summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/cgroup.c54
-rw-r--r--kernel/bpf/core.c30
-rw-r--r--kernel/bpf/sockmap.c254
-rw-r--r--kernel/bpf/syscall.c99
-rw-r--r--kernel/dma/swiotlb.c1
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/ring_buffer.c6
-rw-r--r--kernel/irq/debugfs.c1
-rw-r--r--kernel/kthread.c30
-rw-r--r--kernel/locking/lockdep.c12
-rw-r--r--kernel/locking/rwsem.c1
-rw-r--r--kernel/rseq.c48
-rw-r--r--kernel/sched/core.c67
-rw-r--r--kernel/sched/cpufreq_schedutil.c2
-rw-r--r--kernel/sched/fair.c45
-rw-r--r--kernel/sched/rt.c16
-rw-r--r--kernel/sched/sched.h11
-rw-r--r--kernel/softirq.c6
-rw-r--r--kernel/time/hrtimer.c2
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/time/tick-common.c3
-rw-r--r--kernel/time/time.c6
-rw-r--r--kernel/trace/ftrace.c13
-rw-r--r--kernel/trace/trace.c19
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_events_filter.c15
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/trace/trace_functions_graph.c5
-rw-r--r--kernel/trace/trace_kprobe.c6
-rw-r--r--kernel/trace/trace_output.c5
30 files changed, 450 insertions, 317 deletions
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..3d83ee7df381 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a9e6c04d0f4a..1e5625d46414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
bpf_fill_ill_insns(hdr, size);
hdr->pages = size / PAGE_SIZE;
- hdr->locked = 0;
-
hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
PAGE_SIZE - sizeof(*hdr));
start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
return 0;
}
-static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
-{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
- int i, err;
-
- for (i = 0; i < fp->aux->func_cnt; i++) {
- err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
- if (err)
- return err;
- }
-
- return bpf_prog_check_pages_ro_single(fp);
-#endif
- return 0;
-}
-
static void bpf_prog_select_func(struct bpf_prog *fp)
{
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
@@ -1524,17 +1506,7 @@ finalize:
* all eBPF JITs might immediately support all features.
*/
*err = bpf_check_tail_call(fp);
- if (*err)
- return fp;
-
- /* Checkpoint: at this point onwards any cBPF -> eBPF or
- * native eBPF program is read-only. If we failed to change
- * the page attributes (e.g. allocation failure from
- * splitting large pages), then reject the whole program
- * in order to guarantee not ending up with any W+X pages
- * from BPF side in kernel.
- */
- *err = bpf_prog_check_pages_ro_locked(fp);
+
return fp;
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..cf7b6a6dbd1f 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -72,6 +72,7 @@ struct bpf_htab {
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
@@ -89,8 +90,8 @@ enum smap_psock_state {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
@@ -120,6 +121,7 @@ struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
@@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
@@ -161,7 +164,42 @@ out:
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
@@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk)
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
@@ -219,16 +260,54 @@ out:
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
@@ -247,7 +326,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
@@ -260,20 +338,38 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
close_fun(sk, timeout);
}
@@ -1111,8 +1207,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
@@ -1357,7 +1452,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1508,6 +1605,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
@@ -1564,18 +1662,32 @@ free_stab:
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
@@ -1601,7 +1713,6 @@ static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -1609,10 +1720,9 @@ static void sock_map_free(struct bpf_map *map)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
@@ -1661,17 +1771,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
@@ -1752,7 +1860,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
@@ -1809,7 +1916,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
@@ -1819,9 +1928,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
@@ -1832,7 +1942,6 @@ out_progs:
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
@@ -1869,10 +1978,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
@@ -1915,6 +2022,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
@@ -2043,14 +2168,13 @@ free_htab:
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2193,18 @@ static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
@@ -2086,16 +2212,15 @@ static void sock_hash_free(struct bpf_map *map)
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2247,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
@@ -2254,9 +2366,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto bucket_err;
}
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
@@ -2266,7 +2381,7 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
@@ -2326,7 +2441,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2448,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
@@ -2383,6 +2496,7 @@ const struct bpf_map_ops sock_hash_ops = {
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f12db70d3bf3..8363fd83d399 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1483,8 +1483,6 @@ out_free_tp:
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
