6.1.191-rc1 review

index b9a470038ab33..fe2905e804083 100644
@@ -1529,6 +1529,464 @@ TEST_F(tls, recv_efault)
 		EXPECT_EQ(memcmp(rec2, recv_mem + 9, ret - 9), 0);
 }
 
+#define TLS_RECORD_TYPE_HANDSHAKE      0x16
+/* key_update, length 1, update_not_requested */
+static const char key_update_msg[] = "\x18\x00\x00\x01\x00";
+static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd)
+{
+	size_t len = sizeof(key_update_msg);
+
+	EXPECT_EQ(tls_send_cmsg(fd, TLS_RECORD_TYPE_HANDSHAKE,
+				(char *)key_update_msg, len, 0),
+		  len);
+}
+
+static void tls_recv_keyupdate(struct __test_metadata *_metadata, int fd, int flags)
+{
+	char buf[100];
+
+	EXPECT_EQ(tls_recv_cmsg(_metadata, fd, TLS_RECORD_TYPE_HANDSHAKE, buf, sizeof(buf), flags),
+		  sizeof(key_update_msg));
+	EXPECT_EQ(memcmp(buf, key_update_msg, sizeof(key_update_msg)), 0);
+}
+
+/* set the key to 0 then 1 for RX, immediately to 1 for TX */
+TEST_F(tls_basic, rekey_rx)
+{
+	struct tls_crypto_info_keys tls12_0, tls12_1;
+	char const *test_str = "test_message";
+	int send_len = strlen(test_str) + 1;
+	char buf[20];
+	int ret;
+
+	if (self->notls)
+		return;
+
+	tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+			     &tls12_0, 0);
+	tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+			     &tls12_1, 1);
+
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_0, tls12_0.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len);
+	EXPECT_EQ(ret, 0);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+/* set the key to 0 then 1 for TX, immediately to 1 for RX */
+TEST_F(tls_basic, rekey_tx)
+{
+	struct tls_crypto_info_keys tls12_0, tls12_1;
+	char const *test_str = "test_message";
+	int send_len = strlen(test_str) + 1;
+	char buf[20];
+	int ret;
+
+	if (self->notls)
+		return;
+
+	tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+			     &tls12_0, 0);
+	tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+			     &tls12_1, 1);
+
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_0, tls12_0.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len);
+	EXPECT_EQ(ret, 0);
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, rekey)
+{
+	char const *test_str_1 = "test_message_before_rekey";
+	char const *test_str_2 = "test_message_after_rekey";
+	struct tls_crypto_info_keys tls12;
+	int send_len;
+	char buf[100];
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	/* initial send/recv */
+	send_len = strlen(test_str_1) + 1;
+	EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	/* send after rekey */
+	send_len = strlen(test_str_2) + 1;
+	EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len);
+
+	/* can't receive the KeyUpdate without a control message */
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	/* recv blocking -> -EKEYEXPIRED */
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EKEYEXPIRED);
+
+	/* recv non-blocking -> -EKEYEXPIRED */
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+	EXPECT_EQ(errno, EKEYEXPIRED);
+
+	/* update RX key */
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+	/* recv after rekey */
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0);
+}
+
+TEST_F(tls, rekey_fail)
+{
+	char const *test_str_1 = "test_message_before_rekey";
+	char const *test_str_2 = "test_message_after_rekey";
+	struct tls_crypto_info_keys tls12;
+	int send_len;
+	char buf[100];
+
+	/* initial send/recv */
+	send_len = strlen(test_str_1) + 1;
+	EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+
+	if (variant->tls_version != TLS_1_3_VERSION) {
+		/* just check that rekey is not supported and return */
+		tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+		EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+		EXPECT_EQ(errno, EBUSY);
+		return;
+	}
+
+	/* successful update */
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	/* invalid update: change of version */
+	tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* invalid update (RX socket): change of version */
+	tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* invalid update: change of cipher */
+	if (variant->cipher_type == TLS_CIPHER_AES_GCM_256)
+		tls_crypto_info_init(variant->tls_version, TLS_CIPHER_CHACHA20_POLY1305, &tls12, 1);
+	else
+		tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_256, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* send after rekey, the invalid updates shouldn't have an effect */
+	send_len = strlen(test_str_2) + 1;
+	EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len);
+
+	/* can't receive the KeyUpdate without a control message */
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	/* recv blocking -> -EKEYEXPIRED */
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EKEYEXPIRED);
+
+	/* recv non-blocking -> -EKEYEXPIRED */
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+	EXPECT_EQ(errno, EKEYEXPIRED);
+
+	/* update RX key */
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+	/* recv after rekey */
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0);
+}
+
+TEST_F(tls, rekey_peek)
+{
+	char const *test_str_1 = "test_message_before_rekey";
+	struct tls_crypto_info_keys tls12;
+	int send_len;
+	char buf[100];
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	send_len = strlen(test_str_1) + 1;
+	EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+	/* can't receive the KeyUpdate without a control message */
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+
+	/* peek KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	/* update RX key */
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+}
+
+TEST_F(tls, splice_rekey)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN / 2;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	struct tls_crypto_info_keys tls12;
+	int p[2];
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	memrnd(mem_send, sizeof(mem_send));
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+	EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+
+	/* can't splice the KeyUpdate */
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* peek KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	/* can't splice before updating the key */
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1);
+	EXPECT_EQ(errno, EKEYEXPIRED);
+
+	/* update RX key */
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+	EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, rekey_peek_splice)
+{
+	char const *test_str_1 = "test_message_before_rekey";
+	struct tls_crypto_info_keys tls12;
+	int send_len;
+	char buf[100];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int p[2];
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	ASSERT_GE(pipe(p), 0);
+
+	send_len = strlen(test_str_1) + 1;
+	EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len);
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len);
+	EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0);
+
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len);
+	EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+	EXPECT_EQ(memcmp(mem_recv, test_str_1, send_len), 0);
+}
+
+TEST_F(tls, rekey_getsockopt)
+{
+	struct tls_crypto_info_keys tls12;
+	struct tls_crypto_info_keys tls12_get;
+	socklen_t len;
+
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 0);
+
+	len = tls12.len;
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0);
+	EXPECT_EQ(len, tls12.len);
+	EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+	len = tls12.len;
+	EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0);
+	EXPECT_EQ(len, tls12.len);
+	EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+	EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+	len = tls12.len;
+	EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0);
+	EXPECT_EQ(len, tls12.len);
+	EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+
+	len = tls12.len;
+	EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0);
+	EXPECT_EQ(len, tls12.len);
+	EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0);
+}
+
+TEST_F(tls, rekey_poll_pending)
+{
+	char const *test_str = "test_message_after_rekey";
+	struct tls_crypto_info_keys tls12;
+	struct pollfd pfd = { };
+	int send_len;
+	int ret;
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	/* send immediately after rekey */
+	send_len = strlen(test_str) + 1;
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+	/* key hasn't been updated, expect cfd to be non-readable */
+	pfd.fd = self->cfd;
+	pfd.events = POLLIN;
+	EXPECT_EQ(poll(&pfd, 1, 0), 0);
+
+	ret = fork();
+	ASSERT_GE(ret, 0);
+
+	if (ret) {
+		int pid2, status;
+
+		/* wait before installing the new key */
+		sleep(1);
+
+		/* update RX key while poll() is sleeping */
+		EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+		pid2 = wait(&status);
+		EXPECT_EQ(pid2, ret);
+		EXPECT_EQ(status, 0);
+	} else {
+		pfd.fd = self->cfd;
+		pfd.events = POLLIN;
+		EXPECT_EQ(poll(&pfd, 1, 5000), 1);
+
+		exit(!__test_passed(_metadata));
+	}
+}
+
+TEST_F(tls, rekey_poll_delay)
+{
+	char const *test_str = "test_message_after_rekey";
+	struct tls_crypto_info_keys tls12;
+	struct pollfd pfd = { };
+	int send_len;
+	int ret;
+
+	if (variant->tls_version != TLS_1_3_VERSION)
+		return;
+
+	/* update TX key */
+	tls_send_keyupdate(_metadata, self->fd);
+	tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1);
+	EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0);
+
+	/* get KeyUpdate */
+	tls_recv_keyupdate(_metadata, self->cfd, 0);
+
+	ret = fork();
+	ASSERT_GE(ret, 0);
+
+	if (ret) {
+		int pid2, status;
+
+		/* wait before installing the new key */
+		sleep(1);
+
+		/* update RX key while poll() is sleeping */
+		EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0);
+
+		sleep(1);
+		send_len = strlen(test_str) + 1;
+		EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+		pid2 = wait(&status);
+		EXPECT_EQ(pid2, ret);
+		EXPECT_EQ(status, 0);
+	} else {
+		pfd.fd = self->cfd;
+		pfd.events = POLLIN;
+		EXPECT_EQ(poll(&pfd, 1, 5000), 1);
+		exit(!__test_passed(_metadata));
+	}
+}
+
 FIXTURE(tls_err)
 {
 	int fd, cfd;

index 68b8a59684e30..2aeeeca57da65 100644
@@ -1807,6 +1807,8 @@ tls_decrypt_sw(struct sock *sk, struct tls_context *tls_ctx,
 	/* If opportunistic TLS 1.3 ZC failed retry without ZC */
 	if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION &&
 		     darg->tail != TLS_RECORD_TYPE_DATA)) {
+		iov_iter_revert(&msg->msg_iter, strp_msg(darg->skb)->full_len -
+				prot->overhead_size);
 		darg->zc = false;
 		if (!darg->tail)
 			TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL);

