summaryrefslogtreecommitdiffstats
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/events/core.c8
-rw-r--r--kernel/fork.c50
-rw-r--r--kernel/futex.c14
-rw-r--r--kernel/irq/Makefile1
-rw-r--r--kernel/irq/affinity.c61
-rw-r--r--kernel/irq/internals.h2
-rw-r--r--kernel/irq/ipi.c2
-rw-r--r--kernel/irq/irqdesc.c63
-rw-r--r--kernel/irq/irqdomain.c22
-rw-r--r--kernel/irq/manage.c28
-rw-r--r--kernel/irq/msi.c11
-rw-r--r--kernel/irq/proc.c2
-rw-r--r--kernel/jump_label.c36
-rw-r--r--kernel/kcov.c7
-rw-r--r--kernel/locking/mutex-debug.c12
-rw-r--r--kernel/locking/mutex-debug.h4
-rw-r--r--kernel/locking/mutex.c15
-rw-r--r--kernel/locking/mutex.h2
-rw-r--r--kernel/locking/qspinlock.c60
-rw-r--r--kernel/power/process.c12
-rw-r--r--kernel/relay.c1
-rw-r--r--kernel/sched/core.c42
-rw-r--r--kernel/sched/debug.c15
-rw-r--r--kernel/sched/fair.c72
-rw-r--r--kernel/sched/idle.c2
-rw-r--r--kernel/sched/sched.h2
-rw-r--r--kernel/sched/stats.h3
-rw-r--r--kernel/trace/bpf_trace.c14
-rw-r--r--kernel/trace/trace_printk.c7
34 files changed, 543 insertions, 245 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/events/core.c b/kernel/events/core.c
index 274450efea90..85cd41878a74 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event)
if (event->ctx)
put_ctx(event->ctx);
- if (event->pmu) {
- exclusive_event_destroy(event);
- module_put(event->pmu->module);
- }
+ exclusive_event_destroy(event);
+ module_put(event->pmu->module);
call_rcu(&event->rcu_head, free_event_rcu);
}
@@ -7531,7 +7529,7 @@ 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/fork.c b/kernel/fork.c
index 5c2c355aa97f..4a7ec0c6c88c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk)
}
#endif
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
{
}
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
@@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
return page ? page_address(page) : NULL;
}
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
{
- struct page *page = virt_to_page(ti);
+ struct page *page = virt_to_page(stack);
memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
-(1 << THREAD_SIZE_ORDER));
__free_kmem_pages(page, THREAD_SIZE_ORDER);
}
# else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+ return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
{
- kmem_cache_free(thread_info_cache, ti);
+ kmem_cache_free(thread_stack_cache, stack);
}
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
{
- thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
THREAD_SIZE, 0, NULL);
- BUG_ON(thread_info_cache == NULL);
+ BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
@@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(ti));
+ struct zone *zone = page_zone(virt_to_page(stack));
mod_zone_page_state(zone, NR_KERNEL_STACK, account);
}
@@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account)
void free_task(struct task_struct *tsk)
{
account_kernel_stack(tsk->stack, -1);
- arch_release_thread_info(tsk->stack);
- free_thread_info(tsk->stack);
+ arch_release_thread_stack(tsk->stack);
+ free_thread_stack(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
@@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk)
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
- struct thread_info *ti;
+ unsigned long *stack;
int err;
if (node == NUMA_NO_NODE)
@@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
if (!tsk)
return NULL;
- ti = alloc_thread_info_node(tsk, node);
- if (!ti)
+ stack = alloc_thread_stack_node(tsk, node);
+ if (!stack)
goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
if (err)
- goto free_ti;
+ goto free_stack;
- tsk->stack = ti;
+ tsk->stack = stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
@@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(ti, 1);
+ account_kernel_stack(stack, 1);
kcov_task_init(tsk);
return tsk;
-free_ti:
- free_thread_info(ti);
+free_stack:
+ free_thread_stack(stack);
free_tsk:
free_task_struct(tsk);
return NULL;
diff --git a/kernel/futex.c b/kernel/futex.c
index ee25f5ba4aca..33664f70e2d2 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
{
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
- struct page *page;
+ struct page *page, *tail;
struct address_space *mapping;
int err, ro = 0;
@@ -530,7 +530,15 @@ again:
* considered here and page lock forces unnecessarily serialization
* From this point on, mapping will be re-verified if necessary and
* page lock will be acquired only if it is unavoidable
- */
+ *
+ * Mapping checks require the head page for any compound page so the
+ * head page and mapping is looked up now. For anonymous pages, it
+ * does not matter if the page splits in the future as the key is
+ * based on the address. For filesystem-backed pages, the tail is
+ * required as the index of the page determines the key. For
+ * base pages, there is no tail page and tail == page.
