ustring(char *str)
/* user space address? */
ustr = (char __user *)str;
- if (!strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE))
+ if (strncpy_from_user_nofault(kstr, ustr, USTRING_BUF_SIZE) < 0)
return NULL;
return kstr;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index fee40ffbd490..b9ab06c99543 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1042,11 +1042,12 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
struct trace_event_call *call;
struct list_head *head;
+ lockdep_assert_held_read(&trace_event_sem);
+
/* ftrace defined events have separate call structures */
if (event->type <= __TRACE_LAST_TYPE) {
bool found = false;
- down_read(&trace_event_sem);
list_for_each_entry(call, &ftrace_events, list) {
if (call->event.type == event->type) {
found = true;
@@ -1056,7 +1057,6 @@ enum print_line_t print_event_fields(struct trace_iterator *iter,
if (call->event.type > __TRACE_LAST_TYPE)
break;
}
- up_read(&trace_event_sem);
if (!found) {
trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type);
goto out;
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 2ef2e1b80091..2f844c279a3e 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(vhost_task_stop);
* @arg: data to be passed to fn and handled_kill
* @name: the thread's name
*
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
* failure. The returned task is inactive, and the caller must fire it up
* through vhost_task_start().
*/
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-11 13:03:54 +0000