summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c2
-rw-r--r--kernel/bpf/cgroup.c4
-rw-r--r--kernel/bpf/core.c2
-rw-r--r--kernel/bpf/devmap.c33
-rw-r--r--kernel/bpf/syscall.c38
-rw-r--r--kernel/cgroup/cgroup.c5
-rw-r--r--kernel/cgroup/cpuset.c3
-rw-r--r--kernel/cpu.c27
-rw-r--r--kernel/events/core.c74
-rw-r--r--kernel/events/uprobes.c13
-rw-r--r--kernel/fork.c37
-rw-r--r--kernel/freezer.c6
-rwxr-xr-xkernel/gen_kheaders.sh11
-rw-r--r--kernel/irq/irqdomain.c2
-rw-r--r--kernel/kthread.c6
-rw-r--r--kernel/panic.c1
-rw-r--r--kernel/power/main.c1
-rw-r--r--kernel/power/qos.c240
-rw-r--r--kernel/sched/core.c28
-rw-r--r--kernel/sched/cputime.c6
-rw-r--r--kernel/sched/deadline.c40
-rw-r--r--kernel/sched/fair.c80
-rw-r--r--kernel/sched/idle.c9
-rw-r--r--kernel/sched/rt.c37
-rw-r--r--kernel/sched/sched.h30
-rw-r--r--kernel/sched/stop_task.c18
-rw-r--r--kernel/sched/topology.c11
-rw-r--r--kernel/signal.c2
-rw-r--r--kernel/stacktrace.c6
-rw-r--r--kernel/stop_machine.c10
-rw-r--r--kernel/sysctl.c4
-rw-r--r--kernel/time/hrtimer.c8
-rw-r--r--kernel/time/ntp.c2
-rw-r--r--kernel/time/posix-cpu-timers.c6
-rw-r--r--kernel/time/sched_clock.c2
-rw-r--r--kernel/time/vsyscall.c9
-rw-r--r--kernel/trace/ftrace.c55
-rw-r--r--kernel/trace/trace.c139
-rw-r--r--kernel/trace/trace.h2
-rw-r--r--kernel/trace/trace_dynevent.c4
-rw-r--r--kernel/trace/trace_event_perf.c4
-rw-r--r--kernel/trace/trace_events.c35
-rw-r--r--kernel/trace/trace_events_hist.c15
-rw-r--r--kernel/trace/trace_events_trigger.c8
-rw-r--r--kernel/trace/trace_hwlat.c4
-rw-r--r--kernel/trace/trace_kprobe.c12
-rw-r--r--kernel/trace/trace_printk.c7
-rw-r--r--kernel/trace/trace_stack.c8
-rw-r--r--kernel/trace/trace_stat.c6
-rw-r--r--kernel/trace/trace_uprobe.c11
50 files changed, 869 insertions, 254 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 1f31c2f1e6fc..4508d5e0cf69 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -351,12 +351,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
struct dentry *d = kern_path_locked(watch->path, parent);
if (IS_ERR(d))
return PTR_ERR(d);
- inode_unlock(d_backing_inode(parent->dentry));
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);
return 0;
}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ddd8addcdb5c..a3eaf08e7dd3 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1311,12 +1311,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
return false;
switch (off) {
- case offsetof(struct bpf_sysctl, write):
+ case bpf_ctx_range(struct bpf_sysctl, write):
if (type != BPF_READ)
return false;
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
- case offsetof(struct bpf_sysctl, file_pos):
+ case bpf_ctx_range(struct bpf_sysctl, file_pos):
if (type == BPF_READ) {
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 66088a9e9b9e..ef0e1e3e66f4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -502,7 +502,7 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
}
-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d27f3b60ff6d..3867864cdc2f 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -128,7 +128,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
if (!dtab->n_buckets) /* Overflow check */
return -EINVAL;
- cost += sizeof(struct hlist_head) * dtab->n_buckets;
+ cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets;
}
/* if map size is larger than memlock limit, reject it */
@@ -719,6 +719,32 @@ const struct bpf_map_ops dev_map_hash_ops = {
.map_check_btf = map_check_no_btf,
};
+static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
+ struct net_device *netdev)
+{
+ unsigned long flags;
+ u32 i;
+
+ spin_lock_irqsave(&dtab->index_lock, flags);
+ for (i = 0; i < dtab->n_buckets; i++) {
+ struct bpf_dtab_netdev *dev;
+ struct hlist_head *head;
+ struct hlist_node *next;
+
+ head = dev_map_index_hash(dtab, i);
+
+ hlist_for_each_entry_safe(dev, next, head, index_hlist) {
+ if (netdev != dev->dev)
+ continue;
+
+ dtab->items--;
+ hlist_del_rcu(&dev->index_hlist);
+ call_rcu(&dev->rcu, __dev_map_entry_free);
+ }
+ }
+ spin_unlock_irqrestore(&dtab->index_lock, flags);
+}
+
static int dev_map_notification(struct notifier_block *notifier,
ulong event, void *ptr)
{
@@ -735,6 +761,11 @@ static int dev_map_notification(struct notifier_block *notifier,
*/
rcu_read_lock();
list_for_each_entry_rcu(dtab, &dev_map_list, list) {
+ if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+ dev_map_hash_remove_netdev(dtab, netdev);
+ continue;
+ }
+
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev, *odev;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 82eabd4e38ad..ace1cfaa24b6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -126,7 +126,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
-void *bpf_map_area_alloc(size_t size, int numa_node)
+void *bpf_map_area_alloc(u64 size, int numa_node)
{
/* We really just want to fail instead of triggering OOM killer
* under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -141,6 +141,9 @@ void *bpf_map_area_alloc(size_t size, int numa_node)
const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
void *area;
+ if (size >= SIZE_MAX)
+ return NULL;
+
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
numa_node);
@@ -197,7 +200,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
atomic_long_sub(pages, &user->locked_vm);
}
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size)
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
{
u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
struct user_struct *user;
@@ -1326,24 +1329,32 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
+ kvfree(aux->func_info);
free_used_maps(aux);
bpf_prog_uncharge_memlock(aux->prog);
security_bpf_prog_free(aux);
bpf_prog_free(aux->prog);
}
+static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
+{
+ bpf_prog_kallsyms_del_all(prog);
+ btf_put(prog->aux->btf);
+ bpf_prog_free_linfo(prog);
+
+ if (deferred)
+ call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+ else
+ __bpf_prog_put_rcu(&prog->aux->rcu);
+}
+
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
- bpf_prog_kallsyms_del_all(prog);
- btf_put(prog->aux->btf);
- kvfree(prog->aux->func_info);
- bpf_prog_free_linfo(prog);
-
- call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+ __bpf_prog_put_noref(prog, true);
}
}
@@ -1741,11 +1752,12 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
return err;
free_used_maps:
- bpf_prog_free_linfo(prog);
- kvfree(prog->aux->func_info);
- btf_put(prog->aux->btf);
- bpf_prog_kallsyms_del_subprogs(prog);
- free_used_maps(prog->aux);
+ /* In case we have subprogs, we need to wait for a grace
+ * period before we can tear down JIT memory since symbols
+ * are already exposed under kallsyms.