+ */
+ tail = page;
page = compound_head(page);
mapping = READ_ONCE(page->mapping);
@@ -654,7 +662,7 @@ again:
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.inode = inode;
- key->shared.pgoff = basepage_index(page);
+ key->shared.pgoff = basepage_index(tail);
rcu_read_unlock();
}
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 2ee42e95a3ce..1d3ee3169202 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o
obj-$(CONFIG_PM_SLEEP) += pm.o
obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
+obj-$(CONFIG_SMP) += affinity.o
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
new file mode 100644
index 000000000000..f68959341c0f
--- /dev/null
+++ b/kernel/irq/affinity.c
@@ -0,0 +1,61 @@
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/cpu.h>
+
+static int get_first_sibling(unsigned int cpu)
+{
+ unsigned int ret;
+
+ ret = cpumask_first(topology_sibling_cpumask(cpu));
+ if (ret < nr_cpu_ids)
+ return ret;
+ return cpu;
+}
+
+/*
+ * Take a map of online CPUs and the number of available interrupt vectors
+ * and generate an output cpumask suitable for spreading MSI/MSI-X vectors
+ * so that they are distributed as good as possible around the CPUs. If
+ * more vectors than CPUs are available we'll map one to each CPU,
+ * otherwise we map one to the first sibling of each socket.
+ *
+ * If there are more vectors than CPUs we will still only have one bit
+ * set per CPU, but interrupt code will keep on assigning the vectors from
+ * the start of the bitmap until we run out of vectors.
+ */
+struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
+{
+ struct cpumask *affinity_mask;
+ unsigned int max_vecs = *nr_vecs;
+
+ if (max_vecs == 1)
+ return NULL;
+
+ affinity_mask = kzalloc(cpumask_size(), GFP_KERNEL);
+ if (!affinity_mask) {
+ *nr_vecs = 1;
+ return NULL;
+ }
+
+ if (max_vecs >= num_online_cpus()) {
+ cpumask_copy(affinity_mask, cpu_online_mask);
+ *nr_vecs = num_online_cpus();
+ } else {
+ unsigned int vecs = 0, cpu;
+
+ for_each_online_cpu(cpu) {
+ if (cpu == get_first_sibling(cpu)) {
+ cpumask_set_cpu(cpu, affinity_mask);
+ vecs++;
+ }
+
+ if (--max_vecs == 0)
+ break;
+ }
+ *nr_vecs = vecs;
+ }
+
+ return affinity_mask;
+}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 0c6f35ba9cc0..bc226e783bd2 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -107,6 +107,8 @@ static inline void unregister_handler_proc(unsigned int irq,
struct irqaction *action) { }
#endif
+extern bool irq_can_set_affinity_usr(unsigned int irq);
+
extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
extern void irq_set_thread_affinity(struct irq_desc *desc);
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 89b49f6773f0..4fd23510d5f2 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -76,7 +76,7 @@ int irq_reserve_ipi(struct irq_domain *domain,
}
}
- virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE);
+ virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL);
if (virq <= 0) {
pr_warn("Can't reserve IPI, failed to alloc descs\n");
return -ENOMEM;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 8731e1c5d1e7..a623b44f2d4b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -68,9 +68,13 @@ static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
return 0;
}
-static void desc_smp_init(struct irq_desc *desc, int node)
+static void desc_smp_init(struct irq_desc *desc, int node,
+ const struct cpumask *affinity)
{
- cpumask_copy(desc->irq_common_data.affinity, irq_default_affinity);