@@ -1499,40 +1497,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
@@ -1540,7 +1504,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
@@ -1577,12 +1540,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
@@ -1596,18 +1562,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
@@ -1616,9 +1584,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -1651,29 +1616,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1681,9 +1634,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1711,14 +1661,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -2365,7 +2310,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
@@ -2375,7 +2319,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 04b68d9dffac..904541055792 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1085,3 +1085,4 @@ const struct dma_map_ops swiotlb_dma_ops = {
.unmap_page = swiotlb_unmap_page,
.dma_supported = dma_direct_supported,
};
+EXPORT_SYMBOL(swiotlb_dma_ops);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..8f0434a9951a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6482,7 +6482,7 @@ void perf_prepare_sample(struct perf_event_header *header,
data->phys_addr = perf_virt_to_phys(data->addr);
}
-static void __always_inline
+static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs,
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 045a37e9ddee..5d3cf407e374 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -103,7 +103,7 @@ out:
preempt_enable();
}
-static bool __always_inline
+static __always_inline bool
ring_buffer_has_space(unsigned long head, unsigned long tail,
unsigned long data_size, unsigned int size,
bool backward)
@@ -114,7 +114,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail,
return CIRC_SPACE(tail, head, data_size) >= size;
}
-static int __always_inline
+static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
bool backward)
@@ -414,7 +414,7 @@ err:
}
EXPORT_SYMBOL_GPL(perf_aux_output_begin);
-static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb)
{
if (rb->aux_overwrite)
return false;
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 4dadeb3d6666..6f636136cccc 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -55,6 +55,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE),
BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
+ BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
};
static void
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 481951bf091d..750cb8082694 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task)
static void __kthread_parkme(struct kthread *self)
{
for (;;) {
- set_current_state(TASK_PARKED);
+ /*
+ * TASK_PARKED is a special state; we must serialize against
+ * possible pending wakeups to avoid store-store collisions on
+ * task->state.
+ *
+ * Such a collision might possibly result in the task state
+ * changin from TASK_PARKED and us failing the
+ * wait_task_inactive() in kthread_park().
+ */
+ set_special_state(TASK_PARKED);
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
+
+ complete_all(&self->parked);
schedule();
}
__set_current_state(TASK_RUNNING);
@@ -191,11 +202,6 @@ void kthread_parkme(void)
}
EXPORT_SYMBOL_GPL(kthread_parkme);
-void kthread_park_complete(struct task_struct *k)
-{
- complete_all(&to_kthread(k)->parked);
-}
-
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
@@ -461,6 +467,9 @@ void kthread_unpark(struct task_struct *k)
reinit_completion(&kthread->parked);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ /*
+ * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
+ */
wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -487,7 +496,16 @@ int kthread_park(struct task_struct *k)
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
+ /*
+ * Wait for __kthread_parkme() to complete(), this means we
+ * _will_ have TASK_PARKED and are about to call schedule().
+ */
wait_for_completion(&kthread->parked);
+ /*
+ * Now wait for that schedule() to complete and the task to
+ * get scheduled out.
+ */
+ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
}
return 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index edcac5de7ebc..5fa4d3138bf1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1265,11 +1265,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -1292,11 +1292,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -4411,7 +4411,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
if (unlikely(!debug_locks))
return;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
for (i = 0; i < curr->lockdep_depth; i++) {
hlock = curr->held_locks + i;
@@ -4422,7 +4422,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
break;
}
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index bc1e507be9ff..776308d2fa9e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -181,6 +181,7 @@ void down_read_non_owner(struct rw_semaphore *sem)
might_sleep();
__down_read(sem);
+ rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_non_owner);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index ae306f90c514..c6242d8594dc 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
{
u32 cpu_id = raw_smp_processor_id();
- if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id, &t->rseq->cpu_id_start))
return -EFAULT;
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
trace_rseq_update(t);
return 0;
@@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
/*
* Reset cpu_id_start to its initial state (0).