63 lines not on this page · raw message

index 9124601d658b4..5b4b07e669cd1 100644
@@ -1179,10 +1179,21 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	skb_reset_mac_header(skb);
 	skb->protocol = eth_hdr(skb)->h_proto;
 
+	rcu_read_lock();
+	tap = rcu_dereference(q->tap);
+	if (!tap) {
+		kfree_skb(skb);
+		rcu_read_unlock();
+		return 0;
+	}
+	skb->dev = tap->dev;
+
 	if (vnet_hdr_len) {
 		err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q));
-		if (err)
+		if (err) {
+			rcu_read_unlock();
 			goto err_kfree;
+		}
 	}
 
 	/* Move network header to the right position for VLAN tagged packets */

@@ -1190,15 +1201,8 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
 		skb_set_network_header(skb, depth);
 
-	rcu_read_lock();
-	tap = rcu_dereference(q->tap);
-	if (tap) {
-		skb->dev = tap->dev;
-		skb_probe_transport_header(skb);
-		dev_queue_xmit(skb);
-	} else {
-		kfree_skb(skb);
-	}
+	skb_probe_transport_header(skb);
+	dev_queue_xmit(skb);
 	rcu_read_unlock();
 
 	return 0;

index fed7be2464420..4e5171f4d0061 100644
@@ -242,7 +242,7 @@ static int at91_wdt_init(struct platform_device *pdev, struct at91wdt *wdt)
 	return 0;
 
 out_stop_timer:
-	del_timer(&wdt->timer);
+	timer_shutdown_sync(&wdt->timer);
 	return err;
 }
 

@@ -387,7 +387,7 @@ static int __exit at91wdt_remove(struct platform_device *pdev)
 	watchdog_unregister_device(&wdt->wdd);
 
 	pr_warn("I quit now, hardware will probably reboot!\n");
-	del_timer(&wdt->timer);
+	timer_shutdown_sync(&wdt->timer);
 	clk_disable_unprepare(wdt->sclk);
 
 	return 0;

index 9576e3975c721..c4150dba6cd44 100644
@@ -153,13 +153,16 @@ static int unregister_sba(struct ism_dev *ism)
 	if (ret && ret != ISM_ERROR)
 		return -EIO;
 
+	return 0;
+}
+
+static void ism_free_sba(struct ism_dev *ism)
+{
 	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
 			  ism->sba, ism->sba_dma_addr);
 
 	ism->sba = NULL;
 	ism->sba_dma_addr = 0;
-
-	return 0;
 }
 
 static int unregister_ieq(struct ism_dev *ism)

@@ -173,13 +176,16 @@ static int unregister_ieq(struct ism_dev *ism)
 	if (ret && ret != ISM_ERROR)
 		return -EIO;
 
+	return 0;
+}
+
+static void ism_free_ieq(struct ism_dev *ism)
+{
 	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
 			  ism->ieq, ism->ieq_dma_addr);
 
 	ism->ieq = NULL;
 	ism->ieq_dma_addr = 0;
-
-	return 0;
 }
 
 static int ism_read_local_gid(struct ism_dev *ism)

@@ -537,8 +543,10 @@ static int ism_dev_init(struct ism_dev *ism)
 
 unreg_ieq:
 	unregister_ieq(ism);
+	ism_free_ieq(ism);
 unreg_sba:
 	unregister_sba(ism);
+	ism_free_sba(ism);
 free_irq:
 	free_irq(pci_irq_vector(pdev, 0), ism);
 free_vectors:

@@ -611,9 +619,13 @@ static void ism_dev_exit(struct ism_dev *ism)
 	if (SYSTEM_EID.serial_number[0] != '0' ||
 	    SYSTEM_EID.type[0] != '0')
 		ism_del_vlan_id(ism->smcd, ISM_RESERVED_VLANID);
+	/* ism will only generate new IRQs while ieq & sba are registered */
 	unregister_ieq(ism);
 	unregister_sba(ism);
+	/* drain ongoing irpt handlers */
 	free_irq(pci_irq_vector(pdev, 0), ism);
+	ism_free_ieq(ism);
+	ism_free_sba(ism);
 	pci_free_irq_vectors(pdev);
 }
 

index 523228e969ab4..cd744ac065cd0 100644
@@ -262,6 +262,7 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
 				      struct dst_entry *dst)
 {
 	skb_orphan(skb);
+	skb_dst_drop(skb);
 	skb_dst_set_noref(skb, dst);
 	dst_output(state->net, state->sk, skb);
 	return NF_STOLEN;

@@ -417,6 +418,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 		outdev = rt->dst.dev;
 		skb->dev = outdev;
 		nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 		neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
 		ret = NF_STOLEN;

@@ -678,6 +680,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 		outdev = rt->dst.dev;
 		skb->dev = outdev;
 		nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
+		skb_dst_drop(skb);
 		skb_dst_set_noref(skb, &rt->dst);
 		neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
 		ret = NF_STOLEN;

index ae7b5535eeb13..b3c7325339eb7 100644
@@ -477,6 +477,7 @@ struct tcf_block {
 	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
+	atomic_t skipswcnt; /* Number of skip_sw filters */
 	atomic_t offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
 	unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */

index 44139ca96a1e7..44215aada059b 100644
@@ -3302,6 +3302,8 @@ static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
 	if (*flags & TCA_CLS_FLAGS_IN_HW)
 		return;
 	*flags |= TCA_CLS_FLAGS_IN_HW;
+	if (tc_skip_sw(*flags))
+		atomic_inc(&block->skipswcnt);
 	atomic_inc(&block->offloadcnt);
 }
 

@@ -3310,6 +3312,8 @@ static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags)
 	if (!(*flags & TCA_CLS_FLAGS_IN_HW))
 		return;
 	*flags &= ~TCA_CLS_FLAGS_IN_HW;
+	if (tc_skip_sw(*flags))
+		atomic_dec(&block->skipswcnt);
 	atomic_dec(&block->offloadcnt);
 }
 

index b3c7325339eb7..58235cbd14084 100644
@@ -429,6 +429,7 @@ struct tcf_proto {
 	 */
 	spinlock_t		lock;
 	bool			deleting;
+	bool			counted;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
 	struct hlist_node	destroy_ht_node;

@@ -477,6 +478,7 @@ struct tcf_block {
 	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
+	atomic_t filtercnt; /* Number of filters */
 	atomic_t skipswcnt; /* Number of skip_sw filters */
 	atomic_t offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */

index 44215aada059b..99eec1f27d878 100644
@@ -305,12 +305,30 @@ static void tcf_proto_get(struct tcf_proto *tp)
 	refcount_inc(&tp->refcnt);
 }
 
+static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add)
+{
+	lockdep_assert_not_held(&block->cb_lock);
+
+	down_write(&block->cb_lock);
+	if (*counted != add) {
+		if (add) {
+			atomic_inc(&block->filtercnt);
+			*counted = true;
+		} else {
+			atomic_dec(&block->filtercnt);
+			*counted = false;
+		}
+	}
+	up_write(&block->cb_lock);
+}
+
 static void tcf_chain_put(struct tcf_chain *chain);
 
 static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
 			      bool sig_destroy, struct netlink_ext_ack *extack)
 {
 	tp->ops->destroy(tp, rtnl_held, extack);
+	tcf_block_filter_cnt_update(tp->chain->block, &tp->counted, false);
 	if (sig_destroy)
 		tcf_proto_signal_destroyed(tp->chain, tp);
 	tcf_chain_put(tp->chain);