+ if (!affinity)
+ affinity = irq_default_affinity;
+ cpumask_copy(desc->irq_common_data.affinity, affinity);
+
#ifdef CONFIG_GENERIC_PENDING_IRQ
cpumask_clear(desc->pending_mask);
#endif
@@ -82,11 +86,12 @@ static void desc_smp_init(struct irq_desc *desc, int node)
#else
static inline int
alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
-static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline void
+desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
#endif
static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
- struct module *owner)
+ const struct cpumask *affinity, struct module *owner)
{
int cpu;
@@ -107,7 +112,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
desc->owner = owner;
for_each_possible_cpu(cpu)
*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
- desc_smp_init(desc, node);
+ desc_smp_init(desc, node, affinity);
}
int nr_irqs = NR_IRQS;
@@ -158,7 +163,9 @@ void irq_unlock_sparse(void)
mutex_unlock(&sparse_irq_lock);
}
-static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
+static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
+ const struct cpumask *affinity,
+ struct module *owner)
{
struct irq_desc *desc;
gfp_t gfp = GFP_KERNEL;
@@ -178,7 +185,8 @@ static struct irq_desc *alloc_desc(int irq, int node, struct module *owner)
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
init_rcu_head(&desc->rcu);
- desc_set_defaults(irq, desc, node, owner);
+ desc_set_defaults(irq, desc, node, affinity, owner);
+ irqd_set(&desc->irq_data, flags);
return desc;
@@ -223,13 +231,32 @@ static void free_desc(unsigned int irq)
}
static int alloc_descs(unsigned int start, unsigned int cnt, int node,
- struct module *owner)
+ const struct cpumask *affinity, struct module *owner)
{
+ const struct cpumask *mask = NULL;
struct irq_desc *desc;
- int i;
+ unsigned int flags;
+ int i, cpu = -1;
+
+ if (affinity && cpumask_empty(affinity))
+ return -EINVAL;
+
+ flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
for (i = 0; i < cnt; i++) {
- desc = alloc_desc(start + i, node, owner);
+ if (affinity) {
+ cpu = cpumask_next(cpu, affinity);
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(affinity);
+ node = cpu_to_node(cpu);
+
+ /*
+ * For single allocations we use the caller provided
+ * mask otherwise we use the mask of the target cpu
+ */
+ mask = cnt == 1 ? affinity : cpumask_of(cpu);
+ }
+ desc = alloc_desc(start + i, node, flags, mask, owner);
if (!desc)
goto err;
mutex_lock(&sparse_irq_lock);
@@ -277,7 +304,7 @@ int __init early_irq_init(void)
nr_irqs = initcnt;
for (i = 0; i < initcnt; i++) {
- desc = alloc_desc(i, node, NULL);
+ desc = alloc_desc(i, node, 0, NULL, NULL);
set_bit(i, allocated_irqs);
irq_insert_desc(i, desc);
}
@@ -311,7 +338,7 @@ int __init early_irq_init(void)
alloc_masks(&desc[i], GFP_KERNEL, node);
raw_spin_lock_init(&desc[i].lock);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
- desc_set_defaults(i, &desc[i], node, NULL);
+ desc_set_defaults(i, &desc[i], node, NULL, NULL);
}
return arch_early_irq_init();
}
@@ -328,11 +355,12 @@ static void free_desc(unsigned int irq)
unsigned long flags;
raw_spin_lock_irqsave(&desc->lock, flags);
- desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL);
+ desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
+ const struct cpumask *affinity,
struct module *owner)
{
u32 i;
@@ -453,12 +481,15 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
* @cnt: Number of consecutive irqs to allocate.
