summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/sockmap.c187
-rw-r--r--kernel/configs/kvm_guest.config1
-rw-r--r--kernel/events/core.c2
-rw-r--r--kernel/events/ring_buffer.c2
-rw-r--r--kernel/printk/printk.c6
-rw-r--r--kernel/relay.c4
-rw-r--r--kernel/time/posix-clock.c2
-rw-r--r--kernel/trace/ftrace.c1
-rw-r--r--kernel/trace/ring_buffer.c4
-rw-r--r--kernel/trace/trace.c4
-rw-r--r--kernel/trace/trace_events_filter.c9
11 files changed, 132 insertions, 90 deletions
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 0314d1783d77..48c33417d13c 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -86,9 +86,10 @@ struct smap_psock {
struct work_struct tx_work;
struct work_struct gc_work;
+ struct proto *sk_proto;
+ void (*save_close)(struct sock *sk, long timeout);
void (*save_data_ready)(struct sock *sk);
void (*save_write_space)(struct sock *sk);
- void (*save_state_change)(struct sock *sk);
};
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
@@ -96,12 +97,102 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
return rcu_dereference_sk_user_data(sk);
}
+static struct proto tcp_bpf_proto;
+static int bpf_tcp_init(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ if (unlikely(psock->sk_proto)) {
+ rcu_read_unlock();
+ return -EBUSY;
+ }
+
+ psock->save_close = sk->sk_prot->close;
+ psock->sk_proto = sk->sk_prot;
+ sk->sk_prot = &tcp_bpf_proto;
+ rcu_read_unlock();
+ return 0;
+}
+
+static void bpf_tcp_release(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+
+ if (likely(psock)) {
+ sk->sk_prot = psock->sk_proto;
+ psock->sk_proto = NULL;
+ }
+ rcu_read_unlock();
+}
+
+static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
+
+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 *psock;
+ struct sock *osk;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return sk->sk_prot->close(sk, timeout);
+ }
+
+ /* The psock may be destroyed anytime after exiting the RCU critial
+ * section so by the time we use close_fun the psock may no longer
+ * be valid. However, bpf_tcp_close is called with the sock lock
+ * held so the close hook and sk are still valid.
+ */
+ close_fun = psock->save_close;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ osk = cmpxchg(e->entry, sk, NULL);
+ if (osk == sk) {
+ list_del(&e->list);
+ smap_release_sock(psock, sk);
+ }
+ }
+ write_unlock_bh(&sk->sk_callback_lock);
+ rcu_read_unlock();
+ close_fun(sk, timeout);
+}
+
enum __sk_action {
__SK_DROP = 0,
__SK_PASS,
__SK_REDIRECT,
};
+static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = {
+ .name = "bpf_tcp",
+ .uid = TCP_ULP_BPF,
+ .user_visible = false,
+ .owner = NULL,
+ .init = bpf_tcp_init,
+ .release = bpf_tcp_release,
+};
+
+static int bpf_tcp_ulp_register(void)
+{
+ tcp_bpf_proto = tcp_prot;
+ tcp_bpf_proto.close = bpf_tcp_close;
+ return tcp_register_ulp(&bpf_tcp_ulp_ops);
+}
+
static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
{
struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
@@ -166,68 +257,6 @@ static void smap_report_sk_error(struct smap_psock *psock, int err)
sk->sk_error_report(sk);
}
-static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
-
-/* Called with lock_sock(sk) held */
-static void smap_state_change(struct sock *sk)
-{
- struct smap_psock_map_entry *e, *tmp;
- struct smap_psock *psock;
- struct socket_wq *wq;
- struct sock *osk;
-
- rcu_read_lock();
-
- /* Allowing transitions into an established syn_recv states allows
- * for early binding sockets to a smap object before the connection
- * is established.
