connector/cn_proc: Performance improvements

This patch adds the capability to filter messages sent by the proc
connector on the event type supplied in the message from the client
to the connector. The client can register to listen for an event type
given in struct proc_input.

This event based filteting will greatly enhance performance - handling
8K exits takes about 70ms, whereas 8K-forks + 8K-exits takes about 150ms
& handling 8K-forks + 8K-exits + 8K-execs takes 200ms. There are currently
9 different types of events, and we need to listen to all of them. Also,
measuring the time using pidfds for monitoring 8K process exits took
much longer - 200ms, as compared to 70ms using only exit notifications of
proc connector.

We also add a new event type - PROC_EVENT_NONZERO_EXIT, which is
only sent by kernel to a listening application when any process exiting,
has a non-zero exit status. This will help the clients like Oracle DB,
where a monitoring process wants notfications for non-zero process exits
so it can cleanup after them.

This kind of a new event could also be useful to other applications like
Google's lmkd daemon, which needs a killed process's exit notification.

The patch takes care that existing clients using old mechanism of not
sending the event type work without any changes.

cn_filter function checks to see if the event type being notified via
proc connector matches the event type requested by client, before
sending(matches) or dropping(does not match) a packet.
Signed-off-by: Anjali Kulkarni <anjali.k.kulkarni@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/connector/cn_proc.c

@@ -50,21 +50,45 @@ static DEFINE_PER_CPU(struct local_event, local_event) = {
 
 static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data)
 {
+	__u32 what, exit_code, *ptr;
 	enum proc_cn_mcast_op mc_op;
+	uintptr_t val;
 
-	if (!dsk)
+	if (!dsk || !data)
 		return 0;
 
+	ptr = (__u32 *)data;
+	what = *ptr++;
+	exit_code = *ptr;
+	val = ((struct proc_input *)(dsk->sk_user_data))->event_type;
 	mc_op = ((struct proc_input *)(dsk->sk_user_data))->mcast_op;
 
 	if (mc_op == PROC_CN_MCAST_IGNORE)
 		return 1;
 
-	return 0;
+	if ((__u32)val == PROC_EVENT_ALL)
+		return 0;
+
+	/*
+	 * Drop packet if we have to report only non-zero exit status
+	 * (PROC_EVENT_NONZERO_EXIT) and exit status is 0
+	 */
+	if (((__u32)val & PROC_EVENT_NONZERO_EXIT) &&
+	    (what == PROC_EVENT_EXIT)) {
+		if (exit_code)
+			return 0;
+	}
+
+	if ((__u32)val & what)
+		return 0;
+
+	return 1;
 }
 
 static inline void send_msg(struct cn_msg *msg)
 {
+	__u32 filter_data[2];
+
 	local_lock(&local_event.lock);
 
 	msg->seq = __this_cpu_inc_return(local_event.count) - 1;
@@ -76,8 +100,16 @@ static inline void send_msg(struct cn_msg *msg)
 	 *
 	 * If cn_netlink_send() fails, the data is not sent.
 	 */
+	filter_data[0] = ((struct proc_event *)msg->data)->what;
+	if (filter_data[0] == PROC_EVENT_EXIT) {
+		filter_data[1] =
+		((struct proc_event *)msg->data)->event_data.exit.exit_code;
+	} else {
+		filter_data[1] = 0;
+	}
+
 	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, NULL);
+			     cn_filter, (void *)filter_data);
 
 	local_unlock(&local_event.lock);
 }
@@ -357,12 +389,15 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 
 /**
  * cn_proc_mcast_ctl
- * @data: message sent from userspace via the connector
+ * @msg: message sent from userspace via the connector
+ * @nsp: NETLINK_CB of the client's socket buffer
  */
 static void cn_proc_mcast_ctl(struct cn_msg *msg,
 			      struct netlink_skb_parms *nsp)
 {
 	enum proc_cn_mcast_op mc_op = 0, prev_mc_op = 0;
+	struct proc_input *pinput = NULL;
+	enum proc_cn_event ev_type = 0;
 	int err = 0, initial = 0;
 	struct sock *sk = NULL;
 
@@ -381,10 +416,21 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 		goto out;
 	}
 
-	if (msg->len == sizeof(mc_op))
+	if (msg->len == sizeof(*pinput)) {
+		pinput = (struct proc_input *)msg->data;
+		mc_op = pinput->mcast_op;
+		ev_type = pinput->event_type;
+	} else if (msg->len == sizeof(mc_op)) {
 		mc_op = *((enum proc_cn_mcast_op *)msg->data);
-	else
+		ev_type = PROC_EVENT_ALL;
+	} else {
 		return;
+	}
+
+	ev_type = valid_event((enum proc_cn_event)ev_type);
+
+	if (ev_type == PROC_EVENT_NONE)
+		ev_type = PROC_EVENT_ALL;
 
 	if (nsp->sk) {
 		sk = nsp->sk;
@@ -400,6 +446,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 			prev_mc_op =
 			((struct proc_input *)(sk->sk_user_data))->mcast_op;
 		}
+		((struct proc_input *)(sk->sk_user_data))->event_type =
+			ev_type;
 		((struct proc_input *)(sk->sk_user_data))->mcast_op = mc_op;
 	}
 
@@ -411,6 +459,8 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 	case PROC_CN_MCAST_IGNORE:
 		if (!initial && (prev_mc_op != PROC_CN_MCAST_IGNORE))
 			atomic_dec(&proc_event_num_listeners);
+		((struct proc_input *)(sk->sk_user_data))->event_type =
+			PROC_EVENT_NONE;
 		break;
 	default:
 		err = EINVAL;

include/uapi/linux/cn_proc.h

@@ -30,6 +30,15 @@ enum proc_cn_mcast_op {
 	PROC_CN_MCAST_IGNORE = 2
 };
 
+#define PROC_EVENT_ALL (PROC_EVENT_FORK | PROC_EVENT_EXEC | PROC_EVENT_UID |  \
+			PROC_EVENT_GID | PROC_EVENT_SID | PROC_EVENT_PTRACE | \
+			PROC_EVENT_COMM | PROC_EVENT_NONZERO_EXIT |           \
+			PROC_EVENT_COREDUMP | PROC_EVENT_EXIT)
+
+/*
+ * If you add an entry in proc_cn_event, make sure you add it in
+ * PROC_EVENT_ALL above as well.
+ */
 enum proc_cn_event {
 	/* Use successive bits so the enums can be used to record
 	 * sets of events as well
@@ -45,15 +54,25 @@ enum proc_cn_event {
 	/* "next" should be 0x00000400 */
 	/* "last" is the last process event: exit,
 	 * while "next to last" is coredumping event
+	 * before that is report only if process dies
+	 * with non-zero exit status
 	 */
+	PROC_EVENT_NONZERO_EXIT = 0x20000000,
 	PROC_EVENT_COREDUMP = 0x40000000,
 	PROC_EVENT_EXIT = 0x80000000
 };
 
 struct proc_input {
 	enum proc_cn_mcast_op mcast_op;
+	enum proc_cn_event event_type;
 };
 
+static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type)
+{
+	ev_type &= PROC_EVENT_ALL;
+	return ev_type;
+}
+
 /*
  * From the user's point of view, the process
  * ID is the thread group ID and thread ID is the internal