@@ -2208,6 +2226,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      flags, extack);
 	if (err == 0) {
+		tcf_block_filter_cnt_update(block, &tp->counted, true);
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held, extack);
 		tfilter_put(tp, fh);

index 99eec1f27d878..c645d89cf4fba 100644
@@ -2226,10 +2226,10 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      flags, extack);
 	if (err == 0) {
-		tcf_block_filter_cnt_update(block, &tp->counted, true);
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held, extack);
 		tfilter_put(tp, fh);
+		tcf_block_filter_cnt_update(block, &tp->counted, true);
 		/* q pointer is NULL for shared blocks */
 		if (q)
 			q->flags &= ~TCQ_F_CAN_BYPASS;

index 42ddb2689b8ec..2ef3c220d52ca 100644
@@ -70,6 +70,10 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block)
 	return block && block->index;
 }
 
+#ifdef CONFIG_NET_CLS_ACT
+DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key);
+#endif
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	WARN_ON(tcf_block_shared(block));

@@ -762,6 +766,15 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
 		cls_common->extack = extack;
 }
 
+static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags)
+{
+	if (tp->usesw)
+		return;
+	if (tc_skip_sw(flags) && tc_in_hw(flags))
+		return;
+	tp->usesw = true;
+}
+
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
 {

index 58235cbd14084..9310e02d27c88 100644
@@ -430,6 +430,7 @@ struct tcf_proto {
 	spinlock_t		lock;
 	bool			deleting;
 	bool			counted;
+	bool			usesw;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
 	struct hlist_node	destroy_ht_node;

@@ -478,8 +479,7 @@ struct tcf_block {
 	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
-	atomic_t filtercnt; /* Number of filters */
-	atomic_t skipswcnt; /* Number of skip_sw filters */
+	atomic_t useswcnt;
 	atomic_t offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
 	unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */

index c8d0f98d375e6..06f4f0f2421b4 100644
@@ -2121,6 +2121,11 @@ void net_dec_egress_queue(void)
 EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 #endif
 
+#ifdef CONFIG_NET_CLS_ACT
+DEFINE_STATIC_KEY_FALSE(tcf_sw_enabled_key);
+EXPORT_SYMBOL(tcf_sw_enabled_key);
+#endif
+
 DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
 EXPORT_SYMBOL(netstamp_needed_key);
 #ifdef CONFIG_JUMP_LABEL

82 lines not on this page · raw message

index 00159978c4501..ff0a8dd0b9548 100644
@@ -507,6 +507,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	if (!tc_in_hw(prog->gen_flags))
 		prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
+	tcf_proto_update_usesw(tp, prog->gen_flags);
+
 	if (oldprog) {
 		idr_replace(&head->handle_idr, prog, handle);
 		list_replace_rcu(&oldprog->link, &prog->link);

index 42234a0101e78..67e0a9799bd0c 100644
@@ -2240,6 +2240,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (!tc_in_hw(fnew->flags))
 		fnew->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
+	tcf_proto_update_usesw(tp, fnew->flags);
+
 	spin_lock(&tp->lock);
 
 	/* tp was deleted concurrently. -EAGAIN will cause caller to lookup

index 43f8df5847414..d4bb817b3658a 100644
@@ -226,6 +226,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 	if (!tc_in_hw(new->flags))
 		new->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
+	tcf_proto_update_usesw(tp, new->flags);
+
 	*arg = head;
 	rcu_assign_pointer(tp->root, new);
 	return 0;

index d1f2d194d2267..599563b43def0 100644
@@ -964,6 +964,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (!tc_in_hw(new->flags))
 			new->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
+		tcf_proto_update_usesw(tp, new->flags);
+
 		u32_replace_knode(tp, tp_c, new);
 		tcf_unbind_filter(tp, &n->res);
 		tcf_exts_get_net(&n->exts);

@@ -1196,6 +1198,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (!tc_in_hw(n->flags))
 			n->flags |= TCA_CLS_FLAGS_NOT_IN_HW;
 
+		tcf_proto_update_usesw(tp, n->flags);
+
 		ins = &ht->ht[TC_U32_HASH(handle)];
 		for (pins = rtnl_dereference(*ins); pins;
 		     ins = &pins->next, pins = rtnl_dereference(*ins))

index ad8514da40c80..603b7caebad2b 100644
@@ -338,7 +338,22 @@ static void tcf_chain_put(struct tcf_chain *chain);
 static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
 			      bool sig_destroy, struct netlink_ext_ack *extack)
 {
-	tp->ops->destroy(tp, rtnl_held, extack);
+	/* A locked classifier's destroy callback (e.g. u32_destroy) uses
+	 * rtnl_dereference() and mutates shared structures (e.g. the
+	 * tc_u_common hash list) that are only safe under rtnl_lock. When an
+	 * unlocked classifier's request (e.g. flower on ingress) loses the
+	 * tcf_chain_tp_insert_unique() race and ends up dropping the last
+	 * reference on a locked classifier's proto, destroy() would run
+	 * without rtnl held. Take it here in that case.
+	 */
+	bool not_lockless = !rtnl_held &&
+		!(tp->ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED);
+
+	if (not_lockless)
+		rtnl_lock();
+	tp->ops->destroy(tp, rtnl_held || not_lockless, extack);
+	if (not_lockless)
+		rtnl_unlock();
 	tcf_proto_count_usesw(tp, false);
 	if (sig_destroy)
 		tcf_proto_signal_destroyed(tp->chain, tp);

index b53420e874acb..9727b4352c40b 100644
@@ -11,6 +11,8 @@
 
 #define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
 
+extern int mlx5_vdpa_max_iotlb_entries;
+
 struct mlx5_vdpa_direct_mr {
 	u64 start;
 	u64 end;

index 41489d4371f35..2c0e3ae87476a 100644
@@ -562,6 +562,9 @@ static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev,
 	if (mr->initialized)
 		return 0;
 
+	if (mlx5_vdpa_max_iotlb_entries < 2)
+		return -EINVAL;
+
 	if (iotlb)
 		err = create_user_mr(mvdev, iotlb);
 	else

index 9800f9bec225a..f249f98a3e174 100644
@@ -3,8 +3,14 @@
 
 #include <linux/iova.h>
 #include <linux/mlx5/driver.h>
+#include <linux/moduleparam.h>
 #include "mlx5_vdpa.h"
 
+int mlx5_vdpa_max_iotlb_entries = 2048;
+module_param_named(max_iotlb_entries, mlx5_vdpa_max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+		 "Maximum number of iotlb entries. (default: 2048)");
+
 static int alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;

@@ -229,7 +235,10 @@ int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey)
 
 static int init_ctrl_vq(struct mlx5_vdpa_dev *mvdev)
 {
-	mvdev->cvq.iotlb = vhost_iotlb_alloc(0, 0);
+	if (mlx5_vdpa_max_iotlb_entries < 2)
+		return -EINVAL;
+
+	mvdev->cvq.iotlb = vhost_iotlb_alloc(mlx5_vdpa_max_iotlb_entries, 0);
 	if (!mvdev->cvq.iotlb)
 		return -ENOMEM;
 

index 74d8de5f1e8ba..68d63bb17cac9 100644
@@ -34,7 +34,7 @@ MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
 static int max_iotlb_entries = 2048;
 module_param(max_iotlb_entries, int, 0444);
 MODULE_PARM_DESC(max_iotlb_entries,
-		 "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)");
+		 "Maximum number of iotlb entries for each address space. (default: 2048)");
 
 #define VDPASIM_QUEUE_ALIGN PAGE_SIZE
 #define VDPASIM_QUEUE_MAX 256

@@ -266,6 +266,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
 	struct device *dev;
 	int i, ret = -ENOMEM;
 
+	if (max_iotlb_entries < 2)
+		return ERR_PTR(-EINVAL);
+
 	if (config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
 		if (config->device_features &
 		    ~dev_attr->supported_features)

index 82b796332564b..e60a2b4065af9 100644
@@ -12,11 +12,17 @@
 #include <linux/file.h>
 #include <linux/anon_inodes.h>
 #include <linux/highmem.h>
+#include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
 #include <linux/vdpa.h>
 
 #include "iova_domain.h"
 
+static int max_iotlb_entries = 2048;
+module_param(max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+		 "Maximum number of iotlb entries. (default: 2048)");
+
 static int vduse_iotlb_add_range(struct vduse_iova_domain *domain,
 				 u64 start, u64 last,
 				 u64 addr, unsigned int perm,

@@ -608,11 +614,14 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size)
 	if (iova_limit <= bounce_size)
 		return NULL;
 
+	if (max_iotlb_entries <= 0)
+		return NULL;
+
 	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
 	if (!domain)
 		return NULL;
 
-	domain->iotlb = vhost_iotlb_alloc(0, 0);
+	domain->iotlb = vhost_iotlb_alloc(max_iotlb_entries, 0);
 	if (!domain->iotlb)
 		goto err_iotlb;
 

80 lines not on this page · raw message

index 27a7a168e5bd9..03bc085358ad3 100644
@@ -34,6 +34,11 @@ enum {
 
 #define VHOST_VDPA_DEV_MAX (1U << MINORBITS)
 
