summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c17
-rw-r--r--kernel/audit.h4
-rw-r--r--kernel/auditsc.c8
-rw-r--r--kernel/bpf/verifier.c41
-rw-r--r--kernel/cgroup.c148
-rw-r--r--kernel/cpu.c2
-rw-r--r--kernel/events/core.c25
-rw-r--r--kernel/gcov/gcc_4_7.c2
-rw-r--r--kernel/sched/core.c6
-rw-r--r--kernel/sched/fair.c42
-rw-r--r--kernel/sched/loadavg.c8
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/time/posix-cpu-timers.c1
-rw-r--r--kernel/trace/bpf_trace.c10
-rw-r--r--kernel/workqueue.c6
15 files changed, 173 insertions, 149 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 22bb4f24f071..8d528f9930da 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1883,6 +1883,23 @@ out_null:
audit_log_format(ab, " exe=(null)");
}
+struct tty_struct *audit_get_tty(struct task_struct *tsk)
+{
+ struct tty_struct *tty = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&tsk->sighand->siglock, flags);
+ if (tsk->signal)
+ tty = tty_kref_get(tsk->signal->tty);
+ spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+ return tty;
+}
+
+void audit_put_tty(struct tty_struct *tty)
+{
+ tty_kref_put(tty);
+}
+
void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
diff --git a/kernel/audit.h b/kernel/audit.h
index cbbe6bb6496e..a492f4c4e710 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -23,6 +23,7 @@
#include <linux/audit.h>
#include <linux/skbuff.h>
#include <uapi/linux/mqueue.h>
+#include <linux/tty.h>
/* AUDIT_NAMES is the number of slots we reserve in the audit_context
* for saving names from getname(). If we get more names we will allocate
@@ -262,6 +263,9 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
extern void audit_log_d_path_exe(struct audit_buffer *ab,
struct mm_struct *mm);
+extern struct tty_struct *audit_get_tty(struct task_struct *tsk);
+extern void audit_put_tty(struct tty_struct *tty);
+
/* audit watch functions */
#ifdef CONFIG_AUDIT_WATCH
extern void audit_put_watch(struct audit_watch *watch);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 62ab53d7619c..2672d105cffc 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -63,7 +63,6 @@
#include <asm/unistd.h>
#include <linux/security.h>
#include <linux/list.h>
-#include <linux/tty.h>
#include <linux/binfmts.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
@@ -1985,14 +1984,15 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
if (!audit_enabled)
return;
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+ if (!ab)
+ return;
+
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid),
tty = audit_get_tty(current);
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
- if (!ab)
- return;
audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid);
audit_log_task_context(ab);
audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d",
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 668e07903c8f..eec9f90ba030 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -126,31 +126,6 @@
* are set to NOT_INIT to indicate that they are no longer readable.
*/
-/* types of values stored in eBPF registers */
-enum bpf_reg_type {
- NOT_INIT = 0, /* nothing was written into register */
- UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
- PTR_TO_CTX, /* reg points to bpf_context */
- CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
- PTR_TO_MAP_VALUE, /* reg points to map element value */
- PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
- FRAME_PTR, /* reg == frame_pointer */
- PTR_TO_STACK, /* reg == frame_pointer + imm */
- CONST_IMM, /* constant integer value */
-
- /* PTR_TO_PACKET represents:
- * skb->data
- * skb->data + imm
- * skb->data + (u16) var
- * skb->data + (u16) var + imm
- * if (range > 0) then [ptr, ptr + range - off) is safe to access
- * if (id > 0) means that some 'var' was added
- * if (off > 0) menas that 'imm' was added
- */
- PTR_TO_PACKET,
- PTR_TO_PACKET_END, /* skb->data + headlen */
-};
-
struct reg_state {
enum bpf_reg_type type;
union {
@@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off,
/* check access to 'struct bpf_context' fields */
static int check_ctx_access(struct verifier_env *env, int off, int size,
- enum bpf_access_type t)
+ enum bpf_access_type t, enum bpf_reg_type *reg_type)
{
if (env->prog->aux->ops->is_valid_access &&
- env->prog->aux->ops->is_valid_access(off, size, t)) {
+ env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
@@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
mark_reg_unknown_value(state->regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
+ enum bpf_reg_type reg_type = UNKNOWN_VALUE;
+
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose("R%d leaks addr into ctx\n", value_regno);
return -EACCES;
}
- err = check_ctx_access(env, off, size, t);
+ err = check_ctx_access(env, off, size, t, &reg_type);
if (!err && t == BPF_READ && value_regno >= 0) {
mark_reg_unknown_value(state->regs, value_regno);
- if (off == offsetof(struct __sk_buff, data) &&
- env->allow_ptr_leaks)
+ if (env->allow_ptr_leaks)
/* note that reg.[id|off|range] == 0 */
- state->regs[value_regno].type = PTR_TO_PACKET;