+ */
+ __bpf_prog_put_noref(prog, prog->aux->func_cnt);
+ return err;
free_prog:
bpf_prog_uncharge_memlock(prog);
free_prog_sec:
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 080561bb8a4b..ef4242e5d4bc 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2119,11 +2119,12 @@ int cgroup_do_get_tree(struct fs_context *fc)
nsdentry = kernfs_node_dentry(cgrp->kn, sb);
dput(fc->root);
- fc->root = nsdentry;
if (IS_ERR(nsdentry)) {
- ret = PTR_ERR(nsdentry);
deactivate_locked_super(sb);
+ ret = PTR_ERR(nsdentry);
+ nsdentry = NULL;
}
+ fc->root = nsdentry;
}
if (!ctx->kfc.new_sb_created)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c52bc91f882b..c87ee6412b36 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -798,7 +798,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
continue;
- if (is_sched_load_balance(cp))
+ if (is_sched_load_balance(cp) &&
+ !cpumask_empty(cp->effective_cpus))
csa[csn++] = cp;
/* skip @cp's subtree if not a partition root */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index fc28e17940e0..e2cad3ee2ead 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2373,7 +2373,18 @@ void __init boot_cpu_hotplug_init(void)
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
-enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+/*
+ * These are used for a global "mitigations=" cmdline option for toggling
+ * optional CPU mitigations.
+ */
+enum cpu_mitigations {
+ CPU_MITIGATIONS_OFF,
+ CPU_MITIGATIONS_AUTO,
+ CPU_MITIGATIONS_AUTO_NOSMT,
+};
+
+static enum cpu_mitigations cpu_mitigations __ro_after_init =
+ CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
@@ -2390,3 +2401,17 @@ static int __init mitigations_parse_cmdline(char *arg)
return 0;
}
early_param("mitigations", mitigations_parse_cmdline);
+
+/* mitigations=off */
+bool cpu_mitigations_off(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_OFF;
+}
+EXPORT_SYMBOL_GPL(cpu_mitigations_off);
+
+/* mitigations=auto,nosmt */
+bool cpu_mitigations_auto_nosmt(void)
+{
+ return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
+}
+EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f0cb82e4fbc..00a014670ed0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1031,7 +1031,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
{
}
-void
+static inline void
perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
{
}
@@ -3779,11 +3779,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event)
perf_event_groups_insert(&ctx->flexible_groups, event);
}
+/* pick an event from the flexible_groups to rotate */
static inline struct perf_event *
-ctx_first_active(struct perf_event_context *ctx)
+ctx_event_to_rotate(struct perf_event_context *ctx)
{
- return list_first_entry_or_null(&ctx->flexible_active,
- struct perf_event, active_list);
+ struct perf_event *event;
+
+ /* pick the first active flexible event */
+ event = list_first_entry_or_null(&ctx->flexible_active,
+ struct perf_event, active_list);
+
+ /* if no active flexible event, pick the first event */
+ if (!event) {
+ event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree),
+ typeof(*event), group_node);
+ }
+
+ return event;
}
static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3808,9 +3820,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_rotate)
- task_event = ctx_first_active(task_ctx);
+ task_event = ctx_event_to_rotate(task_ctx);
if (cpu_rotate)
- cpu_event = ctx_first_active(&cpuctx->ctx);
+ cpu_event = ctx_event_to_rotate(&cpuctx->ctx);
/*
* As per the order given at ctx_resched() first 'pop' task flexible
@@ -5595,8 +5607,10 @@ static void perf_mmap_close(struct vm_area_struct *vma)
perf_pmu_output_stop(event);
/* now it's safe to free the pages */
- atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
- atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
+ if (!rb->aux_mmap_locked)
+ atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
+ else
+ atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
/* this has to be the last one */
rb_free_aux(rb);
@@ -5668,7 +5682,8 @@ again:
* undo the VM accounting.
*/
- atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+ atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
+ &mmap_user->locked_vm);
atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
free_uid(mmap_user);
@@ -5812,8 +5827,20 @@ accounting:
user_locked = atomic_long_read(&user->locked_vm) + user_extra;
- if (user_locked > user_lock_limit)
+ if (user_locked <= user_lock_limit) {
+ /* charge all to locked_vm */
+ } else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) {
+ /* charge all to pinned_vm */
+ extra = user_extra;
+ user_extra = 0;
+ } else {
+ /*
+ * charge locked_vm until it hits user_lock_limit;
+ * charge the rest from pinned_vm
+ */
extra = user_locked - user_lock_limit;
+ user_extra -= extra;
+ }
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
@@ -6922,7 +6949,7 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
static int __perf_pmu_output_stop(void *info)
{
struct perf_event *event = info;
- struct pmu *pmu = event->pmu;
+ struct pmu *pmu = event->ctx->pmu;
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
struct remote_output ro = {
.rb = event->rb,
@@ -10508,6 +10535,15 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
goto err_ns;
}
+ /*
+ * Disallow uncore-cgroup events, they don't make sense as the cgroup will
+ * be different on other CPUs in the uncore mask.
+ */
+ if (pmu->task_ctx_nr == perf_invalid_context && cgroup_fd != -1) {
+ err = -EINVAL;
+ goto err_pmu;
+ }
+
if (event->attr.aux_output &&
!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
err = -EOPNOTSUPP;
@@ -10608,7 +10644,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
attr->size = size;
- if (attr->__reserved_1)
+ if (attr->__reserved_1 || attr->__reserved_2)
return -EINVAL;
if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
@@ -11296,8 +11332,11 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
int err;
/*
- * Get the target context (task or percpu):
+ * Grouping is not supported for kernel events, neither is 'AUX',
+ * make sure the caller's intentions are adjusted.
*/
+ if (attr->aux_output)
+ return ERR_PTR(-EINVAL);
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
overflow_handler, context, -1);
@@ -11309,6 +11348,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
/* Mark owner so we could distinguish it from user events. */
event->owner = TASK_TOMBSTONE;
+ /*
+ * Get the target context (task or percpu):
+ */
ctx = find_get_context(event->pmu, task, event);
if (IS_ERR(ctx)) {
err = PTR_ERR(ctx);
@@ -11760,7 +11802,7 @@ inherit_event(struct perf_event *parent_event,
GFP_KERNEL);
if (!child_ctx->task_ctx_data) {
free_event(child_event);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
}
@@ -11862,6 +11904,10 @@ static int inherit_group(struct perf_event *parent_event,
child, leader, child_ctx);
if (IS_ERR(child_ctr))
return PTR_ERR(child_ctr);
+
+ if (sub->aux_event == parent_event && child_ctr &&
+ !perf_get_aux_event(child_ctr, leader))
+ return -EINVAL;
}
return 0;
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 94d38a39d72e..c74761004ee5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
struct vm_area_struct *vma;
int ret, is_register, ref_ctr_updated = 0;
bool orig_page_huge = false;
+ unsigned int gup_flags = FOLL_FORCE;
is_register = is_swbp_insn(&opcode);
uprobe = container_of(auprobe, struct uprobe, arch);
retry:
+ if (is_register)
+ gup_flags |= FOLL_SPLIT_PMD;
/* Read the page with vaddr into memory */
- ret = get_user_pages_remote(NULL, mm, vaddr, 1,
- FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL);
+ ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+ &old_page, &vma, NULL);
if (ret <= 0)
return ret;
@@ -489,6 +492,12 @@ retry:
if (ret <= 0)
goto put_old;
+ if (WARN(!is_register && PageCompound(old_page),
+ "uprobe unregister should never work on compound page\n")) {
+ ret = -EINVAL;
+ goto put_old;
+ }
+
/* We are going to replace instruction, update ref_ctr. */
if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
diff --git a/kernel/fork.c b/kernel/fork.c
index 1f6c45f6a734..55af6931c6ec 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2561,7 +2561,35 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
return 0;
}
-static bool clone3_args_valid(const struct kernel_clone_args *kargs)
+/**
+ * clone3_stack_valid - check and prepare stack
+ * @kargs: kernel clone args
+ *
+ * Verify that the stack arguments userspace gave us are sane.