+static int max_iotlb_entries = 2048;
+module_param(max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+		 "Maximum number of iotlb entries. (default: 2048)");
+
 #define VHOST_VDPA_IOTLB_BUCKETS 16
 
 struct vhost_vdpa_as {

@@ -108,12 +113,14 @@ static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)
 
 	if (asid >= v->vdpa->nas)
 		return NULL;
+	if (max_iotlb_entries <= 0)
+		return NULL;
 
 	as = kmalloc(sizeof(*as), GFP_KERNEL);
 	if (!as)
 		return NULL;
 
-	vhost_iotlb_init(&as->iotlb, 0, 0);
+	vhost_iotlb_init(&as->iotlb, max_iotlb_entries, 0);
 	as->id = asid;
 	hlist_add_head(&as->hash_link, head);
 

index 85d4585c526cc..d68f61cef67e2 100644
@@ -622,6 +622,9 @@ EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
 
 static struct vhost_iotlb *iotlb_alloc(void)
 {
+	if (max_iotlb_entries <= 0)
+		return NULL;
+
 	return vhost_iotlb_alloc(max_iotlb_entries,
 				 VHOST_IOTLB_FLAG_RETIRE);
 }

@@ -1470,6 +1473,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EOPNOTSUPP;
 	if (mem.nregions > max_mem_regions)
 		return -E2BIG;
+	if (max_iotlb_entries <= 0)
+		return -EINVAL;
 	newmem = kvzalloc(struct_size(newmem, regions, mem.nregions),
 			GFP_KERNEL);
 	if (!newmem)

@@ -1778,6 +1783,9 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 	struct vhost_iotlb *niotlb, *oiotlb;
 	int i;
 
+	if (max_iotlb_entries <= 0)
+		return -EINVAL;
+
 	niotlb = iotlb_alloc();
 	if (!niotlb)
 		return -ENOMEM;

index 88ab73db654ae..2cea115c9c9d6 100644
@@ -113,27 +113,32 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 {
 	struct nf_conntrack_tuple otuple, rtuple;
 	struct nf_conn *ct;
+	s32 netns_id;
+	u8 l4proto;
 	int err;
 
-	if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
-	    opts_len != NF_BPF_CT_OPTS_SZ)
+	if (!opts || !bpf_tuple || READ_ONCE(opts->reserved[0]) ||
+	    READ_ONCE(opts->reserved[1]) || opts_len != NF_BPF_CT_OPTS_SZ)
 		return ERR_PTR(-EINVAL);
 
-	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+	netns_id = READ_ONCE(opts->netns_id);
+	l4proto = READ_ONCE(opts->l4proto);
+
+	if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
 		return ERR_PTR(-EINVAL);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_ORIGINAL, &otuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_REPLY, &rtuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (opts->netns_id >= 0) {
-		net = get_net_ns_by_id(net, opts->netns_id);
+	if (netns_id >= 0) {
+		net = get_net_ns_by_id(net, netns_id);
 		if (unlikely(!net))
 			return ERR_PTR(-ENONET);
 	}

@@ -147,7 +152,7 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 	__nf_ct_set_timeout(ct, timeout * HZ);
 
 out:
-	if (opts->netns_id >= 0)
+	if (netns_id >= 0)
 		put_net(net);
 
 	return ct;

@@ -161,29 +166,34 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
 	struct nf_conntrack_tuple_hash *hash;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conn *ct;
+	s32 netns_id;
+	u8 l4proto;
 	int err;
 
-	if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
-	    opts_len != NF_BPF_CT_OPTS_SZ)
+	if (!opts || !bpf_tuple || READ_ONCE(opts->reserved[0]) ||
+	    READ_ONCE(opts->reserved[1]) || opts_len != NF_BPF_CT_OPTS_SZ)
 		return ERR_PTR(-EINVAL);
-	if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP))
+
+	netns_id = READ_ONCE(opts->netns_id);
+	l4proto = READ_ONCE(opts->l4proto);
+	if (unlikely(l4proto != IPPROTO_TCP && l4proto != IPPROTO_UDP))
 		return ERR_PTR(-EPROTO);
-	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+	if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
 		return ERR_PTR(-EINVAL);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_ORIGINAL, &tuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (opts->netns_id >= 0) {
-		net = get_net_ns_by_id(net, opts->netns_id);
+	if (netns_id >= 0) {
+		net = get_net_ns_by_id(net, netns_id);
 		if (unlikely(!net))
 			return ERR_PTR(-ENONET);
 	}
 
 	hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple);
-	if (opts->netns_id >= 0)
+	if (netns_id >= 0)
 		put_net(net);
 	if (!hash)
 		return ERR_PTR(-ENOENT);

index 89bc5f825e0a6..79875e9e1cfa3 100644
@@ -437,7 +437,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
 	char *kaddr;
 	unsigned long bytes;
 
-	if (srclen < LZO_LEN || srclen > max_segment_len + LZO_LEN * 2)
+	if (srclen <= LZO_LEN * 2 || srclen > max_segment_len + LZO_LEN * 2)
 		return -EUCLEAN;
 
 	in_len = read_compress_length(data_in);

index 19780e37d8ea7..95978904c75db 100644
@@ -11,6 +11,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/interrupt.h>
 #include <linux/fs.h>

@@ -60,6 +61,7 @@ struct aspeed_lpc_snoop_model_data {
 
 struct aspeed_lpc_snoop_channel {
 	bool enabled;
+	spinlock_t		lock;
 	struct kfifo		fifo;
 	wait_queue_head_t	wq;
 	struct miscdevice	miscdev;

@@ -83,6 +85,7 @@ static ssize_t snoop_file_read(struct file *file, char __user *buffer,
 				size_t count, loff_t *ppos)
 {
 	struct aspeed_lpc_snoop_channel *chan = snoop_file_to_chan(file);
+	u8 *buf __free(kfree) = NULL;
 	unsigned int copied;
 	int ret = 0;
 

@@ -94,9 +97,16 @@ static ssize_t snoop_file_read(struct file *file, char __user *buffer,
 		if (ret == -ERESTARTSYS)
 			return -EINTR;
 	}
-	ret = kfifo_to_user(&chan->fifo, buffer, count, &copied);
-	if (ret)
-		return ret;
+
+	count = min_t(size_t, count, SNOOP_FIFO_SIZE);
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	copied = kfifo_out_spinlocked(&chan->fifo, buf, count, &chan->lock);
+	if (copied && copy_to_user(buffer, buf, copied))
+		return -EFAULT;
 
 	return copied;
 }

@@ -120,11 +130,13 @@ static const struct file_operations snoop_fops = {
 /* Save a byte to a FIFO and discard the oldest byte if FIFO is full */
 static void put_fifo_with_discard(struct aspeed_lpc_snoop_channel *chan, u8 val)
 {
-	if (!kfifo_initialized(&chan->fifo))
-		return;
-	if (kfifo_is_full(&chan->fifo))
-		kfifo_skip(&chan->fifo);
-	kfifo_put(&chan->fifo, val);
+	scoped_guard(spinlock, &chan->lock) {
+		if (!kfifo_initialized(&chan->fifo))
+			return;
+		if (kfifo_is_full(&chan->fifo))
+			kfifo_skip(&chan->fifo);
+		kfifo_put(&chan->fifo, val);
+	}
 	wake_up_interruptible(&chan->wq);
 }
 

@@ -285,7 +297,7 @@ static int aspeed_lpc_snoop_probe(struct platform_device *pdev)
 	struct device *dev;
 	struct device_node *np;
 	u32 port;
-	int rc;
+	int rc, i;
 
 	dev = &pdev->dev;
 

@@ -293,6 +305,9 @@ static int aspeed_lpc_snoop_probe(struct platform_device *pdev)
 	if (!lpc_snoop)
 		return -ENOMEM;
 
+	for (i = 0; i < NUM_SNOOP_CHANNELS; i++)
+		spin_lock_init(&lpc_snoop->chan[i].lock);
+
 	np = pdev->dev.parent->of_node;
 	if (!of_device_is_compatible(np, "aspeed,ast2400-lpc-v2") &&
 	    !of_device_is_compatible(np, "aspeed,ast2500-lpc-v2") &&

index 7b683553adf5e..2af6027a260f7 100644
@@ -519,15 +519,23 @@ static int pca953x_read_regs(struct pca953x_chip *chip, int reg, unsigned long *
 	return 0;
 }
 
-static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off)
+static int pca953x_gpio_direction_input_unlocked(struct gpio_chip *gc,
+						 unsigned int off)
 {
 	struct pca953x_chip *chip = gpiochip_get_data(gc);
 	u8 dirreg = chip->recalc_addr(chip, chip->regs->direction, off);
 	u8 bit = BIT(off % BANK_SZ);
 