- else if (off == offsetof(struct __sk_buff, data_end) &&
- env->allow_ptr_leaks)
- state->regs[value_regno].type = PTR_TO_PACKET_END;
+ state->regs[value_regno].type = reg_type;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 86cb5c6e8932..75c0ff00aca6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -837,6 +837,8 @@ static void put_css_set_locked(struct css_set *cset)
static void put_css_set(struct css_set *cset)
{
+ unsigned long flags;
+
/*
* Ensure that the refcount doesn't hit zero while any readers
* can see it. Similar to atomic_dec_and_lock(), but for an
@@ -845,9 +847,9 @@ static void put_css_set(struct css_set *cset)
if (atomic_add_unless(&cset->refcount, -1, 1))
return;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, flags);
put_css_set_locked(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, flags);
}
/*
@@ -1070,11 +1072,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
/* First see if we already have a cgroup group that matches
* the desired set */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (cset)
return cset;
@@ -1102,7 +1104,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
* find_existing_css_set() */
memcpy(cset->subsys, template, sizeof(cset->subsys));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
/* Add reference counts and links from the new css_set. */
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
@@ -1128,7 +1130,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
css_get(css);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cset;
}
@@ -1192,7 +1194,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
* Release all the links from cset_links to this hierarchy's
* root cgroup
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
list_del(&link->cset_link);
@@ -1200,7 +1202,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
kfree(link);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
@@ -1600,11 +1602,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
ss->root = dst_root;
css->cgroup = dcgrp;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist)
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* default hierarchy doesn't enable controllers by default */
dst_root->subsys_mask |= 1 << ssid;
@@ -1640,10 +1642,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
if (!buf)
return -ENOMEM;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot);
len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (len >= PATH_MAX)
len = -ERANGE;
@@ -1897,7 +1899,7 @@ static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (use_task_css_set_links)
goto out_unlock;
@@ -1922,8 +1924,12 @@ static void cgroup_enable_task_cg_lists(void)
* entry won't be deleted though the process has exited.
* Do it while holding siglock so that we don't end up
* racing against cgroup_exit().
+ *
+ * Interrupts were already disabled while acquiring
+ * the css_set_lock, so we do not need to disable it
+ * again when acquiring the sighand->siglock here.
*/
- spin_lock_irq(&p->sighand->siglock);
+ spin_lock(&p->sighand->siglock);
if (!(p->flags & PF_EXITING)) {
struct css_set *cset = task_css_set(p);
@@ -1932,11 +1938,11 @@ static void cgroup_enable_task_cg_lists(void)
list_add_tail(&p->cg_list, &cset->tasks);
get_css_set(cset);
}
- spin_unlock_irq(&p->sighand->siglock);
+ spin_unlock(&p->sighand->siglock);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -2043,13 +2049,13 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
* Link the root cgroup in this hierarchy into all the css_set
* objects.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist) {
link_css_set(&tmp_links, cset, root_cgrp);
if (css_set_populated(cset))
cgroup_update_populated(root_cgrp, true);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->self.children));
BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2256,11 +2262,11 @@ out_mount:
struct cgroup *cgrp;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgrp = cset_cgroup_from_root(ns->root_cset, root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
@@ -2337,11 +2343,11 @@ char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
char *ret;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
return ret;
@@ -2369,7 +2375,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
char *path = NULL;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
@@ -2382,7 +2388,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
path = buf;
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
return path;
}
@@ -2557,7 +2563,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
* the new cgroup. There are no failure cases after here, so this
* is the commit point.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(cset, &tset->src_csets, mg_node) {
list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
struct css_set *from_cset = task_css_set(task);
@@ -2568,7 +2574,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
put_css_set_locked(from_cset);
}
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/*
* Migration is committed, all target tasks are now on dst_csets.