+ * In addition, set the stack direction for userspace since it's easy for us to
+ * determine.
+ */
+static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
+{
+ if (kargs->stack == 0) {
+ if (kargs->stack_size > 0)
+ return false;
+ } else {
+ if (kargs->stack_size == 0)
+ return false;
+
+ if (!access_ok((void __user *)kargs->stack, kargs->stack_size))
+ return false;
+
+#if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64)
+ kargs->stack += kargs->stack_size;
+#endif
+ }
+
+ return true;
+}
+
+static bool clone3_args_valid(struct kernel_clone_args *kargs)
{
/*
* All lower bits of the flag word are taken.
@@ -2581,6 +2609,9 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs)
kargs->exit_signal)
return false;
+ if (!clone3_stack_valid(kargs))
+ return false;
+
return true;
}
@@ -2925,7 +2956,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
struct ctl_table t;
int ret;
int threads = max_threads;
- int min = MIN_THREADS;
+ int min = 1;
int max = MAX_THREADS;
t = *table;
@@ -2937,7 +2968,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
if (ret || !write)
return ret;
- set_max_threads(threads);
+ max_threads = threads;
return 0;
}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c0738424bb43..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -22,12 +22,6 @@ EXPORT_SYMBOL(system_freezing_cnt);
bool pm_freezing;
bool pm_nosig_freezing;
-/*
- * Temporary export for the deadlock workaround in ata_scsi_hotplug().
- * Remove once the hack becomes unnecessary.
- */
-EXPORT_SYMBOL_GPL(pm_freezing);
-
/* protects freezing and frozen transitions */
static DEFINE_SPINLOCK(freezer_lock);
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index aff79e461fc9..5a0fc0b0403a 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -71,10 +71,13 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1
find $cpio_dir -type f -print0 |
xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;'
-# Create archive and try to normalize metadata for reproducibility
-tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
- --owner=0 --group=0 --sort=name --numeric-owner \
- -Jcf $tarfile -C $cpio_dir/ . > /dev/null
+# Create archive and try to normalize metadata for reproducibility.
+# For compatibility with older versions of tar, files are fed to tar
+# pre-sorted, as --sort=name might not be available.
+find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \
+ tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+ --owner=0 --group=0 --numeric-owner --no-recursion \
+ -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null
echo "$src_files_md5" > kernel/kheaders.md5
echo "$obj_files_md5" >> kernel/kheaders.md5
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 132672b74e4b..dd822fd8a7d5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
* @type: Type of irqchip_fwnode. See linux/irqdomain.h
* @name: Optional user provided domain name
* @id: Optional user provided id if name != NULL
- * @data: Optional user-provided data
+ * @pa: Optional user-provided physical address
*
* Allocate a struct irqchip_fwid, and return a poiner to the embedded
* fwnode_handle (or NULL on failure).
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 621467c33fef..b262f47046ca 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -866,9 +866,9 @@ void kthread_delayed_work_timer_fn(struct timer_list *t)
}
EXPORT_SYMBOL(kthread_delayed_work_timer_fn);
-void __kthread_queue_delayed_work(struct kthread_worker *worker,
- struct kthread_delayed_work *dwork,
- unsigned long delay)
+static void __kthread_queue_delayed_work(struct kthread_worker *worker,
+ struct kthread_delayed_work *dwork,
+ unsigned long delay)
{
struct timer_list *timer = &dwork->timer;
struct kthread_work *work = &dwork->work;
diff --git a/kernel/panic.c b/kernel/panic.c
index 47e8ebccc22b..f470a038b05b 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -180,6 +180,7 @@ void panic(const char *fmt, ...)
* after setting panic_cpu) from invoking panic() again.
*/
local_irq_disable();
+ preempt_disable_notrace();
/*
* It's possible to come here directly from a panic-assertion and
diff --git a/kernel/power/main.c b/kernel/power/main.c
index e8710d179b35..e26de7af520b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,6 +15,7 @@
#include <linux/seq_file.h>
#include <linux/suspend.h>
#include <linux/syscalls.h>
+#include <linux/pm_runtime.h>
#include "power.h"
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 9568a2fe7c11..04e83fdfbe80 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -650,3 +650,243 @@ static int __init pm_qos_power_init(void)
}
late_initcall(pm_qos_power_init);
+
+/* Definitions related to the frequency QoS below. */
+
+/**
+ * freq_constraints_init - Initialize frequency QoS constraints.
+ * @qos: Frequency QoS constraints to initialize.
+ */
+void freq_constraints_init(struct freq_constraints *qos)
+{
+ struct pm_qos_constraints *c;
+
+ c = &qos->min_freq;
+ plist_head_init(&c->list);
+ c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+ c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+ c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+ c->type = PM_QOS_MAX;
+ c->notifiers = &qos->min_freq_notifiers;
+ BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+
+ c = &qos->max_freq;
+ plist_head_init(&c->list);
+ c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+ c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+ c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+ c->type = PM_QOS_MIN;
+ c->notifiers = &qos->max_freq_notifiers;
+ BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+}
+
+/**
+ * freq_qos_read_value - Get frequency QoS constraint for a given list.
+ * @qos: Constraints to evaluate.
+ * @type: QoS request type.
+ */
+s32 freq_qos_read_value(struct freq_constraints *qos,
+ enum freq_qos_req_type type)
+{
+ s32 ret;
+
+ switch (type) {
+ case FREQ_QOS_MIN:
+ ret = IS_ERR_OR_NULL(qos) ?
+ FREQ_QOS_MIN_DEFAULT_VALUE :
+ pm_qos_read_value(&qos->min_freq);
+ break;
+ case FREQ_QOS_MAX:
+ ret = IS_ERR_OR_NULL(qos) ?
+ FREQ_QOS_MAX_DEFAULT_VALUE :
+ pm_qos_read_value(&qos->max_freq);
+ break;
+ default:
+ WARN_ON(1);
+ ret = 0;
+ }
+
+ return ret;
+}
+
+/**
+ * freq_qos_apply - Add/modify/remove frequency QoS request.
+ * @req: Constraint request to apply.
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
+ */
+static int freq_qos_apply(struct freq_qos_request *req,
+ enum pm_qos_req_action action, s32 value)
+{
+ int ret;
+
+ switch(req->type) {
+ case FREQ_QOS_MIN:
+ ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode,
+ action, value);
+ break;
+ case FREQ_QOS_MAX:
+ ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode,
+ action, value);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+/**
+ * freq_qos_add_request - Insert new frequency QoS request into a given list.
+ * @qos: Constraints to update.
+ * @req: Preallocated request object.
+ * @type: Request type.
+ * @value: Request value.
+ *
+ * Insert a new entry into the @qos list of requests, recompute the effective
+ * QoS constraint value for that list and initialize the @req object. The
+ * caller needs to save that object for later use in updates and removal.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_add_request(struct freq_constraints *qos,
+ struct freq_qos_request *req,
+ enum freq_qos_req_type type, s32 value)
+{
+ int ret;
+
+ if (IS_ERR_OR_NULL(qos) || !req)
+ return -EINVAL;
+
+ if (WARN(freq_qos_request_active(req),
+ "%s() called for active request\n", __func__))
+ return -EINVAL;
+
+ req->qos = qos;
+ req->type = type;
+ ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value);
+ if (ret < 0) {
+ req->qos = NULL;
+ req->type = 0;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_request);
+
+/**
+ * freq_qos_update_request - Modify existing frequency QoS request.