+	return regmap_write_bits(chip->regmap, dirreg, bit, bit);
+}
+
+static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned int off)
+{
+	struct pca953x_chip *chip = gpiochip_get_data(gc);
+
 	guard(mutex)(&chip->i2c_lock);
 
-	return regmap_write_bits(chip->regmap, dirreg, bit, bit);
+	return pca953x_gpio_direction_input_unlocked(gc, off);
 }
 
 static int pca953x_gpio_direction_output(struct gpio_chip *gc,

@@ -756,9 +764,9 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d)
 	DECLARE_BITMAP(reg_direction, MAX_LINE);
 	int level;
 
-	if (chip->driver_data & PCA_PCAL) {
-		guard(mutex)(&chip->i2c_lock);
+	guard(mutex)(&chip->i2c_lock);
 
+	if (chip->driver_data & PCA_PCAL) {
 		/* Enable latch on interrupt-enabled inputs */
 		pca953x_write_regs(chip, PCAL953X_IN_LATCH, chip->irq_mask);
 

@@ -777,7 +785,7 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d)
 
 	/* Look for any newly setup interrupt */
 	for_each_set_bit(level, irq_mask, gc->ngpio)
-		pca953x_gpio_direction_input(&chip->gpio_chip, level);
+		pca953x_gpio_direction_input_unlocked(&chip->gpio_chip, level);
 
 	mutex_unlock(&chip->irq_lock);
 }

index 4595b56d175d9..fe56dbae43bea 100644
@@ -307,6 +307,10 @@ static int l2tp_dfs_seq_release(struct inode *inode, struct file *file)
 
 	seq = file->private_data;
 	pd = seq->private;
+	if (pd->session)
+		l2tp_session_dec_refcount(pd->session);
+	if (pd->tunnel)
+		l2tp_tunnel_dec_refcount(pd->tunnel);
 	if (pd->net)
 		put_net_track(pd->net, &pd->ns_tracker);
 	kfree(pd);

77 lines not on this page · raw message

index 2ef3c220d52ca..5671a05b744b0 100644
@@ -181,6 +181,12 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
+static inline void tcf_set_drop_reason(struct tcf_result *res,
+				       enum skb_drop_reason reason)
+{
+	res->drop_reason = reason;
+}
+
 static inline void
 __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {

index 9310e02d27c88..e16c97cd6ef91 100644
@@ -327,7 +327,6 @@ struct Qdisc_ops {
 	struct module		*owner;
 };
 
-
 struct tcf_result {
 	union {
 		struct {

@@ -335,8 +334,8 @@ struct tcf_result {
 			u32		classid;
 		};
 		const struct tcf_proto *goto_tp;
-
 	};
+	enum skb_drop_reason		drop_reason;
 };
 
 struct tcf_chain;

index 06f4f0f2421b4..1bf404303565e 100644
@@ -4080,6 +4080,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
+	cl_res.drop_reason = SKB_DROP_REASON_TC_EGRESS;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {

@@ -4090,7 +4091,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 	case TC_ACT_SHOT:
 		mini_qdisc_qstats_cpu_drop(miniq);
 		*ret = NET_XMIT_DROP;
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS);
+		kfree_skb_reason(skb, cl_res.drop_reason ?: SKB_DROP_REASON_TC_EGRESS);
 		return NULL;
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:

@@ -5273,6 +5274,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
 	skb->tc_at_ingress = 1;
+	cl_res.drop_reason = SKB_DROP_REASON_TC_INGRESS;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {

@@ -5282,7 +5284,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		break;
 	case TC_ACT_SHOT:
 		mini_qdisc_qstats_cpu_drop(miniq);
-		kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS);
+		kfree_skb_reason(skb, cl_res.drop_reason ?: SKB_DROP_REASON_TC_INGRESS);
 		*ret = NET_RX_DROP;
 		return NULL;
 	case TC_ACT_STOLEN:

index a24e8327e7e7b..5fd72b061801e 100644
@@ -1131,7 +1131,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				net_warn_ratelimited("can't go to NULL chain!\n");
+				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);

index 603b7caebad2b..b79d98711e757 100644
@@ -1601,6 +1601,7 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 bool compat_mode,
 				 u32 *last_executed_chain)
 {
+	u32 orig_reason = res->drop_reason;
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;

@@ -1628,8 +1629,14 @@ static inline int __tcf_classify(struct sk_buff *skb,
 			goto reset;
 		}
 #endif
-		if (err >= 0)
+		if (err >= 0) {
+			/* Policy drop or drop reason is over-written by
+			 * classifiers with a bogus value(0) */
+			if (err == TC_ACT_SHOT &&
+			    res->drop_reason == SKB_NOT_DROPPED_YET)
+				tcf_set_drop_reason(res, orig_reason);
 			return err;
+		}
 	}
 
 	return TC_ACT_UNSPEC; /* signal: continue lookup */

index 5671a05b744b0..7ee8c92c41fa7 100644
@@ -181,10 +181,20 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline void tcf_set_drop_reason(struct tcf_result *res,
+struct tc_skb_cb;
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb);
+
+static inline enum skb_drop_reason
+tcf_get_drop_reason(const struct sk_buff *skb)
+{
+	return tc_skb_cb(skb)->drop_reason;
+}
+
+static inline void tcf_set_drop_reason(const struct sk_buff *skb,
 				       enum skb_drop_reason reason)
 {
-	res->drop_reason = reason;
+	tc_skb_cb(skb)->drop_reason = reason;
 }
 
 static inline void

index 7795b2f68e36b..2ff91bfeb80d2 100644
@@ -218,12 +218,13 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 
 struct tc_skb_cb {
 	struct qdisc_skb_cb qdisc_cb;
+	u32 drop_reason;
 
+	u16 zone; /* Only valid if post_ct = true */
 	u16 mru;
 	u8 post_ct:1;
 	u8 post_ct_snat:1;
 	u8 post_ct_dnat:1;
-	u16 zone; /* Only valid if post_ct = true */
 };
 
 static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)

index e16c97cd6ef91..2bc9b63cf9f22 100644
@@ -335,7 +335,6 @@ struct tcf_result {
 		};
 		const struct tcf_proto *goto_tp;
 	};
-	enum skb_drop_reason		drop_reason;
 };
 
 struct tcf_chain;

index 1bf404303565e..7eccf0fb1709e 100644
@@ -4080,7 +4080,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	cl_res.drop_reason = SKB_DROP_REASON_TC_EGRESS;
+	tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_EGRESS);
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {

@@ -4091,7 +4091,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 	case TC_ACT_SHOT:
 		mini_qdisc_qstats_cpu_drop(miniq);
 		*ret = NET_XMIT_DROP;
-		kfree_skb_reason(skb, cl_res.drop_reason ?: SKB_DROP_REASON_TC_EGRESS);
+		kfree_skb_reason(skb, tcf_get_drop_reason(skb) ?: SKB_DROP_REASON_TC_EGRESS);
 		return NULL;
 	case TC_ACT_STOLEN:
 	case TC_ACT_QUEUED:

@@ -5274,7 +5274,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
 	skb->tc_at_ingress = 1;
-	cl_res.drop_reason = SKB_DROP_REASON_TC_INGRESS;
+	tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_INGRESS);
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {

@@ -5284,7 +5284,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		break;
 	case TC_ACT_SHOT:
 		mini_qdisc_qstats_cpu_drop(miniq);
-		kfree_skb_reason(skb, cl_res.drop_reason ?: SKB_DROP_REASON_TC_INGRESS);
+		kfree_skb_reason(skb, tcf_get_drop_reason(skb) ?: SKB_DROP_REASON_TC_INGRESS);
 		*ret = NET_RX_DROP;
 		return NULL;
 	case TC_ACT_STOLEN:

index 5fd72b061801e..9cbd8446532aa 100644
@@ -1131,7 +1131,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);

index b79d98711e757..603b7caebad2b 100644
@@ -1601,7 +1601,6 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 bool compat_mode,
 				 u32 *last_executed_chain)
 {
-	u32 orig_reason = res->drop_reason;
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;

@@ -1629,14 +1628,8 @@ static inline int __tcf_classify(struct sk_buff *skb,
 			goto reset;
 		}
 #endif
-		if (err >= 0) {
-			/* Policy drop or drop reason is over-written by
-			 * classifiers with a bogus value(0) */
-			if (err == TC_ACT_SHOT &&
-			    res->drop_reason == SKB_NOT_DROPPED_YET)
-				tcf_set_drop_reason(res, orig_reason);
+		if (err >= 0)
 			return err;
-		}
 	}
 
 	return TC_ACT_UNSPEC; /* signal: continue lookup */

index c1cbcdbaf1492..df701ddb8324d 100644
@@ -68,6 +68,7 @@
 	FN(IP_INADDRERRORS)		\
 	FN(IP_INNOROUTES)		\
 	FN(PKT_TOO_BIG)			\
+	FN(TC_CHAIN_NOTFOUND)		\
 	FNe(MAX)
 
