summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/hashtab.c15
-rw-r--r--kernel/bpf/inode.c4
-rw-r--r--kernel/entry/common.c6
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/kprobes.c9
-rw-r--r--kernel/locking/lockdep.c35
-rw-r--r--kernel/locking/lockdep_internals.h2
-rw-r--r--kernel/locking/percpu-rwsem.c4
-rw-r--r--kernel/rcu/tasks.h2
-rw-r--r--kernel/rcu/tree.c2
-rw-r--r--kernel/stackleak.c2
-rw-r--r--kernel/sysctl.c8
-rw-r--r--kernel/trace/trace_preemptirq.c4
13 files changed, 68 insertions, 28 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 78dfff6a501b..7df28a45c66b 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info {
struct bpf_map *map;
struct bpf_htab *htab;
void *percpu_value_buf; // non-zero means percpu hash
- unsigned long flags;
u32 bucket_id;
u32 skip_elems;
};
@@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
struct htab_elem *prev_elem)
{
const struct bpf_htab *htab = info->htab;
- unsigned long flags = info->flags;
u32 skip_elems = info->skip_elems;
u32 bucket_id = info->bucket_id;
struct hlist_nulls_head *head;
@@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
/* not found, unlock and go to the next bucket */
b = &htab->buckets[bucket_id++];
- htab_unlock_bucket(htab, b, flags);
+ rcu_read_unlock();
skip_elems = 0;
}
for (i = bucket_id; i < htab->n_buckets; i++) {
b = &htab->buckets[i];
- flags = htab_lock_bucket(htab, b);
+ rcu_read_lock();
count = 0;
head = &b->head;
hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
if (count >= skip_elems) {
- info->flags = flags;
info->bucket_id = i;
info->skip_elems = count;
return elem;
@@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
count++;
}
- htab_unlock_bucket(htab, b, flags);
+ rcu_read_unlock();
skip_elems = 0;
}
@@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v)
static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v)
{
- struct bpf_iter_seq_hash_map_info *info = seq->private;
-
if (!v)
(void)__bpf_hash_map_seq_show(seq, NULL);
else
- htab_unlock_bucket(info->htab,
- &info->htab->buckets[info->bucket_id],
- info->flags);
+ rcu_read_unlock();
}
static int bpf_iter_init_hash_map(void *priv_data,
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fb878ba3f22f..18f4969552ac 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
else
prev_key = key;
+ rcu_read_lock();
if (map->ops->map_get_next_key(map, prev_key, key)) {
map_iter(m)->done = true;
- return NULL;
+ key = NULL;
}
+ rcu_read_unlock();
return key;
}
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 18683598edbc..6fdb6105e6d6 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -60,13 +60,15 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
return ret;
}
+ /* Either of the above might have changed the syscall number */
+ syscall = syscall_get_nr(current, regs);
+
if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
trace_sys_enter(regs, syscall);
syscall_enter_audit(regs, syscall);
- /* The above might have changed the syscall number */
- return ret ? : syscall_get_nr(current, regs);
+ return ret ? : syscall;
}
static __always_inline long
diff --git a/kernel/fork.c b/kernel/fork.c
index 49677d668de4..da8d360fb032 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
- retval = copy_page_range(mm, oldmm, mpnt);
+ retval = copy_page_range(mm, oldmm, mpnt, tmp);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
@@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
+ atomic_set(&mm->has_pinned, 0);
atomic64_set(&mm->pinned_vm, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d750e025d1ff..e995541d277d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2140,6 +2140,9 @@ static void kill_kprobe(struct kprobe *p)
lockdep_assert_held(&kprobe_mutex);
+ if (WARN_ON_ONCE(kprobe_gone(p)))
+ return;
+
p->flags |= KPROBE_FLAG_GONE;
if (kprobe_aggrprobe(p)) {
/*
@@ -2420,7 +2423,10 @@ static int kprobes_module_callback(struct notifier_block *nb,
mutex_lock(&kprobe_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
- hlist_for_each_entry(p, head, hlist)
+ hlist_for_each_entry(p, head, hlist) {
+ if (kprobe_gone(p))
+ continue;
+
if (within_module_init((unsigned long)p->addr, mod) ||
(checkcore &&
within_module_core((unsigned long)p->addr, mod))) {
@@ -2437,6 +2443,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
*/
kill_kprobe(p);
}
+ }
}
if (val == MODULE_STATE_GOING)
remove_module_kprobe_blacklist(mod);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 54b74fabf40c..2facbbd146ec 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
static int mark_lock(struct task_struct *curr, struct held_lock *this,
enum lock_usage_bit new_bit)
{
- unsigned int new_mask = 1 << new_bit, ret = 1;
+ unsigned int old_mask, new_mask, ret = 1;
if (new_bit >= LOCK_USAGE_STATES) {
DEBUG_LOCKS_WARN_ON(1);
return 0;
}
+ if (new_bit == LOCK_USED && this->read)
+ new_bit = LOCK_USED_READ;
+
+ new_mask = 1 << new_bit;
+
/*
* If already set then do not dirty the cacheline,
* nor do any checks:
@@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
/*
* Make sure we didn't race:
*/
- if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
- graph_unlock();
- return 1;
- }
+ if (unlikely(hlock_class(this)->usage_mask & new_mask))
+ goto unlock;
+ old_mask = hlock_class(this)->usage_mask;
hlock_class(this)->usage_mask |= new_mask;
+ /*
+ * Save one usage_traces[] entry and map both LOCK_USED and
+ * LOCK_USED_READ onto the same entry.