- */
- switch (sk->sk_state) {
- case TCP_SYN_SENT:
- case TCP_SYN_RECV:
- case TCP_ESTABLISHED:
- break;
- case TCP_CLOSE_WAIT:
- case TCP_CLOSING:
- case TCP_LAST_ACK:
- case TCP_FIN_WAIT1:
- case TCP_FIN_WAIT2:
- case TCP_LISTEN:
- break;
- case TCP_CLOSE:
- /* Only release if the map entry is in fact the sock in
- * question. There is a case where the operator deletes
- * the sock from the map, but the TCP sock is closed before
- * the psock is detached. Use cmpxchg to verify correct
- * sock is removed.
- */
- psock = smap_psock_sk(sk);
- if (unlikely(!psock))
- break;
- write_lock_bh(&sk->sk_callback_lock);
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- osk = cmpxchg(e->entry, sk, NULL);
- if (osk == sk) {
- list_del(&e->list);
- smap_release_sock(psock, sk);
- }
- }
- write_unlock_bh(&sk->sk_callback_lock);
- break;
- default:
- psock = smap_psock_sk(sk);
- if (unlikely(!psock))
- break;
- smap_report_sk_error(psock, EPIPE);
- break;
- }
-
- wq = rcu_dereference(sk->sk_wq);
- if (skwq_has_sleeper(wq))
- wake_up_interruptible_all(&wq->wait);
- rcu_read_unlock();
-}
-
static void smap_read_sock_strparser(struct strparser *strp,
struct sk_buff *skb)
{
@@ -322,10 +351,8 @@ static void smap_stop_sock(struct smap_psock *psock, struct sock *sk)
return;
sk->sk_data_ready = psock->save_data_ready;
sk->sk_write_space = psock->save_write_space;
- sk->sk_state_change = psock->save_state_change;
psock->save_data_ready = NULL;
psock->save_write_space = NULL;
- psock->save_state_change = NULL;
strp_stop(&psock->strp);
psock->strp_enabled = false;
}
@@ -350,6 +377,7 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
if (psock->refcnt)
return;
+ tcp_cleanup_ulp(sock);
smap_stop_sock(psock, sock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
@@ -427,10 +455,8 @@ static void smap_start_sock(struct smap_psock *psock, struct sock *sk)
return;
psock->save_data_ready = sk->sk_data_ready;
psock->save_write_space = sk->sk_write_space;
- psock->save_state_change = sk->sk_state_change;
sk->sk_data_ready = smap_data_ready;
sk->sk_write_space = smap_write_space;
- sk->sk_state_change = smap_state_change;
psock->strp_enabled = true;
}
@@ -509,6 +535,10 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
if (attr->value_size > KMALLOC_MAX_SIZE)
return ERR_PTR(-E2BIG);
+ err = bpf_tcp_ulp_register();
+ if (err && err != -EEXIST)
+ return ERR_PTR(err);
+
stab = kzalloc(sizeof(*stab), GFP_USER);
if (!stab)
return ERR_PTR(-ENOMEM);
@@ -590,11 +620,6 @@ static void sock_map_free(struct bpf_map *map)
}
rcu_read_unlock();
- if (stab->bpf_verdict)
- bpf_prog_put(stab->bpf_verdict);
- if (stab->bpf_parse)
- bpf_prog_put(stab->bpf_parse);
-
sock_map_remove_complete(stab);
}
@@ -754,6 +779,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto out_progs;
}
+ err = tcp_set_ulp_id(sock, TCP_ULP_BPF);
+ if (err)
+ goto out_progs;
+
set_bit(SMAP_TX_RUNNING, &psock->state);
}
@@ -866,6 +895,19 @@ static int sock_map_update_elem(struct bpf_map *map,
return err;
}
+static void sock_map_release(struct bpf_map *map, struct file *map_file)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_prog *orig;
+
+ orig = xchg(&stab->bpf_parse, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+ orig = xchg(&stab->bpf_verdict, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+}
+
const struct bpf_map_ops sock_map_ops = {
.map_alloc = sock_map_alloc,
.map_free = sock_map_free,
@@ -873,6 +915,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_get_next_key = sock_map_get_next_key,
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
+ .map_release = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config
index 8d9643767142..108fecc20fc1 100644
--- a/kernel/configs/kvm_guest.config
+++ b/kernel/configs/kvm_guest.config
@@ -18,6 +18,7 @@ CONFIG_VIRTUALIZATION=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
CONFIG_KVM_GUEST=y
+CONFIG_S390_GUEST=y
CONFIG_VIRTIO=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_BLK=y
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f0549e79978b..96db9ae5d5af 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4524,7 +4524,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait)
{
struct perf_event *event = file->private_data;