*/
- if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
return -EFAULT;
/*
* Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
* in after unregistration can figure out that rseq needs to be
* registered again.
*/
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
return 0;
}
@@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
{
struct rseq_cs __user *urseq_cs;
- unsigned long ptr;
+ u64 ptr;
u32 __user *usig;
u32 sig;
int ret;
- ret = __get_user(ptr, &t->rseq->rseq_cs);
- if (ret)
- return ret;
+ if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+ return -EFAULT;
if (!ptr) {
memset(rseq_cs, 0, sizeof(*rseq_cs));
return 0;
}
- urseq_cs = (struct rseq_cs __user *)ptr;
+ if (ptr >= TASK_SIZE)
+ return -EINVAL;
+ urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
return -EFAULT;
- if (rseq_cs->version > 0)
- return -EINVAL;
+ if (rseq_cs->start_ip >= TASK_SIZE ||
+ rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+ rseq_cs->abort_ip >= TASK_SIZE ||
+ rseq_cs->version > 0)
+ return -EINVAL;
+ /* Check for overflow. */
+ if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+ return -EINVAL;
/* Ensure that abort_ip is not in the critical section. */
if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
return -EINVAL;
- usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+ usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
ret = get_user(sig, usig);
if (ret)
return ret;
@@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
printk_ratelimited(KERN_WARNING
"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
sig, current->rseq_sig, current->pid, usig);
- return -EPERM;
+ return -EINVAL;
}
return 0;
}
@@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
int ret;
/* Get thread flags. */
- ret = __get_user(flags, &t->rseq->flags);
+ ret = get_user(flags, &t->rseq->flags);
if (ret)
return ret;
@@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t)
* of code outside of the rseq assembly block. This performs
* a lazy clear of the rseq_cs field.
*
- * Set rseq_cs to NULL with single-copy atomicity.
+ * Set rseq_cs to NULL.
*/
- return __put_user(0UL, &t->rseq->rseq_cs);
+ if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+ return -EFAULT;
+ return 0;
}
/*
@@ -251,10 +260,10 @@ static int rseq_ip_fixup(struct pt_regs *regs)
* respect to other threads scheduled on the same CPU, and with respect
* to signal handlers.
*/
-void __rseq_handle_notify_resume(struct pt_regs *regs)
+void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
{
struct task_struct *t = current;
- int ret;
+ int ret, sig;
if (unlikely(t->flags & PF_EXITING))
return;
@@ -268,7 +277,8 @@ void __rseq_handle_notify_resume(struct pt_regs *regs)
return;
error:
- force_sig(SIGSEGV, t);
+ sig = ksig ? ksig->sig : 0;
+ force_sigsegv(sig, t);
}
#ifdef CONFIG_DEBUG_RSEQ
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..fe365c9a08e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,7 +7,6 @@
*/
#include "sched.h"
-#include <linux/kthread.h>
#include <linux/nospec.h>
#include <linux/kcov.h>
@@ -2724,28 +2723,20 @@ static struct rq *finish_task_switch(struct task_struct *prev)
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
- if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
- switch (prev_state) {
- case TASK_DEAD:
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
+ if (unlikely(prev_state == TASK_DEAD)) {
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
-
- /* Task is done with its stack. */
- put_task_stack(prev);
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
- put_task_struct(prev);
- break;
+ /* Task is done with its stack. */
+ put_task_stack(prev);
- case TASK_PARKED:
- kthread_park_complete(prev);
- break;
- }
+ put_task_struct(prev);
}
tick_nohz_task_switch();
@@ -3113,7 +3104,9 @@ static void sched_tick_remote(struct work_struct *work)
struct tick_work *twork = container_of(dwork, struct tick_work, work);
int cpu = twork->cpu;
struct rq *rq = cpu_rq(cpu);
+ struct task_struct *curr;
struct rq_flags rf;
+ u64 delta;
/*
* Handle the tick only if it appears the remote CPU is running in full
@@ -3122,24 +3115,28 @@ static void sched_tick_remote(struct work_struct *work)
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
- if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
- struct task_struct *curr;
- u64 delta;
+ if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+ goto out_requeue;
- rq_lock_irq(rq, &rf);
- update_rq_clock(rq);
- curr = rq->curr;
- delta = rq_clock_task(rq) - curr->se.exec_start;
+ rq_lock_irq(rq, &rf);
+ curr = rq->curr;
+ if (is_idle_task(curr))
+ goto out_unlock;
- /*
- * Make sure the next tick runs within a reasonable
- * amount of time.