+ * @req: Request to modify.
+ * @new_value: New request value.
+ *
+ * Update an existing frequency QoS request along with the effective constraint
+ * value for the list of requests it belongs to.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_update_request(struct freq_qos_request *req, s32 new_value)
+{
+ if (!req)
+ return -EINVAL;
+
+ if (WARN(!freq_qos_request_active(req),
+ "%s() called for unknown object\n", __func__))
+ return -EINVAL;
+
+ if (req->pnode.prio == new_value)
+ return 0;
+
+ return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
+}
+EXPORT_SYMBOL_GPL(freq_qos_update_request);
+
+/**
+ * freq_qos_remove_request - Remove frequency QoS request from its list.
+ * @req: Request to remove.
+ *
+ * Remove the given frequency QoS request from the list of constraints it
+ * belongs to and recompute the effective constraint value for that list.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_remove_request(struct freq_qos_request *req)
+{
+ if (!req)
+ return -EINVAL;
+
+ if (WARN(!freq_qos_request_active(req),
+ "%s() called for unknown object\n", __func__))
+ return -EINVAL;
+
+ return freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_request);
+
+/**
+ * freq_qos_add_notifier - Add frequency QoS change notifier.
+ * @qos: List of requests to add the notifier to.
+ * @type: Request type.
+ * @notifier: Notifier block to add.
+ */
+int freq_qos_add_notifier(struct freq_constraints *qos,
+ enum freq_qos_req_type type,
+ struct notifier_block *notifier)
+{
+ int ret;
+
+ if (IS_ERR_OR_NULL(qos) || !notifier)
+ return -EINVAL;
+
+ switch (type) {
+ case FREQ_QOS_MIN:
+ ret = blocking_notifier_chain_register(qos->min_freq.notifiers,
+ notifier);
+ break;
+ case FREQ_QOS_MAX:
+ ret = blocking_notifier_chain_register(qos->max_freq.notifiers,
+ notifier);
+ break;
+ default:
+ WARN_ON(1);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_notifier);
+
+/**
+ * freq_qos_remove_notifier - Remove frequency QoS change notifier.
+ * @qos: List of requests to remove the notifier from.
+ * @type: Request type.
+ * @notifier: Notifier block to remove.
+ */
+int freq_qos_remove_notifier(struct freq_constraints *qos,
+ enum freq_qos_req_type type,
+ struct notifier_block *notifier)
+{
+ int ret;
+
+ if (IS_ERR_OR_NULL(qos) || !notifier)
+ return -EINVAL;
+
+ switch (type) {
+ case FREQ_QOS_MIN:
+ ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers,
+ notifier);
+ break;
+ case FREQ_QOS_MAX:
+ ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers,
+ notifier);
+ break;
+ default:
+ WARN_ON(1);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_notifier);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd05a378631a..44123b4d14e8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1065,7 +1065,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
* affecting a valid clamp bucket, the next time it's enqueued,
* it will already see the updated clamp bucket value.
*/
- if (!p->uclamp[clamp_id].active) {
+ if (p->uclamp[clamp_id].active) {
uclamp_rq_dec_id(rq, p, clamp_id);
uclamp_rq_inc_id(rq, p, clamp_id);
}
@@ -1073,6 +1073,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
task_rq_unlock(rq, p, &rf);
}
+#ifdef CONFIG_UCLAMP_TASK_GROUP
static inline void
uclamp_update_active_tasks(struct cgroup_subsys_state *css,
unsigned int clamps)
@@ -1091,7 +1092,6 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css,
css_task_iter_end(&it);
}
-#ifdef CONFIG_UCLAMP_TASK_GROUP
static void cpu_util_update_eff(struct cgroup_subsys_state *css);
static void uclamp_update_root_tg(void)
{
@@ -3929,13 +3929,22 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
restart:
+#ifdef CONFIG_SMP
/*
- * Ensure that we put DL/RT tasks before the pick loop, such that they
- * can PULL higher prio tasks when we lower the RQ 'priority'.
+ * We must do the balancing pass before put_next_task(), such
+ * that when we release the rq->lock the task is in the same
+ * state as before we took rq->lock.
+ *
+ * We can terminate the balance pass as soon as we know there is
+ * a runnable task of @class priority or higher.
*/
- prev->sched_class->put_prev_task(rq, prev, rf);
- if (!rq->nr_running)
- newidle_balance(rq, rf);
+ for_class_range(class, prev->sched_class, &idle_sched_class) {
+ if (class->balance(rq, prev, rf))
+ break;
+ }
+#endif
+
+ put_prev_task(rq, prev);
for_each_class(class) {
p = class->pick_next_task(rq, NULL, NULL);
@@ -6010,10 +6019,11 @@ void init_idle(struct task_struct *idle, int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
+ __sched_fork(0, idle);
+
raw_spin_lock_irqsave(&idle->pi_lock, flags);
raw_spin_lock(&rq->lock);
- __sched_fork(0, idle);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
idle->flags |= PF_IDLE;
@@ -6201,7 +6211,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq)
for_each_class(class) {
next = class->pick_next_task(rq, NULL, NULL);
if (next) {
- next->sched_class->put_prev_task(rq, next, NULL);
+ next->sched_class->put_prev_task(rq, next);
return next;
}
}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2305ce89a26c..46ed4e1383e2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
/* We might have scheduled out from guest path */
- if (current->flags & PF_VCPU)
+ if (tsk->flags & PF_VCPU)
vtime_account_guest(tsk, vtime);
else
__vtime_account_system(tsk, vtime);
@@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk)
*/
write_seqcount_begin(&vtime->seqcount);
__vtime_account_system(tsk, vtime);
- current->flags |= PF_VCPU;
+ tsk->flags |= PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
vtime_account_guest(tsk, vtime);
- current->flags &= ~PF_VCPU;
+ tsk->flags &= ~PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_exit);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2dc48720f189..a8a08030a8f7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1691,6 +1691,22 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
resched_curr(rq);
}
+static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+ if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_dl_task(rq);
+ rq_repin_lock(rq, rf);
+ }
+
+ return sched_stop_runnable(rq) || sched_dl_runnable(rq);
+}
#endif /* CONFIG_SMP */
/*
@@ -1758,45 +1774,28 @@ static struct task_struct *
pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
+ struct dl_rq *dl_rq = &rq->dl;
struct task_struct *p;
- struct dl_rq *dl_rq;
WARN_ON_ONCE(prev || rf);
- dl_rq = &rq->dl;
-
- if (unlikely(!dl_rq->dl_nr_running))
+ if (!sched_dl_runnable(rq))
return NULL;
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);
-
p = dl_task_of(dl_se);
-
set_next_task_dl(rq, p);
-
return p;
}
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
{
update_curr_dl(rq);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
-
- if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we've
- * not yet started the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_dl_task(rq);
- rq_repin_lock(rq, rf);
- }
}
/*
@@ -2442,6 +2441,7 @@ const struct sched_class dl_sched_class = {
.set_next_task = set_next_task_dl,
#ifdef CONFIG_SMP
+ .balance = balance_dl,
.select_task_rq = select_task_rq_dl,
.migrate_task_rq = migrate_task_rq_dl,
.set_cpus_allowed = set_cpus_allowed_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 83ab35e2374f..69a81a5709ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4926,20 +4926,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (++count > 3) {
u64 new, old = ktime_to_ns(cfs_b->period);
- new = (old * 147) / 128; /* ~115% */
- new = min(new, max_cfs_quota_period);
-
- cfs_b->period = ns_to_ktime(new);
-
- /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
- cfs_b->quota *= new;
- cfs_b->quota = div64_u64(cfs_b->quota, old);
-
- pr_warn_ratelimited(
- "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
- smp_processor_id(),
- div_u64(new, NSEC_PER_USEC),
- div_u64(cfs_b->quota, NSEC_PER_USEC));
+ /*
+ * Grow period by a factor of 2 to avoid losing precision.