@@ -2597,13 +2603,13 @@ out_cancel_attach:
}
} while_each_subsys_mask();
out_release_tset:
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_splice_init(&tset->dst_csets, &tset->src_csets);
list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
list_del_init(&cset->mg_node);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return ret;
}
@@ -2634,7 +2640,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
lockdep_assert_held(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
@@ -2642,7 +2648,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
list_del_init(&cset->mg_preload_node);
put_css_set_locked(cset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -2783,7 +2789,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2792,7 +2798,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cgroup_taskset_migrate(&tset, root);
}
@@ -2816,7 +2822,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
return -EBUSY;
/* look up all src csets */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2826,7 +2832,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* prepare dst csets and commit */
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
@@ -2859,9 +2865,9 @@ static int cgroup_procs_write_permission(struct task_struct *task,
struct cgroup *cgrp;
struct inode *inode;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
while (!cgroup_is_descendant(dst_cgrp, cgrp))
cgrp = cgroup_parent(cgrp);
@@ -2962,9 +2968,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
if (root == &cgrp_dfl_root)
continue;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
from_cgrp = task_cgroup_from_root(from, root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
retval = cgroup_attach_task(from_cgrp, tsk, false);
if (retval)
@@ -3080,7 +3086,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
percpu_down_write(&cgroup_threadgroup_rwsem);
/* look up all csses currently attached to @cgrp's subtree */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
struct cgrp_cset_link *link;
@@ -3088,14 +3094,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
cgroup_migrate_add_src(link->cset, dsct,
&preloaded_csets);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
if (ret)
goto out_finish;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
struct task_struct *task, *ntask;
@@ -3107,7 +3113,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
cgroup_taskset_add(task, &tset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_taskset_migrate(&tset, cgrp->root);
out_finish:
@@ -3908,10 +3914,10 @@ static int cgroup_task_count(const struct cgroup *cgrp)
int count = 0;
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += atomic_read(&link->cset->refcount);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return count;
}
@@ -4249,7 +4255,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
memset(it, 0, sizeof(*it));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
it->ss = css->ss;
@@ -4262,7 +4268,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
css_task_iter_advance_css_set(it);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -4280,7 +4286,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
it->cur_task = NULL;
}
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (it->task_pos) {
it->cur_task = list_entry(it->task_pos, struct task_struct,
@@ -4289,7 +4295,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
css_task_iter_advance(it);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return it->cur_task;
}
@@ -4303,10 +4309,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
void css_task_iter_end(struct css_task_iter *it)
{
if (it->cur_cset) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
if (it->cur_task)
@@ -4338,10 +4344,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
mutex_lock(&cgroup_mutex);
/* all tasks in @from are being moved, all csets are source */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &from->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_prepare_dst(&preloaded_csets);
if (ret)
@@ -5063,6 +5069,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
css->ss = ss;
+ css->id = -1;
INIT_LIST_HEAD(&css->sibling);
INIT_LIST_HEAD(&css->children);
css->serial_nr = css_serial_nr_next++;
@@ -5150,7 +5157,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL);
if (err < 0)
- goto err_free_percpu_ref;
+ goto err_free_css;
css->id = err;
/* @css is ready to be brought online now, make it visible */
@@ -5174,9 +5181,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
err_list_del:
list_del_rcu(&css->sibling);
- cgroup_idr_remove(&ss->css_idr, css->id);
-err_free_percpu_ref:
- percpu_ref_exit(&css->refcnt);
err_free_css:
call_rcu(&css->rcu_head, css_free_rcu_fn);
return ERR_PTR(err);
@@ -5451,10 +5455,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
*/
cgrp->self.flags &= ~CSS_ONLINE;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
link->cset->dead = true;
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* initiate massacre of all css's */
for_each_css(css, ssid, cgrp)
@@ -5725,7 +5729,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
goto out;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
for_each_root(root) {
struct cgroup_subsys *ss;
@@ -5778,7 +5782,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
retval = 0;