 /**

@@ -298,6 +299,8 @@ enum skb_drop_reason {
 	 * MTU)
 	 */
 	SKB_DROP_REASON_PKT_TOO_BIG,
+	/** @SKB_DROP_REASON_TC_CHAIN_NOTFOUND: tc chain lookup failed. */
+	SKB_DROP_REASON_TC_CHAIN_NOTFOUND,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be
 	 * used as a real 'reason'

index 9cbd8446532aa..9f21cc4d1dacc 100644
@@ -1131,7 +1131,8 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);

index 9f21cc4d1dacc..7cfae02653002 100644
@@ -40,11 +40,9 @@ int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
 }
 EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit);
 
-static void tcf_action_goto_chain_exec(const struct tc_action *a,
+static void tcf_action_goto_chain_exec(const struct tcf_chain *chain,
 				       struct tcf_result *res)
 {
-	const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain);
-
 	res->goto_tp = rcu_dereference_bh(chain->filter_chain);
 }
 

@@ -1130,12 +1128,14 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 					return TC_ACT_OK;
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
-			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
+			struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain);
+
+			if (unlikely(!chain)) {
 				tcf_set_drop_reason(skb,
 						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
 				return TC_ACT_SHOT;
 			}
-			tcf_action_goto_chain_exec(a, res);
+			tcf_action_goto_chain_exec(chain, res);
 		}
 
 		if (ret != TC_ACT_PIPE)

index 9aeb44f03f17c..9ac0ffb54bebd 100644
@@ -1583,7 +1583,7 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
 	return fwd;
 }
 
-void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
+bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		    struct ip_vs_conn *cp, int dir, unsigned int toff,
 		    bool has_ports, struct ip_vs_iphdr *ciph);
 

index 41f09e29d221b..dec212507ba99 100644
@@ -745,7 +745,7 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
  * Packet has been made sufficiently writable in caller
  * - inout: 1=in->out, 0=out->in
  */
-void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
+bool ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		    struct ip_vs_conn *cp, int inout, unsigned int toff,
 		    bool has_ports, struct ip_vs_iphdr *ciph)
 {

@@ -753,6 +753,11 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	struct icmphdr *icmph	 = (struct icmphdr *)(skb->data + toff);
 	struct iphdr *cih	 = (struct iphdr *)(icmph + 1);
 
+	/* Before now we may used ihl from skb frag, revalidate it after
+	 * copying it into skb head to prevent out-of-bounds access
+	 */
+	if (cih->ihl * 4 != ciph->len - ciph->off)
+		return false;
 	if (inout) {
 		iph->saddr = cp->vaddr.ip;
 		ip_send_check(iph);

@@ -786,6 +791,7 @@ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 	else
 		IP_VS_DBG_PKT(11, AF_INET, pp, skb, ciph->off,
 			      "Forwarding altered incoming ICMP");
+	return true;
 }
 
 #ifdef CONFIG_IP_VS_IPV6

@@ -877,7 +883,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 		ip_vs_nat_icmp_v6(skb, pp, cp, 1, toff, has_ports, ciph);
 	else
 #endif
-		ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph);
+		if (!ip_vs_nat_icmp(skb, pp, cp, 1, toff, has_ports, ciph))
+			goto out;
 
 	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
 		goto out;

index b424ebd7235fe..cbef6ca5088a6 100644
@@ -1615,7 +1615,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (skb_cow(skb, rt->dst.dev->hard_header_len))
 		goto tx_error;
 
-	ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph);
+	if (!ip_vs_nat_icmp(skb, pp, cp, 0, toff, has_ports, ciph))
+		goto tx_error;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->ignore_df = 1;

index 8063ec6c82645..b458a8cb619f9 100644
@@ -2277,6 +2277,7 @@ static void scsi_unjam_host(struct Scsi_Host *shost)
 int scsi_error_handler(void *data)
 {
 	struct Scsi_Host *shost = data;
+	bool eh_noresume;
 
 	/*
 	 * We use TASK_INTERRUPTIBLE so that the thread is not

@@ -2318,7 +2319,8 @@ int scsi_error_handler(void *data)
 		 * what we need to do to get it up and online again (if we can).
 		 * If we fail, we end up taking the thing offline.
 		 */
-		if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) {
+		eh_noresume = READ_ONCE(shost->eh_noresume);
+		if (!eh_noresume && scsi_autopm_get_host(shost) != 0) {
 			SCSI_LOG_ERROR_RECOVERY(1,
 				shost_printk(KERN_ERR, shost,
 					     "scsi_eh_%d: unable to autoresume\n",

@@ -2342,7 +2344,7 @@ int scsi_error_handler(void *data)
 		 * which are still online.
 		 */
 		scsi_restart_operations(shost);
-		if (!shost->eh_noresume)
+		if (!eh_noresume)
 			scsi_autopm_put_host(shost);
 	}
 	__set_current_state(TASK_RUNNING);

index f8f64b8f111c9..0e9ea032711b9 100644
@@ -8838,7 +8838,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * we are functional while we are here, skip host resume in error
 	 * handling context.
 	 */
-	hba->host->eh_noresume = 1;
+	WRITE_ONCE(hba->host->eh_noresume, 1);
 
 	cmd[4] = pwr_mode << 4;
 

@@ -8872,7 +8872,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 		hba->curr_dev_pwr_mode = pwr_mode;
 
 	scsi_device_put(sdp);
-	hba->host->eh_noresume = 0;
+	WRITE_ONCE(hba->host->eh_noresume, 0);
 	return ret;
 }
 

index 71d47d4ec04d9..4be73c771ed0c 100644
@@ -623,6 +623,9 @@ struct Scsi_Host {
 	 */
 	unsigned nr_hw_queues;
 	unsigned nr_maps;
+	/* Don't resume host in EH */
+	bool eh_noresume;
+
 	unsigned active_mode:2;
 
 	/*

@@ -644,9 +647,6 @@ struct Scsi_Host {
 	/* Asynchronous scan in progress */
 	unsigned async_scan:1;
 
-	/* Don't resume host in EH */
-	unsigned eh_noresume:1;
-
 	/* The controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 

index 07336352272b3..bb9dfd10d2d7a 100644
@@ -474,10 +474,14 @@ static int tas2562_volume_control_put(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct tas2562_data *tas2562 = snd_soc_component_get_drvdata(component);
-	int ret;
+	int ret, index;
 	u32 reg_val;
 
-	reg_val = float_vol_db_lookup[ucontrol->value.integer.value[0]/2];
+	index = ucontrol->value.integer.value[0] / 2;
+	if (index < 0 || index >= ARRAY_SIZE(float_vol_db_lookup))
+		return -EINVAL;
+
+	reg_val = float_vol_db_lookup[index];
 	/*
 	 * The device applies the 32-bit coefficient to the playback path on
 	 * the write to DVC_CFG4 (the LSB, book 0 page 2 reg 0x0F), so the

index e64ac6e9b2911..3a234cd20cfb0 100644
@@ -376,6 +376,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 	chain->ch_len = len;
 
 	list_add_tail(&chain->next, &cp->ccwchain_list);
+	cp->ccwchain_count++;
 
 	return chain;
 }

@@ -478,6 +479,10 @@ static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
 	if (len < 0)
 		return len;
 
+	/* Limit number of chains in a single channel program */
+	if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX)
+		return -EINVAL;
+
 	/* Need alloc a new chain for this one. */
 	chain = ccwchain_alloc(cp, len);
 	if (!chain)

@@ -709,6 +714,7 @@ int cp_init(struct channel_program *cp, union orb *orb)
 			vdev->dev,
 			"Prefetching channel program even though prefetch not specified in ORB");
 
+	cp->ccwchain_count = 0;
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
 

index 54d26e2425334..5c51d1197ba98 100644
@@ -23,12 +23,19 @@
  */
 #define CCWCHAIN_LEN_MAX	256
 
+/*
+ * Maximum number of chains
+ */
+#define CCWCHAIN_COUNT_MAX	16
+
 /**
  * struct channel_program - manage information for channel program
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @mdev: the mediated device to perform page pinning/unpinning
  * @initialized: whether this instance is actually initialized
+ * @guest_cp: copy of guest channel program
+ * @ccwchain_count: number of channel program segments (linked by TIC)
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by