+ * Precision loss in the quota/period ratio can cause __cfs_schedulable
+ * to fail.
+ */
+ new = old * 2;
+ if (new < max_cfs_quota_period) {
+ cfs_b->period = ns_to_ktime(new);
+ cfs_b->quota *= 2;
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ } else {
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(old, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ }
/* reset count so we don't come right back in here */
count = 0;
@@ -6562,6 +6570,15 @@ static void task_dead_fair(struct task_struct *p)
{
remove_entity_load_avg(&p->se);
}
+
+static int
+balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ if (rq->nr_running)
+ return 1;
+
+ return newidle_balance(rq, rf) != 0;
+}
#endif /* CONFIG_SMP */
static unsigned long wakeup_gran(struct sched_entity *se)
@@ -6738,7 +6755,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
int new_tasks;
again:
- if (!cfs_rq->nr_running)
+ if (!sched_fair_runnable(rq))
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6876,7 +6893,7 @@ idle:
/*
* Account for a descheduled task:
*/
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
@@ -7531,6 +7548,19 @@ static void update_blocked_averages(int cpu)
update_rq_clock(rq);
/*
+ * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+ * that RT, DL and IRQ signals have been updated before updating CFS.
+ */
+ curr_class = rq->curr->sched_class;
+ update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
+ update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
+ update_irq_load_avg(rq, 0);
+
+ /* Don't need periodic decay once load/util_avg are null */
+ if (others_have_blocked(rq))
+ done = false;
+
+ /*
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
@@ -7557,14 +7587,6 @@ static void update_blocked_averages(int cpu)
done = false;
}
- curr_class = rq->curr->sched_class;
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
- update_irq_load_avg(rq, 0);
- /* Don't need periodic decay once load/util_avg are null */
- if (others_have_blocked(rq))
- done = false;
-
update_blocked_load_status(rq, !done);
rq_unlock_irqrestore(rq, &rf);
}
@@ -7625,12 +7647,18 @@ static inline void update_blocked_averages(int cpu)
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+ /*
+ * update_cfs_rq_load_avg() can call cpufreq_update_util(). Make sure
+ * that RT, DL and IRQ signals have been updated before updating CFS.
+ */
curr_class = rq->curr->sched_class;
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
update_irq_load_avg(rq, 0);
+
+ update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+
update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq));
rq_unlock_irqrestore(rq, &rf);
}
@@ -10406,11 +10434,11 @@ const struct sched_class fair_sched_class = {
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair,
-
.put_prev_task = put_prev_task_fair,
.set_next_task = set_next_task_fair,
#ifdef CONFIG_SMP
+ .balance = balance_fair,
.select_task_rq = select_task_rq_fair,
.migrate_task_rq = migrate_task_rq_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8dad5aa600ea..f65ef1e2f204 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -365,6 +365,12 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
+
+static int
+balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ return WARN_ON_ONCE(1);
+}
#endif
/*
@@ -375,7 +381,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
resched_curr(rq);
}
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
}
@@ -460,6 +466,7 @@ const struct sched_class idle_sched_class = {
.set_next_task = set_next_task_idle,
#ifdef CONFIG_SMP
+ .balance = balance_idle,
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ebaa4e619684..9b8adc01be3d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1469,6 +1469,22 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
resched_curr(rq);
}
+static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+ if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_rt_task(rq);
+ rq_repin_lock(rq, rf);
+ }
+
+ return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq);
+}
#endif /* CONFIG_SMP */
/*
@@ -1552,21 +1568,18 @@ static struct task_struct *
pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *p;
- struct rt_rq *rt_rq = &rq->rt;
WARN_ON_ONCE(prev || rf);
- if (!rt_rq->rt_queued)
+ if (!sched_rt_runnable(rq))
return NULL;
p = _pick_next_task_rt(rq);
-
set_next_task_rt(rq, p);
-
return p;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
update_curr_rt(rq);
@@ -1578,18 +1591,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_fla
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
-
- if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we've
- * not yet started the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
- rq_repin_lock(rq, rf);
- }
}
#ifdef CONFIG_SMP
@@ -2366,8 +2367,8 @@ const struct sched_class rt_sched_class = {
.set_next_task = set_next_task_rt,
#ifdef CONFIG_SMP
+ .balance = balance_rt,
.select_task_rq = select_task_rq_rt,
-
.set_cpus_allowed = set_cpus_allowed_common,
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0db2c1b3361e..c8870c5bd7df 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1727,10 +1727,11 @@ struct sched_class {
struct task_struct * (*pick_next_task)(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf);
- void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
+ void (*put_prev_task)(struct rq *rq, struct task_struct *p);
void (*set_next_task)(struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
+ int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
@@ -1773,7 +1774,7 @@ struct sched_class {
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
WARN_ON_ONCE(rq->curr != prev);
- prev->sched_class->put_prev_task(rq, prev, NULL);
+ prev->sched_class->put_prev_task(rq, prev);
}
static inline void set_next_task(struct rq *rq, struct task_struct *next)
@@ -1787,8 +1788,12 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
#else
#define sched_class_highest (&dl_sched_class)
#endif
+
+#define for_class_range(class, _from, _to) \
+ for (class = (_from); class != (_to); class = class->next)
+
#define for_each_class(class) \
- for (class = sched_class_highest; class; class = class->next)
+ for_class_range(class, sched_class_highest, NULL)
extern const struct sched_class stop_sched_class;
extern const struct sched_class dl_sched_class;
@@ -1796,6 +1801,25 @@ extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
+static inline bool sched_stop_runnable(struct rq *rq)
+{
+ return rq->stop && task_on_rq_queued(rq->stop);
+}
+
+static inline bool sched_dl_runnable(struct rq *rq)
+{
+ return rq->dl.dl_nr_running > 0;
+}
+
+static inline bool sched_rt_runnable(struct rq *rq)
+{
+ return rq->rt.rt_queued > 0;
+}
+
+static inline bool sched_fair_runnable(struct rq *rq)
+{
+ return rq->cfs.nr_running > 0;
+}
#ifdef CONFIG_SMP
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 7e1cee4e65b2..c0640739e05e 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -15,6 +15,12 @@ select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
{
return task_cpu(p); /* stop tasks as never migrate */
}
+
+static int
+balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+ return sched_stop_runnable(rq);
+}
#endif /* CONFIG_SMP */
static void
@@ -31,16 +37,13 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
static struct task_struct *
pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
- struct task_struct *stop = rq->stop;
-
WARN_ON_ONCE(prev || rf);
- if (!stop || !task_on_rq_queued(stop))
+ if (!sched_stop_runnable(rq))
return NULL;
- set_next_task_stop(rq, stop);
-
- return stop;
+ set_next_task_stop(rq, rq->stop);
+ return rq->stop;
}
static void
@@ -60,7 +63,7 @@ static void yield_task_stop(struct rq *rq)
BUG(); /* the stop task should never yield, its pointless. */
}
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
{
struct task_struct *curr = rq->curr;
u64 delta_exec;
@@ -129,6 +132,7 @@ const struct sched_class stop_sched_class = {
.set_next_task = set_next_task_stop,
#ifdef CONFIG_SMP
+ .balance = balance_stop,
.select_task_rq = select_task_rq_stop,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index b5667a273bf6..49b835f1305f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1948,7 +1948,7 @@ next_level:
static int
build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
{