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
kfree(buf);
out:
@@ -5923,13 +5927,13 @@ void cgroup_post_fork(struct task_struct *child)
if (use_task_css_set_links) {
struct css_set *cset;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
if (list_empty(&child->cg_list)) {
get_css_set(cset);
css_set_move_task(child, NULL, cset, false);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/*
@@ -5974,9 +5978,9 @@ void cgroup_exit(struct task_struct *tsk)
cset = task_css_set(tsk);
if (!list_empty(&tsk->cg_list)) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
css_set_move_task(tsk, cset, NULL, false);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
} else {
get_css_set(cset);
}
@@ -6044,9 +6048,9 @@ static void cgroup_release_agent(struct work_struct *work)
if (!pathbuf || !agentbuf)
goto out;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (!path)
goto out;
@@ -6306,12 +6310,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
return ERR_PTR(-EPERM);
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
get_css_set(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
new_ns = alloc_cgroup_ns();
@@ -6435,7 +6439,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
if (!name_buf)
return -ENOMEM;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
@@ -6446,7 +6450,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
kfree(name_buf);
return 0;
}
@@ -6457,7 +6461,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
@@ -6480,7 +6484,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
overflow:
seq_puts(seq, " ...\n");
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return 0;
}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d948e44c471e..7b61887f7ccd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1201,6 +1201,8 @@ static struct cpuhp_step cpuhp_bp_states[] = {
.teardown = takedown_cpu,
.cant_stop = true,
},
+#else
+ [CPUHP_BRINGUP_CPU] = { },
#endif
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9c51ec3f0f44..43d43a2d5811 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1678,12 +1678,33 @@ static bool is_orphaned_event(struct perf_event *event)
return event->state == PERF_EVENT_STATE_DEAD;
}
-static inline int pmu_filter_match(struct perf_event *event)
+static inline int __pmu_filter_match(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
return pmu->filter_match ? pmu->filter_match(event) : 1;
}
+/*
+ * Check whether we should attempt to schedule an event group based on
+ * PMU-specific filtering. An event group can consist of HW and SW events,
+ * potentially with a SW leader, so we must check all the filters, to
+ * determine whether a group is schedulable:
+ */
+static inline int pmu_filter_match(struct perf_event *event)
+{
+ struct perf_event *child;
+
+ if (!__pmu_filter_match(event))
+ return 0;
+
+ list_for_each_entry(child, &event->sibling_list, group_entry) {
+ if (!__pmu_filter_match(child))
+ return 0;
+ }
+
+ return 1;
+}
+
static inline int
event_filter_match(struct perf_event *event)
{
@@ -7529,7 +7550,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
prog = event->tp_event->prog;
if (prog) {
event->tp_event->prog = NULL;
- bpf_prog_put(prog);
+ bpf_prog_put_rcu(prog);
}
}
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index e25e92fb44fa..6a5c239c7669 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,7 @@
#include <linux/vmalloc.h>
#include "gcov.h"
-#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#if (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
#define GCOV_COUNTERS 10
#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
#define GCOV_COUNTERS 9
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51d7105f529a..97ee9ac7e97c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5394,13 +5394,15 @@ void idle_task_exit(void)
/*
* Since this CPU is going 'away' for a while, fold any nr_active delta
* we might have. Assumes we're called after migrate_tasks() so that the
- * nr_active count is stable.
+ * nr_active count is stable. We need to take the teardown thread which
+ * is calling this into account, so we hand in adjust = 1 to the load
+ * calculation.
*
* Also see the comment "Global load-average calculations".
*/
static void calc_load_migrate(struct rq *rq)
{
- long delta = calc_load_fold_active(rq);
+ long delta = calc_load_fold_active(rq, 1);
if (delta)
atomic_long_add(delta, &calc_load_tasks);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bdcbeea90c95..c8c5d2d48424 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -735,8 +735,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
}
}
-static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
-static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
#else
void init_entity_runnable_average(struct sched_entity *se)
{
@@ -2499,28 +2497,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
-static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
- long tg_weight;
+ long tg_weight, load, shares;
/*
- * Use this CPU's real-time load instead of the last load contribution
- * as the updating of the contribution is delayed, and we will use the
- * the real-time load to calc the share. See update_tg_load_avg().
+ * This really should be: cfs_rq->avg.load_avg, but instead we use
+ * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+ * the shares for small weight interactive tasks.