- */
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
- curr->sched_class->task_tick(rq, curr, 0);
- rq_unlock_irq(rq, &rf);
- }
+ update_rq_clock(rq);
+ delta = rq_clock_task(rq) - curr->se.exec_start;
+
+ /*
+ * Make sure the next tick runs within a reasonable
+ * amount of time.
+ */
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ curr->sched_class->task_tick(rq, curr, 0);
+
+out_unlock:
+ rq_unlock_irq(rq, &rf);
+out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3cde46483f0a..c907fde01eaa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -192,7 +192,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
- if (rq->rt.rt_nr_running)
+ if (rt_rq_is_runnable(&rq->rt))
return sg_cpu->max;
/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..2f0a0be4d344 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3982,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
if (!sched_feat(UTIL_EST))
return;
- /*
- * Update root cfs_rq's estimated utilization
- *
- * If *p is the last task then the root cfs_rq's estimated utilization
- * of a CPU is 0 by definition.
- */
- ue.enqueued = 0;
- if (cfs_rq->nr_running) {
- ue.enqueued = cfs_rq->avg.util_est.enqueued;
- ue.enqueued -= min_t(unsigned int, ue.enqueued,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
- }
+ /* Update root cfs_rq's estimated utilization */
+ ue.enqueued = cfs_rq->avg.util_est.enqueued;
+ ue.enqueued -= min_t(unsigned int, ue.enqueued,
+ (_task_util_est(p) | UTIL_AVG_UNCHANGED));
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
/*
@@ -4590,6 +4582,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4612,6 +4605,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
u64 amount = 0, min_amount, expires;
+ int expires_seq;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4628,6 +4622,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
cfs_b->idle = 0;
}
}
+ expires_seq = cfs_b->expires_seq;
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
@@ -4637,8 +4632,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
* spread between our sched_clock and the one on which runtime was
* issued.
*/
- if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+ if (cfs_rq->expires_seq != expires_seq) {
+ cfs_rq->expires_seq = expires_seq;
cfs_rq->runtime_expires = expires;
+ }
return cfs_rq->runtime_remaining > 0;
}
@@ -4664,12 +4661,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
* has not truly expired.
*
* Fortunately we can check determine whether this the case by checking
- * whether the global deadline has advanced. It is valid to compare
- * cfs_b->runtime_expires without any locks since we only care about
- * exact equality, so a partial write will still work.
+ * whether the global deadline(cfs_b->expires_seq) has advanced.