- enum s_alloc alloc_state;
+ enum s_alloc alloc_state = sa_none;
struct sched_domain *sd;
struct s_data d;
struct rq *rq = NULL;
@@ -1956,6 +1956,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
struct sched_domain_topology_level *tl_asym;
bool has_asym = false;
+ if (WARN_ON(cpumask_empty(cpu_map)))
+ goto error;
+
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
if (alloc_state != sa_rootdomain)
goto error;
@@ -2026,7 +2029,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
rcu_read_unlock();
if (has_asym)
- static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
+ static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
if (rq && sched_debug_enabled) {
pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
@@ -2121,8 +2124,12 @@ int sched_init_domains(const struct cpumask *cpu_map)
*/
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
+ unsigned int cpu = cpumask_any(cpu_map);
int i;
+ if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
+ static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
+
rcu_read_lock();
for_each_cpu(i, cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
diff --git a/kernel/signal.c b/kernel/signal.c
index c4da1ef56fdf..bcd46f547db3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2205,8 +2205,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
*/
preempt_disable();
read_unlock(&tasklist_lock);
- preempt_enable_no_resched();
cgroup_enter_frozen();
+ preempt_enable_no_resched();
freezable_schedule();
cgroup_leave_frozen(true);
} else {
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 6d1f68b7e528..c9ea7eb2cb1a 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -141,7 +141,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
struct stacktrace_cookie c = {
.store = store,
.size = size,
- .skip = skipnr + 1,
+ /* skip this function if they are tracing us */
+ .skip = skipnr + !!(current == tsk),
};
if (!try_get_task_stack(tsk))
@@ -298,7 +299,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *task,
struct stack_trace trace = {
.entries = store,
.max_entries = size,
- .skip = skipnr + 1,
+ /* skip this function if they are tracing us */
+ .skip = skipnr + !!(current == task),
};
save_stack_trace_tsk(task, &trace);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c7031a22aa7b..998d50ee2d9b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -7,6 +7,7 @@
* Copyright (C) 2010 SUSE Linux Products GmbH
* Copyright (C) 2010 Tejun Heo <tj@kernel.org>
*/
+#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/cpu.h>
#include <linux/init.h>
@@ -167,7 +168,7 @@ static void set_state(struct multi_stop_data *msdata,
/* Reset ack counter. */
atomic_set(&msdata->thread_ack, msdata->num_threads);
smp_wmb();
- msdata->state = newstate;
+ WRITE_ONCE(msdata->state, newstate);
}
/* Last one to ack a state moves to the next state. */
@@ -186,7 +187,7 @@ void __weak stop_machine_yield(const struct cpumask *cpumask)
static int multi_cpu_stop(void *data)
{
struct multi_stop_data *msdata = data;
- enum multi_stop_state curstate = MULTI_STOP_NONE;
+ enum multi_stop_state newstate, curstate = MULTI_STOP_NONE;
int cpu = smp_processor_id(), err = 0;
const struct cpumask *cpumask;
unsigned long flags;
@@ -210,8 +211,9 @@ static int multi_cpu_stop(void *data)
do {
/* Chill out and ensure we re-read multi_stop_state. */
stop_machine_yield(cpumask);
- if (msdata->state != curstate) {
- curstate = msdata->state;
+ newstate = READ_ONCE(msdata->state);
+ if (newstate != curstate) {
+ curstate = newstate;
switch (curstate) {
case MULTI_STOP_DISABLE_IRQ:
local_irq_disable();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 00fcea236eba..b6f2f35d0bcf 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -163,7 +163,7 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
#ifdef CONFIG_SPARC
#endif
-#ifdef __hppa__
+#ifdef CONFIG_PARISC
extern int pwrsw_enabled;
#endif
@@ -620,7 +620,7 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
-#ifdef __hppa__
+#ifdef CONFIG_PARISC
{
.procname = "soft-power",
.data = &pwrsw_enabled,
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 0d4dc241c0fb..65605530ee34 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -164,7 +164,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
struct hrtimer_clock_base *base;
for (;;) {
- base = timer->base;
+ base = READ_ONCE(timer->base);
if (likely(base != &migration_base)) {
raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
if (likely(base == timer->base))
@@ -244,7 +244,7 @@ again:
return base;
/* See the comment in lock_hrtimer_base() */
- timer->base = &migration_base;
+ WRITE_ONCE(timer->base, &migration_base);
raw_spin_unlock(&base->cpu_base->lock);
raw_spin_lock(&new_base->cpu_base->lock);
@@ -253,10 +253,10 @@ again:
raw_spin_unlock(&new_base->cpu_base->lock);
raw_spin_lock(&base->cpu_base->lock);
new_cpu_base = this_cpu_base;
- timer->base = base;
+ WRITE_ONCE(timer->base, base);
goto again;
}
- timer->base = new_base;
+ WRITE_ONCE(timer->base, new_base);
} else {
if (new_cpu_base != this_cpu_base &&
hrtimer_check_target(timer, new_base)) {
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 65eb796610dc..069ca78fb0bf 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -771,7 +771,7 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts,
/* fill PPS status fields */
pps_fill_timex(txc);
- txc->time.tv_sec = (time_t)ts->tv_sec;
+ txc->time.tv_sec = ts->tv_sec;
txc->time.tv_usec = ts->tv_nsec;
if (!(time_status & STA_NANO))
txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 92a431981b1c..42d512fcfda2 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -266,7 +266,7 @@ static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic,
/**
* thread_group_sample_cputime - Sample cputime for a given task
* @tsk: Task for which cputime needs to be started
- * @iimes: Storage for time samples
+ * @samples: Storage for time samples
*
* Called from sys_getitimer() to calculate the expiry time of an active
* timer. That means group cputime accounting is already active. Called
@@ -1038,12 +1038,12 @@ unlock:
* member of @pct->bases[CLK].nextevt. False otherwise
*/
static inline bool
-task_cputimers_expired(const u64 *sample, struct posix_cputimers *pct)
+task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct)
{
int i;
for (i = 0; i < CPUCLOCK_MAX; i++) {
- if (sample[i] >= pct->bases[i].nextevt)
+ if (samples[i] >= pct->bases[i].nextevt)
return true;
}
return false;
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 142b07619918..dbd69052eaa6 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -17,6 +17,8 @@
#include <linux/seqlock.h>
#include <linux/bitops.h>
+#include "timekeeping.h"
+
/**
* struct clock_read_data - data required to read from sched_clock()
*
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 4bc37ac3bb05..5ee0f7709410 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -110,8 +110,7 @@ void update_vsyscall(struct timekeeper *tk)
nsec = nsec + tk->wall_to_monotonic.tv_nsec;
vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
- if (__arch_use_vsyscall(vdata))
- update_vdso_data(vdata, tk);
+ update_vdso_data(vdata, tk);
__arch_update_vsyscall(vdata, tk);
@@ -124,10 +123,8 @@ void update_vsyscall_tz(void)
{
struct vdso_data *vdata = __arch_get_k_vdso_data();
- if (__arch_use_vsyscall(vdata)) {
- vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
- vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
- }
+ vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
+ vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
__arch_sync_vdso_data(vdata);
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 62a50bf399d6..f296d89be757 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -18,6 +18,7 @@
#include <linux/clocksource.h>
#include <linux/sched/task.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/tracefs.h>
#include <linux/hardirq.h>
@@ -3486,6 +3487,11 @@ static int
ftrace_avail_open(struct inode *inode, struct file *file)
{
struct ftrace_iterator *iter;
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
@@ -3505,6 +3511,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
{
struct ftrace_iterator *iter;
+ /*
+ * This shows us what functions are currently being
+ * traced and by what. Not sure if we want lockdown
+ * to hide such critical information for an admin.