*/
- tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight -= cfs_rq->tg_load_avg_contrib;
- tg_weight += cfs_rq->load.weight;
+ load = scale_load_down(cfs_rq->load.weight);
- return tg_weight;
-}
-
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
- long tg_weight, load, shares;
+ tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight = calc_tg_weight(tg, cfs_rq);
- load = cfs_rq->load.weight;
+ /* Ensure tg_weight >= load */
+ tg_weight -= cfs_rq->tg_load_avg_contrib;
+ tg_weight += load;
shares = (tg->shares * load);
if (tg_weight)
@@ -2539,6 +2531,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
return tg->shares;
}
# endif /* CONFIG_SMP */
+
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
@@ -4946,19 +4939,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
return wl;
for_each_sched_entity(se) {
- long w, W;
+ struct cfs_rq *cfs_rq = se->my_q;
+ long W, w = cfs_rq_load_avg(cfs_rq);
- tg = se->my_q->tg;
+ tg = cfs_rq->tg;
/*
* W = @wg + \Sum rw_j
*/
- W = wg + calc_tg_weight(tg, se->my_q);
+ W = wg + atomic_long_read(&tg->load_avg);
+
+ /* Ensure \Sum rw_j >= rw_i */
+ W -= cfs_rq->tg_load_avg_contrib;
+ W += w;
/*
* w = rw_i + @wl
*/
- w = cfs_rq_load_avg(se->my_q) + wl;
+ w += wl;
/*
* wl = S * s'_i; see (2)
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index b0b93fd33af9..a2d6eb71f06b 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -78,11 +78,11 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
loads[2] = (avenrun[2] + offset) << shift;
}
-long calc_load_fold_active(struct rq *this_rq)
+long calc_load_fold_active(struct rq *this_rq, long adjust)
{
long nr_active, delta = 0;
- nr_active = this_rq->nr_running;
+ nr_active = this_rq->nr_running - adjust;
nr_active += (long)this_rq->nr_uninterruptible;
if (nr_active != this_rq->calc_load_active) {
@@ -188,7 +188,7 @@ void calc_load_enter_idle(void)
* We're going into NOHZ mode, if there's any pending delta, fold it
* into the pending idle delta.
*/
- delta = calc_load_fold_active(this_rq);
+ delta = calc_load_fold_active(this_rq, 0);
if (delta) {
int idx = calc_load_write_idx();
@@ -389,7 +389,7 @@ void calc_global_load_tick(struct rq *this_rq)
if (time_before(jiffies, this_rq->calc_load_update))
return;
- delta = calc_load_fold_active(this_rq);
+ delta = calc_load_fold_active(this_rq, 0);
if (delta)
atomic_long_add(delta, &calc_load_tasks);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7cbeb92a1cb9..898c0d2f18fe 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -28,7 +28,7 @@ extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;
extern void calc_global_load_tick(struct rq *this_rq);
-extern long calc_load_fold_active(struct rq *this_rq);
+extern long calc_load_fold_active(struct rq *this_rq, long adjust);
#ifdef CONFIG_SMP
extern void cpu_load_update_active(struct rq *this_rq);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 1cafba860b08..39008d78927a 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -777,6 +777,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
timer->it.cpu.expires = 0;
sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
&itp->it_value);
+ return;
} else {
cpu_timer_sample_group(timer->it_clock, p, &now);
unlock_task_sighand(p, &flags);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 720b7bb01d43..26f603da7e26 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -209,6 +209,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
event->pmu->count)
return -EINVAL;
+ if (unlikely(event->attr.type != PERF_TYPE_HARDWARE &&
+ event->attr.type != PERF_TYPE_RAW))
+ return -EINVAL;
+
/*
* we don't know if the function is run successfully by the
* return value. It can be judged in other places, such as
@@ -349,7 +353,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
}
/* bpf+kprobe programs can access fields of 'struct pt_regs' */
-static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
/* check bounds */
if (off < 0 || off >= sizeof(struct pt_regs))
@@ -427,7 +432,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
}
}
-static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
+ enum bpf_reg_type *reg_type)
{
if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
return false;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e1c0e996b5ae..97e7b793df35 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4600,15 +4600,11 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
return;
- /* is @cpu the only online CPU? */
cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask);
- if (cpumask_weight(&cpumask) != 1)
- return;
/* as we're called from CPU_ONLINE, the following shouldn't fail */
for_each_pool_worker(worker, pool)
- WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
- pool->attrs->cpumask) < 0);
+ WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0);
}
/*
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-25 17:14:32 +0000