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/bpf/sysfs_btf.c6
-rw-r--r--kernel/bpf/verifier.c8
-rw-r--r--kernel/events/core.c5
-rw-r--r--kernel/fork.c3
-rw-r--r--kernel/kprobes.c27
-rw-r--r--kernel/rcu/tree.c2
-rw-r--r--kernel/trace/ftrace.c9
-rw-r--r--kernel/trace/trace.c48
-rw-r--r--kernel/trace/trace_events_hist.c1
-rw-r--r--kernel/trace/trace_output.c12
-rw-r--r--kernel/umh.c9
13 files changed, 91 insertions, 58 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/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index 3b495773de5a..11b3380887fa 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -30,15 +30,15 @@ static struct kobject *btf_kobj;
static int __init btf_vmlinux_init(void)
{
- if (!__start_BTF)
+ bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
+
+ if (!__start_BTF || bin_attr_btf_vmlinux.size == 0)
return 0;
btf_kobj = kobject_create_and_add("btf", kernel_kobj);
if (!btf_kobj)
return -ENOMEM;
- bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
-
return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux);
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 47e74f09fa37..fba52d9ec8fc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5667,8 +5667,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
bool src_known = tnum_subreg_is_const(src_reg->var_off);
bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
struct tnum var32_off = tnum_subreg(dst_reg->var_off);
- s32 smin_val = src_reg->smin_value;
- u32 umin_val = src_reg->umin_value;
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;
/* Assuming scalar64_min_max_or will be called so it is safe
* to skip updating register for known case.
@@ -5691,8 +5691,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
/* ORing two positives gives a positive, so safe to
* cast result into s64.
*/
- dst_reg->s32_min_value = dst_reg->umin_value;
- dst_reg->s32_max_value = dst_reg->umax_value;
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
}
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7ed5248f0445..e8bf92202542 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -99,7 +99,7 @@ static void remote_function(void *data)
* retry due to any failures in smp_call_function_single(), such as if the
* task_cpu() goes offline concurrently.
*
- * returns @func return value or -ESRCH when the process isn't running
+ * returns @func return value or -ESRCH or -ENXIO when the process isn't running
*/
static int
task_function_call(struct task_struct *p, remote_function_f func, void *info)
@@ -115,7 +115,8 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
for (;;) {
ret = smp_call_function_single(task_cpu(p), remote_function,
&data, 1);
- ret = !ret ? data.ret : -EAGAIN;
+ if (!ret)
+ ret = data.ret;
if (ret != -EAGAIN)
break;
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 049da84e1952..e995541d277d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2162,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p)
/*
* The module is going away. We should disarm the kprobe which
- * is using ftrace.
+ * is using ftrace, because ftrace framework is still available at
+ * MODULE_STATE_GOING notification.
*/
- if (kprobe_ftrace(p))
+ if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
disarm_kprobe_ftrace(p);
}
@@ -2459,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = {
extern unsigned long __start_kprobe_blacklist[];
extern unsigned long __stop_kprobe_blacklist[];
+void kprobe_free_init_mem(void)
+{
+ void *start = (void *)(&__init_begin);
+ void *end = (void *)(&__init_end);
+ struct hlist_head *head;
+ struct kprobe *p;
+ int i;
+
+ mutex_lock(&kprobe_mutex);
+
+ /* Kill all kprobes on initmem */
+ for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+ head = &kprobe_table[i];
+ hlist_for_each_entry(p, head, hlist) {
+ if (start <= (void *)p->addr && (void *)p->addr < end)
+ kill_kprobe(p);
+ }
+ }
+
+ mutex_unlock(&kprobe_mutex);
+}
+
static int __init init_kprobes(void)
{
int i, err = 0;
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/trace/ftrace.c b/kernel/trace/ftrace.c
index e9fa580f3083..541453927c82 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
{
lockdep_assert_held(&ftrace_lock);
list_del_rcu(&ops->list);
+ synchronize_rcu();
}
/*
@@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
__unregister_ftrace_function(ops);
ftrace_start_up--;
ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+ if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+ ftrace_trampoline_free(ops);
return ret;
}
@@ -6990,16 +6993,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
{
int bit;
- if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
- return;
-
bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
if (bit < 0)
return;
preempt_disable_notrace();
- op->func(ip, parent_ip, op, regs);
+ if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
+ op->func(ip, parent_ip, op, regs);
preempt_enable_notrace();
trace_clear_recursion(bit);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..d3e5de717df2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3546,13 +3546,15 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
if (iter->ent && iter->ent != iter->temp) {