+ * Although, perhaps it can show information we don't
+ * want people to see, but if something is tracing
+ * something, we probably want to know about it.
+ */
+
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
if (!iter)
return -ENOMEM;
@@ -3540,21 +3555,22 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
struct ftrace_hash *hash;
struct list_head *mod_head;
struct trace_array *tr = ops->private;
- int ret = 0;
+ int ret = -ENOMEM;
ftrace_ops_init(ops);
if (unlikely(ftrace_disabled))
return -ENODEV;
+ if (tracing_check_open_get_tr(tr))
+ return -ENODEV;
+
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter)
- return -ENOMEM;
+ goto out;
- if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
- kfree(iter);
- return -ENOMEM;
- }
+ if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX))
+ goto out;
iter->ops = ops;
iter->flags = flag;
@@ -3584,13 +3600,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
if (!iter->hash) {
trace_parser_put(&iter->parser);
- kfree(iter);
- ret = -ENOMEM;
goto out_unlock;
}
} else
iter->hash = hash;
+ ret = 0;
+
if (file->f_mode & FMODE_READ) {
iter->pg = ftrace_pages_start;
@@ -3602,7 +3618,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
/* Failed */
free_ftrace_hash(iter->hash);
trace_parser_put(&iter->parser);
- kfree(iter);
}
} else
file->private_data = iter;
@@ -3610,6 +3625,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
out_unlock:
mutex_unlock(&ops->func_hash->regex_lock);
+ out:
+ if (ret) {
+ kfree(iter);
+ if (tr)
+ trace_array_put(tr);
+ }
+
return ret;
}
@@ -3618,6 +3640,7 @@ ftrace_filter_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops,
FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES,
inode, file);
@@ -3628,6 +3651,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE,
inode, file);
}
@@ -5037,6 +5061,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
mutex_unlock(&iter->ops->func_hash->regex_lock);
free_ftrace_hash(iter->hash);
+ if (iter->tr)
+ trace_array_put(iter->tr);
kfree(iter);
return 0;
@@ -5194,9 +5220,13 @@ static int
__ftrace_graph_open(struct inode *inode, struct file *file,
struct ftrace_graph_data *fgd)
{
- int ret = 0;
+ int ret;
struct ftrace_hash *new_hash = NULL;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if (file->f_mode & FMODE_WRITE) {
const int size_bits = FTRACE_HASH_DEFAULT_BITS;
@@ -6537,8 +6567,9 @@ ftrace_pid_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret = 0;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 252f79c435f8..6a0ee9178365 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
#include <linux/stacktrace.h>
#include <linux/writeback.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
@@ -304,6 +305,23 @@ void trace_array_put(struct trace_array *this_tr)
mutex_unlock(&trace_types_lock);
}
+int tracing_check_open_get_tr(struct trace_array *tr)
+{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ if (tr && trace_array_get(tr) < 0)
+ return -ENODEV;
+
+ return 0;
+}
+
int call_filter_check_discard(struct trace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
@@ -4140,8 +4158,11 @@ release:
int tracing_open_generic(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
filp->private_data = inode->i_private;
return 0;
@@ -4156,15 +4177,14 @@ bool tracing_is_disabled(void)
* Open and update trace_array ref count.
* Must have the current trace_array passed to it.
*/
-static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
+int tracing_open_generic_tr(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
+ int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
filp->private_data = inode->i_private;
@@ -4233,10 +4253,11 @@ static int tracing_open(struct inode *inode, struct file *file)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
- int ret = 0;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
@@ -4352,12 +4373,15 @@ static int show_traces_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret;
- if (tracing_disabled)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = seq_open(file, &show_traces_seq_ops);
- if (ret)
+ if (ret) {
+ trace_array_put(tr);
return ret;
+ }
m = file->private_data;
m->private = tr;
@@ -4365,6 +4389,14 @@ static int show_traces_open(struct inode *inode, struct file *file)
return 0;
}
+static int show_traces_release(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+
+ trace_array_put(tr);
+ return seq_release(inode, file);
+}
+
static ssize_t
tracing_write_stub(struct file *filp, const char __user *ubuf,
size_t count, loff_t *ppos)
@@ -4395,8 +4427,8 @@ static const struct file_operations tracing_fops = {
static const struct file_operations show_traces_fops = {
.open = show_traces_open,
.read = seq_read,
- .release = seq_release,
.llseek = seq_lseek,
+ .release = show_traces_release,
};
static ssize_t
@@ -4697,11 +4729,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_trace_options_show, inode->i_private);
if (ret < 0)
@@ -5038,8 +5068,11 @@ static const struct seq_operations tracing_saved_tgids_seq_ops = {
static int tracing_saved_tgids_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_saved_tgids_seq_ops);
}
@@ -5115,8 +5148,11 @@ static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
}
@@ -5280,8 +5316,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = {
static int tracing_eval_map_open(struct inode *inode, struct file *filp)
{
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
+
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
return seq_open(filp, &tracing_eval_map_seq_ops);
}
@@ -5804,13 +5843,11 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
- int ret = 0;
-
- if (tracing_disabled)
- return -ENODEV;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
mutex_lock(&trace_types_lock);
@@ -5999,6 +6036,7 @@ waitagain:
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
cpumask_clear(iter->started);
+ trace_seq_init(&iter->seq);
iter->pos = -1;
trace_event_read_lock();
@@ -6547,11 +6585,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr))
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_clock_show, inode->i_private);
if (ret < 0)
@@ -6581,11 +6617,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr))
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private);
if (ret < 0)
@@ -6638,10 +6672,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
struct seq_file *m;
- int ret = 0;
+ int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if (file->f_mode & FMODE_READ) {
iter = __tracing_open(inode, file, true);
@@ -6786,6 +6821,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp)
struct ftrace_buffer_info *info;
int ret;
+ /* The following checks for tracefs lockdown */
ret = tracing_buffers_open(inode, filp);
if (ret < 0)
return ret;
@@ -7105,8 +7141,9 @@ static int tracing_err_log_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret = 0;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
/* If this file was opened for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
@@ -7157,11 +7194,9 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
struct ftrace_buffer_info *info;
int ret;
- if (tracing_disabled)
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f801d154ff6a..d685c61085c0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -338,6 +338,7 @@ extern struct mutex trace_types_lock;
extern int trace_array_get(struct trace_array *tr);
extern void trace_array_put(struct trace_array *tr);
+extern int tracing_check_open_get_tr(struct trace_array *tr);
extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
@@ -681,6 +682,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf);
void tracing_reset_current(int cpu);
void tracing_reset_all_online_cpus(void);
int tracing_open_generic(struct inode *inode, struct file *filp);
+int tracing_open_generic_tr(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index a41fed46c285..89779eb84a07 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -174,6 +174,10 @@ static int dyn_event_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = tracing_check_open_get_tr(NULL);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(NULL);