* @node: Preferred node on which the irq descriptor should be allocated
* @owner: Owning module (can be NULL)
+ * @affinity: Optional pointer to an affinity mask which hints where the
+ * irq descriptors should be allocated and which default
+ * affinities to use
*
* Returns the first irq number or error code
*/
int __ref
__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
- struct module *owner)
+ struct module *owner, const struct cpumask *affinity)
{
int start, ret;
@@ -494,7 +525,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
bitmap_set(allocated_irqs, start, cnt);
mutex_unlock(&sparse_irq_lock);
- return alloc_descs(start, cnt, node, owner);
+ return alloc_descs(start, cnt, node, affinity, owner);
err:
mutex_unlock(&sparse_irq_lock);
@@ -512,7 +543,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs);
*/
unsigned int irq_alloc_hwirqs(int cnt, int node)
{
- int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL);
+ int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
if (irq < 0)
return 0;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 5d89d724a02a..a82853739694 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -481,7 +481,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
}
/* Allocate a virtual interrupt number */
- virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node));
+ virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
if (virq <= 0) {
pr_debug("-> virq allocation failed\n");
return 0;
@@ -879,19 +879,23 @@ const struct irq_domain_ops irq_domain_simple_ops = {
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
- int node)
+ int node, const struct cpumask *affinity)
{
unsigned int hint;
if (virq >= 0) {
- virq = irq_alloc_descs(virq, virq, cnt, node);
+ virq = __irq_alloc_descs(virq, virq, cnt, node, THIS_MODULE,
+ affinity);
} else {
hint = hwirq % nr_irqs;
if (hint == 0)
hint++;
- virq = irq_alloc_descs_from(hint, cnt, node);
- if (virq <= 0 && hint > 1)
- virq = irq_alloc_descs_from(1, cnt, node);
+ virq = __irq_alloc_descs(-1, hint, cnt, node, THIS_MODULE,
+ affinity);
+ if (virq <= 0 && hint > 1) {
+ virq = __irq_alloc_descs(-1, 1, cnt, node, THIS_MODULE,
+ affinity);
+ }
}
return virq;
@@ -1204,6 +1208,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
* @node: NUMA node id for memory allocation
* @arg: domain specific argument
* @realloc: IRQ descriptors have already been allocated if true
+ * @affinity: Optional irq affinity mask for multiqueue devices
*
* Allocate IRQ numbers and initialized all data structures to support
* hierarchy IRQ domains.
@@ -1219,7 +1224,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain,
*/
int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
unsigned int nr_irqs, int node, void *arg,
- bool realloc)
+ bool realloc, const struct cpumask *affinity)
{
int i, ret, virq;
@@ -1237,7 +1242,8 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
if (realloc && irq_base >= 0) {
virq = irq_base;
} else {
- virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node);
+ virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node,
+ affinity);
if (virq < 0) {
pr_debug("cannot allocate IRQ(base %d, count %d)\n",
irq_base, nr_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 00cfc852cca8..73a2b786b5e9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -115,12 +115,12 @@ EXPORT_SYMBOL(synchronize_irq);
#ifdef CONFIG_SMP
cpumask_var_t irq_default_affinity;
-static int __irq_can_set_affinity(struct irq_desc *desc)
+static bool __irq_can_set_affinity(struct irq_desc *desc)
{
if (!desc || !irqd_can_balance(&desc->irq_data) ||
!desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
- return 0;
- return 1;
+ return false;
+ return true;
}
/**
@@ -134,6 +134,21 @@ int irq_can_set_affinity(unsigned int irq)
}
/**
+ * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
+ * @irq: Interrupt to check
+ *
+ * Like irq_can_set_affinity() above, but additionally checks for the
+ * AFFINITY_MANAGED flag.
+ */
+bool irq_can_set_affinity_usr(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ return __irq_can_set_affinity(desc) &&
+ !irqd_affinity_is_managed(&desc->irq_data);
+}
+
+/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
* @desc: irq descriptor which has affitnity changed
*
@@ -338,10 +353,11 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask)
return 0;
/*
- * Preserve an userspace affinity setup, but make sure that
- * one of the targets is online.