+ */
+ if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+ if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+ goto unlock;
+ new_bit = LOCK_USED;
+ }
+
if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
return 0;
@@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
return 0;
}
+unlock:
graph_unlock();
/*
@@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
{
#ifdef CONFIG_PROVE_LOCKING
struct lock_class *class = look_up_lock_class(lock, subclass);
+ unsigned long mask = LOCKF_USED;
/* if it doesn't have a class (yet), it certainly hasn't been used yet */
if (!class)
return;
- if (!(class->usage_mask & LOCK_USED))
+ /*
+ * READ locks only conflict with USED, such that if we only ever use
+ * READ locks, there is no deadlock possible -- RCU.
+ */
+ if (!hlock->read)
+ mask |= LOCKF_USED_READ;
+
+ if (!(class->usage_mask & mask))
return;
hlock->class_idx = class - lock_classes;
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index baca699b94e9..b0be1560ed17 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -19,6 +19,7 @@ enum lock_usage_bit {
#include "lockdep_states.h"
#undef LOCKDEP_STATE
LOCK_USED,
+ LOCK_USED_READ,
LOCK_USAGE_STATES
};
@@ -40,6 +41,7 @@ enum {
#include "lockdep_states.h"
#undef LOCKDEP_STATE
__LOCKF(USED)
+ __LOCKF(USED_READ)
};
#define LOCKDEP_STATE(__STATE) LOCKF_ENABLED_##__STATE |
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 8bbafe3e5203..70a32a576f3f 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
{
- __this_cpu_inc(*sem->read_count);
+ this_cpu_inc(*sem->read_count);
/*
* Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
if (likely(!atomic_read_acquire(&sem->block)))
return true;
- __this_cpu_dec(*sem->read_count);
+ this_cpu_dec(*sem->read_count);
/* Prod writer to re-evaluate readers_active_check() */
rcuwait_wake_up(&sem->writer);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 835e2df8590a..05d3e1375e4c 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -590,7 +590,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
}
#else /* #ifdef CONFIG_TASKS_RCU */
-static void show_rcu_tasks_classic_gp_kthread(void) { }
+static inline void show_rcu_tasks_classic_gp_kthread(void) { }
void exit_tasks_rcu_start(void) { }
void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
#endif /* #else #ifdef CONFIG_TASKS_RCU */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8ce77d9ac716..f78ee759af9c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -673,6 +673,7 @@ void rcu_idle_enter(void)
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -886,6 +887,7 @@ void rcu_idle_exit(void)
rcu_eqs_exit(false);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
#ifdef CONFIG_NO_HZ_FULL
/**
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index a8fc9ae1d03d..ce161a8e8d97 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -20,7 +20,7 @@
static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
int stack_erasing_sysctl(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret = 0;
int state = !static_branch_unlikely(&stack_erasing_bypass);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09e70ee2332e..afad085960b8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2912,6 +2912,14 @@ static struct ctl_table vm_table[] = {
.proc_handler = percpu_pagelist_fraction_sysctl_handler,
.extra1 = SYSCTL_ZERO,
},
+ {
+ .procname = "page_lock_unfairness",
+ .data = &sysctl_page_lock_unfairness,
+ .maxlen = sizeof(sysctl_page_lock_unfairness),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
#ifdef CONFIG_MMU
{
.procname = "max_map_count",
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f10073e62603..f4938040c228 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
{
+ lockdep_hardirqs_off(CALLER_ADDR0);
+
if (!this_cpu_read(tracing_irq_cpu)) {
this_cpu_write(tracing_irq_cpu, 1);
tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
if (!in_nmi())
trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
}
-
- lockdep_hardirqs_off(CALLER_ADDR0);
}
EXPORT_SYMBOL(trace_hardirqs_off_caller);
NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
generated by cgit (git 2.34.1) at 2024-05-02 09:13:48 +0000