if (ret < 0)
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0892e38ed6fb..a9dfa04ffa44 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -272,9 +272,11 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
goto out;
}
+ mutex_lock(&event_mutex);
ret = perf_trace_event_init(tp_event, p_event);
if (ret)
destroy_local_trace_kprobe(tp_event);
+ mutex_unlock(&event_mutex);
out:
kfree(func);
return ret;
@@ -282,8 +284,10 @@ out:
void perf_kprobe_destroy(struct perf_event *p_event)
{
+ mutex_lock(&event_mutex);
perf_trace_event_close(p_event);
perf_trace_event_unreg(p_event);
+ mutex_unlock(&event_mutex);
destroy_local_trace_kprobe(p_event->tp_event);
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b89cdfe20bc1..fba87d10f0c1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -12,6 +12,7 @@
#define pr_fmt(fmt) fmt
#include <linux/workqueue.h>
+#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/tracefs.h>
@@ -1294,6 +1295,8 @@ static int trace_format_open(struct inode *inode, struct file *file)
struct seq_file *m;
int ret;
+ /* Do we want to hide event format files on tracefs lockdown? */
+
ret = seq_open(file, &trace_format_seq_ops);
if (ret < 0)
return ret;
@@ -1440,28 +1443,17 @@ static int system_tr_open(struct inode *inode, struct file *filp)
struct trace_array *tr = inode->i_private;
int ret;
- if (tracing_is_disabled())
- return -ENODEV;
-
- if (trace_array_get(tr) < 0)
- return -ENODEV;
-
/* Make a temporary dir that has no system but points to tr */
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
- if (!dir) {
- trace_array_put(tr);
+ if (!dir)
return -ENOMEM;
- }
- dir->tr = tr;
-
- ret = tracing_open_generic(inode, filp);
+ ret = tracing_open_generic_tr(inode, filp);
if (ret < 0) {
- trace_array_put(tr);
kfree(dir);
return ret;
}
-
+ dir->tr = tr;
filp->private_data = dir;
return 0;
@@ -1771,6 +1763,10 @@ ftrace_event_open(struct inode *inode, struct file *file,
struct seq_file *m;
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
ret = seq_open(file, seq_ops);
if (ret < 0)
return ret;
@@ -1795,6 +1791,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file)
{
const struct seq_operations *seq_ops = &show_event_seq_ops;
+ /* Checks for tracefs lockdown */
return ftrace_event_open(inode, file, seq_ops);
}
@@ -1805,8 +1802,9 @@ ftrace_event_set_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
@@ -1825,8 +1823,9 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file)
struct trace_array *tr = inode->i_private;
int ret;
- if (trace_array_get(tr) < 0)
- return -ENODEV;
+ ret = tracing_check_open_get_tr(tr);
+ if (ret)
+ return ret;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 9468bd8d44a2..7482a1466ebf 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -7,6 +7,7 @@
#include <linux/module.h>
#include <linux/kallsyms.h>
+#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/stacktrace.h>
@@ -678,6 +679,8 @@ static bool synth_field_signed(char *type)
{
if (str_has_prefix(type, "u"))
return false;
+ if (strcmp(type, "gfp_t") == 0)
+ return false;
return true;
}
@@ -1448,6 +1451,10 @@ static int synth_events_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&synth_event_ops);
if (ret < 0)
@@ -1680,7 +1687,7 @@ static int save_hist_vars(struct hist_trigger_data *hist_data)
if (var_data)
return 0;
- if (trace_array_get(tr) < 0)
+ if (tracing_check_open_get_tr(tr))
return -ENODEV;
var_data = kzalloc(sizeof(*var_data), GFP_KERNEL);
@@ -5515,6 +5522,12 @@ static int hist_show(struct seq_file *m, void *v)
static int event_hist_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return single_open(file, hist_show, file);
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2a2912cb4533..2cd53ca21b51 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -5,6 +5,7 @@
* Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
*/
+#include <linux/security.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
@@ -173,7 +174,11 @@ static const struct seq_operations event_triggers_seq_ops = {
static int event_trigger_regex_open(struct inode *inode, struct file *file)
{
- int ret = 0;
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
mutex_lock(&event_mutex);
@@ -292,6 +297,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf,
static int
event_trigger_open(struct inode *inode, struct file *filp)
{
+ /* Checks for tracefs lockdown */
return event_trigger_regex_open(inode, filp);
}
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index fa95139445b2..862f4b0139fc 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -150,7 +150,7 @@ void trace_hwlat_callback(bool enter)
if (enter)
nmi_ts_start = time_get();
else
- nmi_total_ts = time_get() - nmi_ts_start;
+ nmi_total_ts += time_get() - nmi_ts_start;
}
if (enter)
@@ -256,6 +256,8 @@ static int get_sample(void)
/* Keep a running maximum ever recorded hardware latency */
if (sample > tr->max_latency)
tr->max_latency = sample;
+ if (outer_sample > tr->max_latency)
+ tr->max_latency = outer_sample;
}
out:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 324ffbea3556..1552a95c743b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,11 +7,11 @@
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
+#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/rculist.h>
#include <linux/error-injection.h>
-#include <linux/security.h>
#include <asm/setup.h> /* for COMMAND_LINE_SIZE */
@@ -936,6 +936,10 @@ static int probes_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&trace_kprobe_ops);
if (ret < 0)
@@ -988,6 +992,12 @@ static const struct seq_operations profile_seq_op = {
static int profile_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &profile_seq_op);
}
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index c3fd849d4a8f..d4e31e969206 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -6,6 +6,7 @@
*
*/
#include <linux/seq_file.h>
+#include <linux/security.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
@@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = {
static int
ftrace_formats_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &show_format_seq_ops);
}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index ec9a34a97129..4df9a209f7ca 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -5,6 +5,7 @@
*/
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
+#include <linux/security.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
@@ -470,6 +471,12 @@ static const struct seq_operations stack_trace_seq_ops = {
static int stack_trace_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &stack_trace_seq_ops);
}
@@ -487,6 +494,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file)
{
struct ftrace_ops *ops = inode->i_private;
+ /* Checks for tracefs lockdown */
return ftrace_regex_open(ops, FTRACE_ITER_FILTER,
inode, file);
}
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75bf1bcb4a8a..9ab0a1a7ad5e 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -9,7 +9,7 @@
*
*/
-
+#include <linux/security.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
@@ -238,6 +238,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
struct seq_file *m;
struct stat_session *session = inode->i_private;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
ret = stat_seq_init(session);
if (ret)
return ret;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index dd884341f5c5..352073d36585 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
*/
#define pr_fmt(fmt) "trace_uprobe: " fmt
+#include <linux/security.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/uaccess.h>
@@ -769,6 +770,10 @@ static int probes_open(struct inode *inode, struct file *file)
{
int ret;
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
ret = dyn_events_release_all(&trace_uprobe_ops);
if (ret)
@@ -818,6 +823,12 @@ static const struct seq_operations profile_seq_op = {
static int profile_open(struct inode *inode, struct file *file)
{
+ int ret;
+
+ ret = security_locked_down(LOCKDOWN_TRACEFS);
+ if (ret)
+ return ret;
+
return seq_open(file, &profile_seq_op);
}