+ * Preserve the managed affinity setting and an userspace affinity
+ * setup, but make sure that one of the targets is online.
*/
- if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
+ if (irqd_affinity_is_managed(&desc->irq_data) ||
+ irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
if (cpumask_intersects(desc->irq_common_data.affinity,
cpu_online_mask))
set = desc->irq_common_data.affinity;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 38e89ce7b071..0e2a736b14a7 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -324,7 +324,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
struct msi_domain_ops *ops = info->ops;
msi_alloc_info_t arg;
struct msi_desc *desc;
- int i, ret, virq = -1;
+ int i, ret, virq;
ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
if (ret)
@@ -332,13 +332,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
for_each_msi_entry(desc, dev) {
ops->set_desc(&arg, desc);
- if (info->flags & MSI_FLAG_IDENTITY_MAP)
- virq = (int)ops->get_hwirq(info, &arg);
- else
- virq = -1;
- virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used,
- dev_to_node(dev), &arg, false);
+ virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+ dev_to_node(dev), &arg, false,
+ desc->affinity);
if (virq < 0) {
ret = -ENOSPC;
if (ops->handle_error)
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index f30425dce9dd..feaa813b84a9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -96,7 +96,7 @@ static ssize_t write_irq_affinity(int type, struct file *file,
cpumask_var_t new_value;
int err;
- if (!irq_can_set_affinity(irq) || no_irq_affinity)
+ if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
return -EIO;
if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 05254eeb4b4e..4b353e0be121 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key);
void static_key_slow_inc(struct static_key *key)
{
+ int v, v1;
+
STATIC_KEY_CHECK_USE();
- if (atomic_inc_not_zero(&key->enabled))
- return;
+
+ /*
+ * Careful if we get concurrent static_key_slow_inc() calls;
+ * later calls must wait for the first one to _finish_ the
+ * jump_label_update() process. At the same time, however,
+ * the jump_label_update() call below wants to see
+ * static_key_enabled(&key) for jumps to be updated properly.
+ *
+ * So give a special meaning to negative key->enabled: it sends
+ * static_key_slow_inc() down the slow path, and it is non-zero
+ * so it counts as "enabled" in jump_label_update(). Note that
+ * atomic_inc_unless_negative() checks >= 0, so roll our own.
+ */
+ for (v = atomic_read(&key->enabled); v > 0; v = v1) {
+ v1 = atomic_cmpxchg(&key->enabled, v, v + 1);
+ if (likely(v1 == v))
+ return;
+ }
jump_label_lock();
- if (atomic_inc_return(&key->enabled) == 1)
+ if (atomic_read(&key->enabled) == 0) {
+ atomic_set(&key->enabled, -1);
jump_label_update(key);
+ atomic_set(&key->enabled, 1);
+ } else {
+ atomic_inc(&key->enabled);
+ }
jump_label_unlock();
}
EXPORT_SYMBOL_GPL(static_key_slow_inc);
@@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc);
static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
+ /*
+ * The negative count check is valid even when a negative
+ * key->enabled is in use by static_key_slow_inc(); a
+ * __static_key_slow_dec() before the first static_key_slow_inc()
+ * returns is unbalanced, because all other static_key_slow_inc()
+ * instances block while the update is in progress.
+ */
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
WARN(atomic_read(&key->enabled) < 0,
"jump label: negative count!\n");
diff --git a/kernel/kcov.c b/kernel/kcov.c
index a02f2dddd1d7..8d44b3fea9d0 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = {
static int __init kcov_init(void)
{
- if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+ /*
+ * The kcov debugfs file won't ever get removed and thus,
+ * there is no need to protect it against removal races. The
+ * use of debugfs_create_file_unsafe() is actually safe here.