if ((!iter->temp || iter->temp_size < iter->ent_size) &&
!WARN_ON_ONCE(iter->temp == static_temp_buf)) {
- kfree(iter->temp);
- iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
- if (!iter->temp)
+ void *temp;
+ temp = kmalloc(iter->ent_size, GFP_KERNEL);
+ if (!temp)
return NULL;
+ kfree(iter->temp);
+ iter->temp = temp;
+ iter->temp_size = iter->ent_size;
}
memcpy(iter->temp, iter->ent, iter->ent_size);
- iter->temp_size = iter->ent_size;
iter->ent = iter->temp;
}
entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
@@ -3782,14 +3784,14 @@ unsigned long trace_total_entries(struct trace_array *tr)
static void print_lat_help_header(struct seq_file *m)
{
- seq_puts(m, "# _------=> CPU# \n"
- "# / _-----=> irqs-off \n"
- "# | / _----=> need-resched \n"
- "# || / _---=> hardirq/softirq \n"
- "# ||| / _--=> preempt-depth \n"
- "# |||| / delay \n"
- "# cmd pid ||||| time | caller \n"
- "# \\ / ||||| \\ | / \n");
+ seq_puts(m, "# _------=> CPU# \n"
+ "# / _-----=> irqs-off \n"
+ "# | / _----=> need-resched \n"
+ "# || / _---=> hardirq/softirq \n"
+ "# ||| / _--=> preempt-depth \n"
+ "# |||| / delay \n"
+ "# cmd pid ||||| time | caller \n"
+ "# \\ / ||||| \\ | / \n");
}
static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -3810,26 +3812,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m,
print_event_info(buf, m);
- seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
- seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
+ seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : "");
+ seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
}
static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m,
unsigned int flags)
{
bool tgid = flags & TRACE_ITER_RECORD_TGID;
- const char *space = " ";
- int prec = tgid ? 10 : 2;
+ const char *space = " ";
+ int prec = tgid ? 12 : 2;
print_event_info(buf, m);
- seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space);
- seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space);
- seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space);
- seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space);
- seq_printf(m, "# %.*s||| / delay\n", prec, space);
- seq_printf(m, "# TASK-PID %.*sCPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID ");
- seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | ");
+ seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space);
+ seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space);
+ seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space);
+ seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space);
+ seq_printf(m, "# %.*s||| / delay\n", prec, space);
+ seq_printf(m, "# TASK-PID %.*s CPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID ");
+ seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | ");
}
void
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0b933546142e..1b2ef6490229 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
s = kstrdup(field_str, GFP_KERNEL);
if (!s) {
- kfree(hist_data->attrs->var_defs.name[n_vars]);
ret = -ENOMEM;
goto free;
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 4d1893564912..000e9dc224c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%8.8s-%-5d %3d",
+ trace_seq_printf(s, "%8.8s-%-7d %3d",
comm, entry->pid, cpu);
return trace_print_lat_fmt(s, entry);
@@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter)
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+ trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
if (!tgid)
- trace_seq_printf(s, "(-----) ");
+ trace_seq_printf(s, "(-------) ");
else
- trace_seq_printf(s, "(%5d) ", tgid);
+ trace_seq_printf(s, "(%7d) ", tgid);
}
trace_seq_printf(s, "[%03d] ", iter->cpu);
@@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
trace_find_cmdline(entry->pid, comm);
trace_seq_printf(
- s, "%16s %5d %3d %d %08x %08lx ",
+ s, "%16s %7d %3d %d %08x %08lx ",
comm, entry->pid, iter->cpu, entry->flags,
entry->preempt_count, iter->idx);
} else {
@@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
S = task_index_to_char(field->prev_state);
trace_find_cmdline(field->next_pid, comm);
trace_seq_printf(&iter->seq,
- " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+ " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
field->prev_pid,
field->prev_prio,
S, delim,
diff --git a/kernel/umh.c b/kernel/umh.c
index fcf3ee803630..3f646613a9d3 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -14,6 +14,7 @@
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+#include <linux/fs_struct.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/mount.h>
@@ -72,6 +73,14 @@ static int call_usermodehelper_exec_async(void *data)
spin_unlock_irq(&current->sighand->siglock);
/*
+ * Initial kernel threads share ther FS with init, in order to
+ * get the init root directory. But we've now created a new
+ * thread that is going to execve a user process and has its own
+ * 'struct fs_struct'. Reset umask to the default.
+ */
+ current->fs->umask = 0022;
+
+ /*
* Our parent (unbound workqueue) runs with elevated scheduling
* priority. Avoid propagating that into the userspace child.
*/
generated by cgit (git 2.34.1) at 2024-06-11 04:42:51 +0000