*/
-
- if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+ if (cfs_rq->expires_seq == cfs_b->expires_seq) {
/* extend local deadline, drift is bounded above by 2 ticks */
cfs_rq->runtime_expires += TICK_NSEC;
} else {
@@ -5202,13 +5196,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ u64 overrun;
+
lockdep_assert_held(&cfs_b->lock);
- if (!cfs_b->period_active) {
- cfs_b->period_active = 1;
- hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
- }
+ if (cfs_b->period_active)
+ return;
+
+ cfs_b->period_active = 1;
+ overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 47556b0c9a95..572567078b60 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
rt_se = rt_rq->tg->rt_se[cpu];
- if (!rt_se)
+ if (!rt_se) {
dequeue_top_rt_rq(rt_rq);
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
+ }
else if (on_rt_rq(rt_se))
dequeue_rt_entity(rt_se, 0);
}
@@ -1001,8 +1004,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
sub_nr_running(rq, rt_rq->rt_nr_running);
rt_rq->rt_queued = 0;
- /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_util(rq, 0);
}
static void
@@ -1014,11 +1015,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq)
if (rt_rq->rt_queued)
return;
- if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+
+ if (rt_rq_throttled(rt_rq))
return;
- add_nr_running(rq, rt_rq->rt_nr_running);
- rt_rq->rt_queued = 1;
+ if (rt_rq->rt_nr_running) {
+ add_nr_running(rq, rt_rq->rt_nr_running);
+ rt_rq->rt_queued = 1;
+ }
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
cpufreq_update_util(rq, 0);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6601baf2361c..c7742dcc136c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -334,9 +334,10 @@ struct cfs_bandwidth {
u64 runtime;
s64 hierarchical_quota;
u64 runtime_expires;
+ int expires_seq;
- int idle;
- int period_active;
+ short idle;
+ short period_active;
struct hrtimer period_timer;
struct hrtimer slack_timer;
struct list_head throttled_cfs_rq;
@@ -551,6 +552,7 @@ struct cfs_rq {
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
+ int expires_seq;
u64 runtime_expires;
s64 runtime_remaining;
@@ -609,6 +611,11 @@ struct rt_rq {
#endif
};
+static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_queued && rt_rq->rt_nr_running;
+}
+
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index de2f57fddc04..900dcfee542c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -139,9 +139,13 @@ static void __local_bh_enable(unsigned int cnt)
{
lockdep_assert_irqs_disabled();
+ if (preempt_count() == cnt)
+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
- preempt_count_sub(cnt);
+
+ __preempt_count_sub(cnt);
}
/*
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 055a4a728c00..3e93c54bd3a1 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1659,7 +1659,7 @@ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
{
switch(restart->nanosleep.type) {
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
case TT_COMPAT:
if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp))
return -EFAULT;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 5a6251ac6f7a..9cdf54b04ca8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -604,7 +604,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
/*
* Disarm any old timer after extracting its expiry time.
*/
- lockdep_assert_irqs_disabled();
ret = 0;
old_incr = timer->it.cpu.incr;
@@ -1049,7 +1048,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
/*
* Now re-arm for the new expiry time.
*/
- lockdep_assert_irqs_disabled();
arm_timer(timer);
unlock:
unlock_task_sighand(p, &flags);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b7005dd21ec1..14de3727b18e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
*/
return !curdev ||
newdev->rating > curdev->rating ||
- (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
- !tick_check_percpu(curdev, newdev, smp_processor_id()));
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
}
/*
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6fa99213fc72..2b41e8e2d31d 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -28,6 +28,7 @@
*/
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
@@ -314,9 +315,10 @@ unsigned int jiffies_to_msecs(const unsigned long j)
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
- return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+ return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
+ HZ_TO_MSEC_SHR32;
# else
- return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+ return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index efed9c1cfb7e..caf9cbf35816 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
op->saved_func(ip, parent_ip, op, regs);
}
-/**
- * clear_ftrace_function - reset the ftrace function
- *
- * This NULLs the ftrace function and in essence stops
- * tracing. There may be lag
- */
-void clear_ftrace_function(void)
-{
- ftrace_trace_function = ftrace_stub;
-}
-
static void ftrace_sync(struct work_struct *work)
{
/*
@@ -6689,7 +6678,7 @@ void ftrace_kill(void)
{
ftrace_disabled = 1;
ftrace_enabled = 0;
- clear_ftrace_function();
+ ftrace_trace_function = ftrace_stub;
}
/**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c9336e98ac59..87cf25171fb8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1360,8 +1360,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf;
-
if (tr->stop_count)
return;
@@ -1375,9 +1373,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