struct ring_buffer *rb;
- __poll_t events = POLLHUP;
+ __poll_t events = EPOLLHUP;
poll_wait(file, &event->waitq, wait);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 141aa2ca8728..6c6b3c48db71 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -19,7 +19,7 @@
static void perf_output_wakeup(struct perf_output_handle *handle)
{
- atomic_set(&handle->rb->poll, POLLIN);
+ atomic_set(&handle->rb->poll, EPOLLIN);
handle->event->pending_wakeup = 1;
irq_work_queue(&handle->event->pending);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index db4b9b8929eb..fc1123583fa6 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -930,7 +930,7 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
__poll_t ret = 0;
if (!user)
- return POLLERR|POLLNVAL;
+ return EPOLLERR|EPOLLNVAL;
poll_wait(file, &log_wait, wait);
@@ -938,9 +938,9 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
if (user->seq < log_next_seq) {
/* return error when data has vanished underneath us */
if (user->seq < log_first_seq)
- ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
+ ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
else
- ret = POLLIN|POLLRDNORM;
+ ret = EPOLLIN|EPOLLRDNORM;
}
logbuf_unlock_irq();
diff --git a/kernel/relay.c b/kernel/relay.c
index f7f40a6e6352..c3029402f15c 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -924,12 +924,12 @@ static __poll_t relay_file_poll(struct file *filp, poll_table *wait)
struct rchan_buf *buf = filp->private_data;
if (buf->finalized)
- return POLLERR;
+ return EPOLLERR;
if (filp->f_mode & FMODE_READ) {
poll_wait(filp, &buf->read_wait, wait);
if (!relay_buf_empty(buf))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
return mask;
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 94ad46d50b56..fe56c4e06c51 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -74,7 +74,7 @@ static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
__poll_t result = 0;
if (!clk)
- return POLLERR;
+ return EPOLLERR;
if (clk->ops.poll)
result = clk->ops.poll(clk, fp, wait);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index dabd9d167d42..eac9ce2c57a2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4456,7 +4456,6 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
func_g.type = filter_parse_regex(glob, strlen(glob),
&func_g.search, &not);
func_g.len = strlen(func_g.search);
- func_g.search = glob;
/* we do not support '!' for function probes */
if (WARN_ON(not))
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ca6930e0d25e..dcf1c4dd3efe 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -627,7 +627,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
* as data is added to any of the @buffer's cpu buffers. Otherwise
* it will wait for data to be added to a specific cpu buffer.
*
- * Returns POLLIN | POLLRDNORM if data exists in the buffers,
+ * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers,
* zero otherwise.
*/
__poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
@@ -665,7 +665,7 @@ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
(cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 56608538a4ad..20a2300ae4e8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5623,13 +5623,13 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (tr->trace_flags & TRACE_ITER_BLOCK)
/*
* Always select as readable when in blocking mode
*/
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
else
return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file,
filp, poll_table);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 61e7f0678d33..a764aec3c9a1 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -400,7 +400,6 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
for (i = 0; i < len; i++) {
if (buff[i] == '*') {
if (!i) {
- *search = buff + 1;
type = MATCH_END_ONLY;
} else if (i == len - 1) {
if (type == MATCH_END_ONLY)
@@ -410,14 +409,14 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
buff[i] = 0;
break;
} else { /* pattern continues, use full glob */
- type = MATCH_GLOB;
- break;
+ return MATCH_GLOB;
}
} else if (strchr("[?\\", buff[i])) {
- type = MATCH_GLOB;
- break;
+ return MATCH_GLOB;
}
}
+ if (buff[0] == '*')
+ *search = buff + 1;
return type;
}