@@ -39,6 +46,7 @@ struct channel_program {
 	union orb orb;
 	bool initialized;
 	struct ccw1 *guest_cp;
+	unsigned int ccwchain_count;
 };
 
 int cp_init(struct channel_program *cp, union orb *orb);

index e63a71506871d..a9e046576f7ef 100644
@@ -39,6 +39,25 @@
 #include "amdgpu_gem.h"
 #include "amdgpu_ras.h"
 
+/*
+ * Maximum IB length (dwords) for rings whose emit_ib packet format
+ * documents a 20-bit size field.
+ */
+#define AMDGPU_GFX_SDMA_IB_PACKET_SIZE_MAX_DW	0xFFFFF
+#define AMDGPU_MM_IB_PACKET_SIZE_MAX_DW	0x7FFFF0
+
+static u32 amdgpu_cs_ib_packet_size_max_dw(enum amdgpu_ring_type type)
+{
+	switch (type) {
+	case AMDGPU_RING_TYPE_GFX:
+	case AMDGPU_RING_TYPE_COMPUTE:
+	case AMDGPU_RING_TYPE_SDMA:
+		return AMDGPU_GFX_SDMA_IB_PACKET_SIZE_MAX_DW;
+	default:
+		return AMDGPU_MM_IB_PACKET_SIZE_MAX_DW;
+	}
+}
+
 static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
 				 struct amdgpu_device *adev,
 				 struct drm_file *filp,

@@ -343,7 +362,6 @@ static int amdgpu_cs_p2_ib(struct amdgpu_cs_parser *p,
 
 	job = p->jobs[r];
 	ring = amdgpu_job_ring(job);
-	ib = &job->ibs[job->num_ibs++];
 
 	/* MM engine doesn't support user fences */
 	if (p->uf_entry.tv.bo && ring->funcs->no_user_fence)

@@ -362,6 +380,12 @@ static int amdgpu_cs_p2_ib(struct amdgpu_cs_parser *p,
 			return -EINVAL;
 	}
 
+	if (chunk_ib->ib_bytes / 4 >
+	    amdgpu_cs_ib_packet_size_max_dw(ring->funcs->type))
+		return -EINVAL;
+
+	ib = &job->ibs[job->num_ibs++];
+
 	if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE)
 		job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT;
 

index 6f82517b8f6f5..79c5f731a5e12 100644
@@ -26,6 +26,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 {
 	u8 subtype = *ptr >> 4;
 	int expected_opsize;
+	u16 subopt;
 	u8 version;
 	u8 flags;
 	u8 i;

@@ -38,11 +39,23 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA;
 			else
 				expected_opsize = TCPOLEN_MPTCP_MPC_ACK;
+			subopt = OPTION_MPTCP_MPC_ACK;
 		} else {
-			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) {
 				expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;
-			else
+				subopt = OPTION_MPTCP_MPC_SYNACK;
+			} else {
 				expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
+				subopt = OPTION_MPTCP_MPC_SYN;
+			}
+		}
+
+		/* Only the MPC + ACK can be used with a RM_ADDR */
+		if (subopt == OPTION_MPTCP_MPC_ACK) {
+			if ((mp_opt->suboptions & ~OPTION_MPTCP_RM_ADDR) != 0)
+				break;
+		} else if (mp_opt->suboptions != 0) {
+			break;
 		}
 
 		/* Cfr RFC 8684 Section 3.3.0:

@@ -86,7 +99,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 		mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0);
 
-		mp_opt->suboptions |= OPTIONS_MPTCP_MPC;
+		mp_opt->suboptions |= subopt;
 		if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
 			mp_opt->sndr_key = get_unaligned_be64(ptr);
 			ptr += 8;

@@ -118,6 +131,11 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_JOIN:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTION_MPTCP_RM_ADDR |
+					    OPTION_MPTCP_PRIO)) != 0)
+			break;
+
 		if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
 			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;

@@ -149,6 +167,14 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_DSS:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTION_MPTCP_ADD_ADDR |
+					    OPTION_MPTCP_RM_ADDR |
+					    OPTION_MPTCP_PRIO |
+					    OPTION_MPTCP_FASTCLOSE |
+					    OPTION_MPTCP_FAIL)) != 0)
+			break;
+
 		pr_debug("DSS\n");
 		ptr++;
 

@@ -236,6 +262,12 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_ADD_ADDR:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS |
+					    OPTION_MPTCP_RM_ADDR |
+					    OPTION_MPTCP_PRIO)) != 0)
+			break;
+
 		mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO;
 		if (!mp_opt->echo) {
 			if (opsize == TCPOLEN_MPTCP_ADD_ADDR ||

@@ -295,6 +327,14 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_RM_ADDR:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTION_MPTCP_MPC_ACK |
+					    OPTIONS_MPTCP_MPJ |
+					    OPTIONS_MPTCP_DSS |
+					    OPTION_MPTCP_ADD_ADDR |
+					    OPTION_MPTCP_PRIO)) != 0)
+			break;
+
 		if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 ||
 		    opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX)
 			break;

@@ -309,6 +349,13 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_PRIO:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_MPJ |
+					    OPTIONS_MPTCP_DSS |
+					    OPTION_MPTCP_ADD_ADDR |
+					    OPTION_MPTCP_RM_ADDR)) != 0)
+			break;
+
 		if (opsize != TCPOLEN_MPTCP_PRIO)
 			break;
 

@@ -318,6 +365,11 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_FASTCLOSE:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS |
+					    OPTION_MPTCP_RST)) != 0)
+			break;
+
 		if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
 			break;
 

@@ -329,6 +381,11 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_RST:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTION_MPTCP_FAIL |
+					    OPTION_MPTCP_FASTCLOSE)) != 0)
+			break;
+
 		if (opsize != TCPOLEN_MPTCP_RST)
 			break;
 

@@ -344,6 +401,11 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_FAIL:
+		/* Can be used with a restricted number of other options */
+		if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS |
+					    OPTION_MPTCP_RST)) != 0)
+			break;
+
 		if (opsize != TCPOLEN_MPTCP_FAIL)
 			break;
 

@@ -1416,7 +1478,7 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
 	 *  RM   |  C   |  C   |  C   |  P   |------|------|------|------|
 	 *  PRIO |  X   |  C   |  C   |  C   |  C   |------|------|------|
 	 *  FAIL |  X   |  X   |  C   |  X   |  X   |  X   |------|------|
-	 *  FC   |  X   |  X   |  X   |  X   |  X   |  X   |  X   |------|
+	 *  FC   |  X   |  X   |  P   |  X   |  X   |  X   |  X   |------|
 	 *  RST  |  X   |  X   |  X   |  X   |  X   |  X   |  O   |  O   |
 	 * ------|------|------|------|------|------|------|------|------|
 	 *

index 716a6947fba74..6728f08970f2f 100644
@@ -36,6 +36,7 @@
 				 OPTION_MPTCP_MPC_ACK)
 #define OPTIONS_MPTCP_MPJ	(OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \
 				 OPTION_MPTCP_MPJ_ACK)
+#define OPTIONS_MPTCP_DSS	(OPTION_MPTCP_DSS | OPTION_MPTCP_CSUMREQD)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0

index 8df8e789a0dbe..90b9e8d725d41 100644
@@ -1183,7 +1183,7 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr)
 	return 0;
 }
 
-int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+int __weak __cpuidle acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
 	return -ENODEV;
 }

@@ -1196,7 +1196,7 @@ int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
  *
  * Return: 0 for success or negative value for error
  */
-static int acpi_idle_lpi_enter(struct cpuidle_device *dev,
+static int __cpuidle acpi_idle_lpi_enter(struct cpuidle_device *dev,
 			       struct cpuidle_driver *drv, int index)
 {
 	struct acpi_processor *pr;

index b3b89a1cd2a4c..a5b1795408831 100644
@@ -206,8 +206,10 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 			continue;
 		wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
 		err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d");
-		if (err)
+		if (err) {
+			WARN_ON(err && err != -ENOMEM);
 			break;
+		}
 		wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL;
 	}
 

@@ -223,7 +225,7 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 			wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
 			err = dev_change_net_namespace(wpan_dev->netdev, net,
 						       "wpan%d");
-			WARN_ON(err);
+			WARN_ON(err && err != -ENOMEM);
 			wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL;
 		}
 

@@ -233,7 +235,7 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 	wpan_phy_net_set(&rdev->wpan_phy, net);
 
 	err = device_rename(&rdev->wpan_phy.dev, dev_name(&rdev->wpan_phy.dev));
-	WARN_ON(err);
+	WARN_ON(err && err != -ENOMEM);
 
 	return 0;
 }

index 45f2f6db15886..32be2cd1b3b7d 100644
@@ -3,6 +3,7 @@
  * Copyright (c) 2014, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/moduleparam.h>