+ */
+ if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) {
pr_err("failed to create kcov in debugfs\n");
return -ENOMEM;
}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 3ef3736002d8..9c951fade415 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
}
void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
/* Mark the current thread as blocked on the lock: */
- ti->task->blocked_on = waiter;
+ task->blocked_on = waiter;
}
void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
- DEBUG_LOCKS_WARN_ON(waiter->task != ti->task);
- DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter);
- ti->task->blocked_on = NULL;
+ DEBUG_LOCKS_WARN_ON(waiter->task != task);
+ DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
+ task->blocked_on = NULL;
list_del_init(&waiter->list);
waiter->task = NULL;
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..d06ae3bb46c5 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock,
extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
extern void debug_mutex_add_waiter(struct mutex *lock,
struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void debug_mutex_unlock(struct mutex *lock);
extern void debug_mutex_init(struct mutex *lock, const char *name,
struct lock_class_key *key);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e364b424b019..a70b90db3909 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
if (!hold_ctx)
return 0;
- if (unlikely(ctx == hold_ctx))
- return -EALREADY;
-
if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
(ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
#ifdef CONFIG_DEBUG_MUTEXES
@@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
unsigned long flags;
int ret;
+ if (use_ww_ctx) {
+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+ if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+ return -EALREADY;
+ }
+
preempt_disable();
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
@@ -534,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto skip_wait;
debug_mutex_lock_common(lock, &waiter);
- debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
+ debug_mutex_add_waiter(lock, &waiter, task);
/* add waiting tasks to the end of the waitqueue (FIFO): */
list_add_tail(&waiter.list, &lock->wait_list);
@@ -581,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
}
__set_task_state(task, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, current_thread_info());
+ mutex_remove_waiter(lock, &waiter, task);
/* set it to 0 if there are no waiters left: */
if (likely(list_empty(&lock->wait_list)))
atomic_set(&lock->count, 0);
@@ -602,7 +605,7 @@ skip_wait:
return 0;
err:
- mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+ mutex_remove_waiter(lock, &waiter, task);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 5cda397607f2..a68bae5e852a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -13,7 +13,7 @@
do { spin_lock(lock); (void)(flags); } while (0)
#define spin_unlock_mutex(lock, flags) \
do { spin_unlock(lock); (void)(flags); } while (0)
-#define mutex_remove_waiter(lock, waiter, ti) \
+#define mutex_remove_waiter(lock, waiter, task) \
__list_del((waiter)->list.prev, (waiter)->list.next)
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32ae1..5fc8c311b8fe 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath
#endif
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ * (1) clear_pending_set_locked(): *,1,0 -> *,0,1
+ *
+ * (2) set_locked(): t,0,0 -> t,0,1 ; t != 0
+ * atomic_cmpxchg_relaxed(): t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+ u32 val;
+
+ for (;;) {
+ val = atomic_read(&lock->val);
+
+ if (!val) /* not locked, we're done */
+ goto done;
+
+ if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+ break;
+
+ /* not locked, but pending, wait until we observe the lock */
+ cpu_relax();
+ }
+
+ /* any unlock is good */
+ while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+ cpu_relax();
+
+done:
+ smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
#endif /* _GEN_PV_LOCK_SLOWPATH */
/**
diff --git a/kernel/power/process.c b/kernel/power/process.c
index df058bed53ce..0c2ee9761d57 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -146,6 +146,18 @@ int freeze_processes(void)
if (!error && !oom_killer_disable())
error = -EBUSY;
+ /*
+ * There is a hard to fix race between oom_reaper kernel thread
+ * and oom_killer_disable. oom_reaper calls exit_oom_victim
+ * before the victim reaches exit_mm so try to freeze all the tasks
+ * again and catch such a left over task.