- buf = tr->trace_buffer.buffer;
- tr->trace_buffer.buffer = tr->max_buffer.buffer;
- tr->max_buffer.buffer = buf;
+ swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
@@ -2957,6 +2953,7 @@ out_nobuffer:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
+__printf(3, 0)
static int
__trace_array_vprintk(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, va_list args)
@@ -3011,12 +3008,14 @@ out_nobuffer:
return len;
}
+__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}
+__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
@@ -3032,6 +3031,7 @@ int trace_array_printk(struct trace_array *tr,
return ret;
}
+__printf(3, 4)
int trace_array_printk_buf(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
@@ -3047,6 +3047,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
return ret;
}
+__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -3364,8 +3365,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
print_event_info(buf, m);
- seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
- seq_printf(m, "# | | | %s | |\n", tgid ? " | " : "");
+ seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
+ seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
}
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
@@ -3385,9 +3386,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
tgid ? tgid_space : space);
seq_printf(m, "# %s||| / delay\n",
tgid ? tgid_space : space);
- seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n",
+ seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n",
tgid ? " TGID " : space);
- seq_printf(m, "# | | | %s|||| | |\n",
+ seq_printf(m, "# | | %s | |||| | |\n",
tgid ? " | " : space);
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 630c5a24b2b2..f8f86231ad90 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -583,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit)
static inline struct ring_buffer_iter *
trace_buffer_iter(struct trace_iterator *iter, int cpu)
{
- if (iter->buffer_iter && iter->buffer_iter[cpu])
- return iter->buffer_iter[cpu];
- return NULL;
+ return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
}
int tracer_init(struct tracer *t, struct trace_array *tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e1c818dbc0d7..893a206bcba4 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -78,7 +78,8 @@ static const char * ops[] = { OPS };
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
- C(INVALID_VALUE, "Invalid value (did you forget quotes)?"),
+ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
+ C(NO_FILTER, "No filter found"),
#undef C
#define C(a, b) FILT_ERR_##a
@@ -550,6 +551,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
goto out_free;
}
+ if (!N) {
+ /* No program? */
+ ret = -EINVAL;
+ parse_error(pe, FILT_ERR_NO_FILTER, ptr - str);
+ goto out_free;
+ }
+
prog[N].pred = NULL; /* #13 */
prog[N].target = 1; /* TRUE */
prog[N+1].pred = NULL;
@@ -1693,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
* @filter_str: filter string
* @set_str: remember @filter_str and enable detailed error in filter
* @filterp: out param for created filter (always updated on return)
+ * Must be a pointer that references a NULL pointer.
*
* Creates a filter for @call with @filter_str. If @set_str is %true,
* @filter_str is copied and recorded in the new filter.
@@ -1710,6 +1719,10 @@ static int create_filter(struct trace_event_call *call,
struct filter_parse_error *pe = NULL;
int err;
+ /* filterp must point to NULL */
+ if (WARN_ON(*filterp))
+ *filterp = NULL;
+
err = create_filter_start(filter_string, set_str, &pe, filterp);
if (err)
return err;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 046c716a6536..aae18af94c94 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var)
else if (system)
snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
else
- strncpy(err, var, MAX_FILTER_STR_VAL);
+ strscpy(err, var, MAX_FILTER_STR_VAL);
hist_err(str, err);
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 23c0b0cb5fb9..169b3c44ee97 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
struct ftrace_graph_ret *graph_ret;
struct ftrace_graph_ent *call;
unsigned long long duration;
+ int cpu = iter->cpu;
int i;
graph_ret = &ret_entry->ret;
@@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter,
if (data) {
struct fgraph_cpu_data *cpu_data;
- int cpu = iter->cpu;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
@@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter,
trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+ cpu, iter->ent->pid, flags);
+
return trace_handle_return(s);
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..21f718472942 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1480,8 +1480,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
}
ret = __register_trace_kprobe(tk);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(tk->tp.call.print_fmt);
goto error;
+ }
return &tk->tp.call;
error:
@@ -1501,6 +1503,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
}
__unregister_trace_kprobe(tk);
+
+ kfree(tk->tp.call.print_fmt);
free_trace_kprobe(tk);
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 90db994ac900..1c8e30fda46a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
trace_seq_printf(s, "(%5d) ", tgid);
}
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
+
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);