@@ -51,10 +52,14 @@ MODULE_PARM_DESC(boot_enable, "Enable tracing on boot");
 #define PARAM_PM_SAVE_NEVER	  1 /* never save any state */
 #define PARAM_PM_SAVE_SELF_HOSTED 2 /* save self-hosted state only */
 
+/*
+ * Save option for ETM4. ETE, sysreg ETM4s and ACPI boots ignore this option and
+ * will always save.
+ */
 static int pm_save_enable = PARAM_PM_SAVE_FIRMWARE;
 module_param(pm_save_enable, int, 0444);
 MODULE_PARM_DESC(pm_save_enable,
-	"Save/restore state on power down: 1 = never, 2 = self-hosted");
+	"Save/restore state on power down: 1 = never, 2 = self-hosted. MMIO and DT only.");
 
 static struct etmv4_drvdata *etmdrvdata[NR_CPUS];
 static void etm4_set_default_config(struct etmv4_config *config);

@@ -1994,6 +1999,17 @@ static void etm4_pm_clear(void)
 	}
 }
 
+static bool etm4x_always_pm_save(struct device *dev, struct csdev_access *csa)
+{
+	/*
+	 * Only IO mem ETM devices will benefit from skipping PM save and only
+	 * DT has the option to control it, not ACPI. Otherwise system register
+	 * based ETMs and ETEs will always lose context on CPU power down, so
+	 * always save.
+	 */
+	return !csa->io_mem || is_acpi_device_node(dev_fwnode(dev));
+}
+
 static int etm4_probe(struct device *dev, void __iomem *base, u32 etm_pid)
 {
 	int ret;

@@ -2003,6 +2019,7 @@ static int etm4_probe(struct device *dev, void __iomem *base, u32 etm_pid)
 	struct etm4_init_arg init_arg = { 0 };
 	u8 major, minor;
 	char *type_name;
+	bool pm_save;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)

@@ -2010,17 +2027,6 @@ static int etm4_probe(struct device *dev, void __iomem *base, u32 etm_pid)
 
 	dev_set_drvdata(dev, drvdata);
 
-	if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE)
-		pm_save_enable = coresight_loses_context_with_cpu(dev) ?
-			       PARAM_PM_SAVE_SELF_HOSTED : PARAM_PM_SAVE_NEVER;
-
-	if (pm_save_enable != PARAM_PM_SAVE_NEVER) {
-		drvdata->save_state = devm_kmalloc(dev,
-				sizeof(struct etmv4_save_state), GFP_KERNEL);
-		if (!drvdata->save_state)
-			return -ENOMEM;
-	}
-
 	drvdata->base = base;
 
 	spin_lock_init(&drvdata->spinlock);

@@ -2064,6 +2070,21 @@ static int etm4_probe(struct device *dev, void __iomem *base, u32 etm_pid)
 	etm4_init_trace_id(drvdata);
 	etm4_set_default(&drvdata->config);
 
+	if (etm4x_always_pm_save(dev, &desc.access))
+		pm_save = true;
+	else if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE)
+		pm_save = coresight_loses_context_with_cpu(dev);
+	else
+		pm_save = pm_save_enable != PARAM_PM_SAVE_NEVER;
+
+	if (pm_save) {
+		drvdata->save_state = devm_kmalloc(dev,
+						   sizeof(struct etmv4_save_state),
+						   GFP_KERNEL);
+		if (!drvdata->save_state)
+			return -ENOMEM;
+	}
+
 	pdata = coresight_get_platform_data(dev);
 	if (IS_ERR(pdata))
 		return PTR_ERR(pdata);

index f0db5d3dcba47..b7cdb1c61f265 100644
@@ -73,13 +73,17 @@ snd_seq_oss_readq_delete(struct seq_oss_readq *q)
 void
 snd_seq_oss_readq_clear(struct seq_oss_readq *q)
 {
-	if (q->qlen) {
-		q->qlen = 0;
-		q->head = q->tail = 0;
+	scoped_guard(spinlock_irqsave, &q->lock) {
+		if (q->qlen) {
+			q->qlen = 0;
+			q->head = 0;
+			q->tail = 0;
+		}
+		q->input_time = (unsigned long)-1;
 	}
+
 	/* if someone sleeping, wake'em up */
 	wake_up(&q->midi_sleep);
-	q->input_time = (unsigned long)-1;
 }
 
 /*

@@ -136,28 +140,37 @@ int snd_seq_oss_readq_sysex(struct seq_oss_readq *q, int dev,
 /*
  * copy an event to input queue:
  * return zero if enqueued
+ * caller must hold lock
  */
-int
-snd_seq_oss_readq_put_event(struct seq_oss_readq *q, union evrec *ev)
+static int snd_seq_oss_readq_put_event_locked(struct seq_oss_readq *q,
+					      union evrec *ev)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->lock, flags);
-	if (q->qlen >= q->maxlen - 1) {
-		spin_unlock_irqrestore(&q->lock, flags);
+	if (q->qlen >= q->maxlen - 1)
 		return -ENOMEM;
-	}
 
 	memcpy(&q->q[q->tail], ev, sizeof(*ev));
 	q->tail = (q->tail + 1) % q->maxlen;
 	q->qlen++;
 
-	/* wake up sleeper */
-	wake_up(&q->midi_sleep);
+	return 0;
+}
 
-	spin_unlock_irqrestore(&q->lock, flags);
+/*
+ * copy an event to input queue:
+ * return zero if enqueued
+ */
+int
+snd_seq_oss_readq_put_event(struct seq_oss_readq *q, union evrec *ev)
+{
+	int rc;
 
-	return 0;
+	scoped_guard(spinlock_irqsave, &q->lock) {
+		rc = snd_seq_oss_readq_put_event_locked(q, ev);
+		if (!rc)
+			wake_up(&q->midi_sleep);
+	}
+
+	return rc;
 }
 
 

@@ -215,23 +228,31 @@ snd_seq_oss_readq_poll(struct seq_oss_readq *q, struct file *file, poll_table *w
 int
 snd_seq_oss_readq_put_timestamp(struct seq_oss_readq *q, unsigned long curt, int seq_mode)
 {
-	if (curt != q->input_time) {
-		union evrec rec;
-		memset(&rec, 0, sizeof(rec));
-		switch (seq_mode) {
-		case SNDRV_SEQ_OSS_MODE_SYNTH:
-			rec.echo = (curt << 8) | SEQ_WAIT;
-			snd_seq_oss_readq_put_event(q, &rec);
-			break;
-		case SNDRV_SEQ_OSS_MODE_MUSIC:
-			rec.t.code = EV_TIMING;
-			rec.t.cmd = TMR_WAIT_ABS;
-			rec.t.time = curt;
-			snd_seq_oss_readq_put_event(q, &rec);
-			break;
+	int queued = 0;
+
+	scoped_guard(spinlock_irqsave, &q->lock) {
+		if (curt != q->input_time) {
+			union evrec rec;
+
+			memset(&rec, 0, sizeof(rec));
+			switch (seq_mode) {
+			case SNDRV_SEQ_OSS_MODE_SYNTH:
+				rec.echo = (curt << 8) | SEQ_WAIT;
+				queued = !snd_seq_oss_readq_put_event_locked(q, &rec);
+				break;
+			case SNDRV_SEQ_OSS_MODE_MUSIC:
+				rec.t.code = EV_TIMING;
+				rec.t.cmd = TMR_WAIT_ABS;
+				rec.t.time = curt;
+				queued = !snd_seq_oss_readq_put_event_locked(q, &rec);
+				break;
+			}
+			q->input_time = curt;
 		}
-		q->input_time = curt;
 	}
+	if (queued)
+		wake_up(&q->midi_sleep);
+
 	return 0;
 }
 

index ed1b66ea0aeff..c8146e3afb1b8 100644
@@ -1934,7 +1934,7 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	/* Alloc memory for MCAM entry to counter mapping and for tracking
 	 * counter's reference count.
 	 */
-	mcam->entry2cntr_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
+	mcam->entry2cntr_map = devm_kcalloc(rvu->dev, mcam->total_entries,
 					    sizeof(u16), GFP_KERNEL);
 	if (!mcam->entry2cntr_map)
 		goto free_mem;

@@ -1950,10 +1950,11 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (!mcam->entry2target_pffunc)
 		goto free_mem;
 
-	for (index = 0; index < mcam->bmap_entries; index++) {
+	for (index = 0; index < mcam->bmap_entries; index++)
 		mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+
+	for (index = 0; index < mcam->total_entries; index++)
 		mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
-	}
 
 	for (cntr = 0; cntr < mcam->counters.max; cntr++)
 		mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;