+ */
+ if (!error) {
+ pr_info("Double checking all user space processes after OOM killer disable... ");
+ error = try_to_freeze_tasks(true);
+ pr_cont("\n");
+ }
+
if (error)
thaw_processes();
return error;
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994bcfa9b..04d7cf3ef8cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@ free_bufs:
kref_put(&chan->kref, relay_destroy_channel);
mutex_unlock(&relay_channels_mutex);
+ kfree(chan);
return NULL;
}
EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4620c7..51d7105f529a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
for (;;) {
/* Any allowed, online CPU? */
for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) {
- if (!cpu_active(dest_cpu))
+ if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
+ continue;
+ if (!cpu_online(dest_cpu))
continue;
goto out;
}
@@ -2253,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
#endif
#endif
+#ifdef CONFIG_SCHEDSTATS
+
DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+static bool __initdata __sched_schedstats = false;
-#ifdef CONFIG_SCHEDSTATS
static void set_schedstats(bool enabled)
{
if (enabled)
@@ -2278,11 +2282,16 @@ static int __init setup_schedstats(char *str)
if (!str)
goto out;
+ /*
+ * This code is called before jump labels have been set up, so we can't
+ * change the static branch directly just yet. Instead set a temporary
+ * variable so init_schedstats() can do it later.
+ */
if (!strcmp(str, "enable")) {
- set_schedstats(true);
+ __sched_schedstats = true;
ret = 1;
} else if (!strcmp(str, "disable")) {
- set_schedstats(false);
+ __sched_schedstats = false;
ret = 1;
}
out:
@@ -2293,6 +2302,11 @@ out:
}
__setup("schedstats=", setup_schedstats);
+static void __init init_schedstats(void)
+{
+ set_schedstats(__sched_schedstats);
+}
+
#ifdef CONFIG_PROC_SYSCTL
int sysctl_schedstats(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2313,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write,
set_schedstats(state);
return err;
}
-#endif
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
+#else /* !CONFIG_SCHEDSTATS */
+static inline void init_schedstats(void) {}
+#endif /* CONFIG_SCHEDSTATS */
/*
* fork()/clone()-time setup:
@@ -2521,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p)
*/
set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
- /* Post initialize new task's util average when its cfs_rq is set */
+ rq = __task_rq_lock(p, &rf);
post_init_entity_util_avg(&p->se);
- rq = __task_rq_lock(p, &rf);
activate_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
@@ -3156,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev)
static inline void schedule_debug(struct task_struct *prev)
{
#ifdef CONFIG_SCHED_STACK_END_CHECK
- BUG_ON(task_stack_end_corrupted(prev));
+ if (task_stack_end_corrupted(prev))
+ panic("corrupted stack end detected inside scheduler\n");
#endif
if (unlikely(in_atomic_preempt_off())) {
@@ -5133,14 +5149,16 @@ void show_state_filter(unsigned long state_filter)
/*
* reset the NMI-timeout, listing all files on a slow
* console might take a lot of time:
+ * Also, reset softlockup watchdogs on all CPUs, because
+ * another CPU might be blocked waiting for us to process
+ * an IPI.
*/
touch_nmi_watchdog();
+ touch_all_softlockup_watchdogs();
if (!state_filter || (p->state & state_filter))
sched_show_task(p);
}
- touch_all_softlockup_watchdogs();
-
#ifdef CONFIG_SCHED_DEBUG
if (!state_filter)
sysrq_sched_debug_show();
@@ -7487,6 +7505,8 @@ void __init sched_init(void)
#endif
init_sched_fair_class();
+ init_schedstats();
+
scheduler_running = 1;
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index cf905f655ba1..0368c393a336 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
SPLIT_NS(p->se.vruntime),
(long long)(p->nvcsw + p->nivcsw),
p->prio);
-#ifdef CONFIG_SCHEDSTATS
- if (schedstat_enabled()) {
- SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- SPLIT_NS(p->se.statistics.wait_sum),
- SPLIT_NS(p->se.sum_exec_runtime),
- SPLIT_NS(p->se.statistics.sum_sleep_runtime));
- }
-#else
+
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
- 0LL, 0L,
+ SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
SPLIT_NS(p->se.sum_exec_runtime),
- 0LL, 0L);
-#endif
+ SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 218f8e83db73..bdcbeea90c95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2904,6 +2904,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
}
}
+/*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define sub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(*ptr) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ res = var - val; \
+ if (res > var) \
+ res = 0; \
+ WRITE_ONCE(*ptr, res); \
+} while (0)
+
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
@@ -2913,15 +2930,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
- sa->load_avg = max_t(long, sa->load_avg - r, 0);
- sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->load_avg, r);
+ sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed_load = 1;
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
- sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->util_avg, r);
+ sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
removed_util = 1;
}
@@ -2994,10 +3011,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
&se->avg, se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
- cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+ sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+ sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+ sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+ sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
cfs_rq_util_change(cfs_rq);
}
@@ -3246,7 +3263,7 @@ static inline void check_schedstat_required(void)
trace_sched_stat_iowait_enabled() ||
trace_sched_stat_blocked_enabled() ||
trace_sched_stat_runtime_enabled()) {
- pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+ printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
"stat_blocked and stat_runtime require the "
"kernel parameter schedstats=enabled or "
"kernel.sched_schedstats=1\n");
@@ -4185,6 +4202,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
if (!cfs_bandwidth_used())
return;
+ /* Synchronize hierarchical throttle counter: */
+ if (unlikely(!cfs_rq->throttle_uptodate)) {
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_rq *pcfs_rq;
+ struct task_group *tg;
+
+ cfs_rq->throttle_uptodate = 1;
+
+ /* Get closest up-to-date node, because leaves go first: */
+ for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+ pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+ if (pcfs_rq->throttle_uptodate)
+ break;
+ }
+ if (tg) {
+ cfs_rq->throttle_count = pcfs_rq->throttle_count;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ }
+ }
+
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
@@ -4500,15 +4537,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
+ /* Avoid re-evaluating load for this entity: */
+ se = parent_entity(se);
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
- if (task_sleep && parent_entity(se))
- set_next_buddy(parent_entity(se));
-
- /* avoid re-evaluating load for this entity */
- se = parent_entity(se);
+ if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+ set_next_buddy(se);
break;
}
flags |= DEQUEUE_SLEEP;
@@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg)
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
- struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
@@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
init_entity_runnable_average(se);
+
+ raw_spin_lock_irq(&rq->lock);
post_init_entity_util_avg(se);
+ raw_spin_unlock_irq(&rq->lock);
}
return 1;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c714ec..c5aeedf4e93a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
*/
static void cpuidle_idle_call(void)
{
- struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 72f1f3087b04..7cbeb92a1cb9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ struct cfs_rq {
u64 throttled_clock, throttled_clock_task;
u64 throttled_clock_task_time;
- int throttled, throttle_count;
+ int throttled, throttle_count, throttle_uptodate;
struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 70b3b6a20fb0..78955cbea31c 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
# define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
# define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
# define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)
+# define schedstat_val(rq, field) ((schedstat_enabled()) ? (rq)->field : 0)
+
#else /* !CONFIG_SCHEDSTATS */
static inline void
rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
# define schedstat_inc(rq, field) do { } while (0)
# define schedstat_add(rq, field, amt) do { } while (0)
# define schedstat_set(var, val) do { } while (0)
+# define schedstat_val(rq, field) 0
#endif
#ifdef CONFIG_SCHED_INFO
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe1d4de..26f603da7e26 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -198,7 +198,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -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
@@ -247,7 +251,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
if (unlikely(index >= array->map.max_entries))
return -E2BIG;
- file = (struct file *)array->ptrs[index];
+ file = READ_ONCE(array->ptrs[index]);
if (unlikely(!file))
return -ENOENT;
@@ -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/trace/trace_printk.c b/kernel/trace/trace_printk.c
index f96f0383f6c6..ad1d6164e946 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -36,6 +36,10 @@ struct trace_bprintk_fmt {
static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
{
struct trace_bprintk_fmt *pos;
+
+ if (!fmt)
+ return ERR_PTR(-EINVAL);
+
list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
if (!strcmp(pos->fmt, fmt))
return pos;
@@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
for (iter = start; iter < end; iter++) {
struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
if (tb_fmt) {
- *iter = tb_fmt->fmt;
+ if (!IS_ERR(tb_fmt))
+ *iter = tb_fmt->fmt;
continue;
}