bind/backport-CVE-2024-12705.patch

1320 lines
40 KiB
Diff
Raw Normal View History

2025-02-08 16:48:39 +08:00
From 11a2956dce6f983d2bfcb532f5719791845b06ab Mon Sep 17 00:00:00 2001
From: Artem Boldariev <artem@isc.org>
Date: Thu, 4 Jul 2024 14:58:10 +0300
Subject: [PATCH] DoH: process data chunk by chunk instead of all at once
Initially, our DNS-over-HTTP(S) implementation would try to process as
much incoming data from the network as possible. However, that might
be undesirable as we might create too many streams (each effectively
backed by a ns_client_t object). That is too forgiving as it might
overwhelm the server and trash its memory allocator, causing high CPU
and memory usage.
Instead of doing that, we resort to processing incoming data using a
chunk-by-chunk processing strategy. That is, we split data into small
chunks (currently 256 bytes) and process each of them
asynchronously. However, we can process more than one chunk at
once (up to 4 currently), given that the number of HTTP/2 streams has
not increased while processing a chunk.
That alone is not enough, though. In addition to the above, we should
limit the number of active streams: these streams for which we have
received a request and started processing it (the ones for which a
read callback was called), as it is perfectly fine to have more opened
streams than active ones. In the case we have reached or surpassed the
limit of active streams, we stop reading AND processing the data from
the remote peer. The number of active streams is effectively decreased
only when responses associated with the active streams are sent to the
remote peer.
Overall, this strategy is very similar to the one used for other
stream-based DNS transports like TCP and TLS.
(cherry picked from commit 9846f395ad79bb50a5fa5ca6ab97ef904b3be35a)
Conflict:NA
Reference:https://downloads.isc.org/isc/bind9/9.18.33/patches/0002-CVE-2024-12705.patch
---
lib/isc/netmgr/http.c | 451 +++++++++++++++++++++++++++++++++---
lib/isc/netmgr/netmgr-int.h | 81 ++++++-
lib/isc/netmgr/netmgr.c | 78 +++++++
lib/isc/netmgr/tcp.c | 26 ++-
lib/isc/netmgr/tlsstream.c | 137 +++++++++--
5 files changed, 723 insertions(+), 50 deletions(-)
diff --git a/lib/isc/netmgr/http.c b/lib/isc/netmgr/http.c
index 2220edf..6aaa6da 100644
--- a/lib/isc/netmgr/http.c
+++ b/lib/isc/netmgr/http.c
@@ -85,6 +85,37 @@
#define INITIAL_DNS_MESSAGE_BUFFER_SIZE (512)
+/*
+ * The value should be small enough to not allow a server to open too
+ * many streams at once. It should not be too small either because
+ * the incoming data will be split into too many chunks with each of
+ * them processed asynchronously.
+ */
+#define INCOMING_DATA_CHUNK_SIZE (256)
+
+/*
+ * Often processing a chunk does not change the number of streams. In
+ * that case we can process more than once, but we still should have a
+ * hard limit on that.
+ */
+#define INCOMING_DATA_MAX_CHUNKS_AT_ONCE (4)
+
+/*
+ * These constants define the grace period to help detect flooding clients.
+ *
+ * The first one defines how much data can be processed before opening
+ * a first stream and received at least some useful (=DNS) data.
+ *
+ * The second one defines how much data from a client we read before
+ * trying to drop a clients who sends not enough useful data.
+ *
+ * The third constant defines how many streams we agree to process
+ * before checking if there was at least one DNS request received.
+ */
+#define INCOMING_DATA_INITIAL_STREAM_SIZE (1536)
+#define INCOMING_DATA_GRACE_SIZE (MAX_ALLOWED_DATA_IN_HEADERS)
+#define MAX_STREAMS_BEFORE_FIRST_REQUEST (50)
+
typedef struct isc_nm_http_response_status {
size_t code;
size_t content_length;
@@ -143,6 +174,7 @@ struct isc_nm_http_session {
ISC_LIST(http_cstream_t) cstreams;
ISC_LIST(isc_nmsocket_h2_t) sstreams;
size_t nsstreams;
+ uint64_t total_opened_sstreams;
isc_nmhandle_t *handle;
isc_nmhandle_t *client_httphandle;
@@ -155,6 +187,18 @@ struct isc_nm_http_session {
isc__nm_http_pending_callbacks_t pending_write_callbacks;
isc_buffer_t *pending_write_data;
+
+ /*
+ * The statistical values below are for usage on server-side
+ * only. They are meant to detect clients that are taking too many
+ * resources from the server.
+ */
+ uint64_t received; /* How many requests have been received. */
+ uint64_t submitted; /* How many responses were submitted to send */
+ uint64_t processed; /* How many responses were processed. */
+
+ uint64_t processed_incoming_data;
+ uint64_t processed_useful_data; /* DNS data */
};
typedef enum isc_http_error_responses {
@@ -177,6 +221,7 @@ typedef struct isc_http_send_req {
void *cbarg;
isc_buffer_t *pending_write_data;
isc__nm_http_pending_callbacks_t pending_write_callbacks;
+ uint64_t submitted;
} isc_http_send_req_t;
#define HTTP_ENDPOINTS_MAGIC ISC_MAGIC('H', 'T', 'E', 'P')
@@ -186,10 +231,26 @@ static bool
http_send_outgoing(isc_nm_http_session_t *session, isc_nmhandle_t *httphandle,
isc_nm_cb_t cb, void *cbarg);
+static void
+http_log_flooding_peer(isc_nm_http_session_t *session);
+
+static bool
+http_is_flooding_peer(isc_nm_http_session_t *session);
+
+static ssize_t
+http_process_input_data(isc_nm_http_session_t *session,
+ isc_buffer_t *input_data);
+
+static inline bool
+http_too_many_active_streams(isc_nm_http_session_t *session);
+
static void
http_do_bio(isc_nm_http_session_t *session, isc_nmhandle_t *send_httphandle,
isc_nm_cb_t send_cb, void *send_cbarg);
+static void
+http_do_bio_async(isc_nm_http_session_t *session);
+
static void
failed_httpstream_read_cb(isc_nmsocket_t *sock, isc_result_t result,
isc_nm_http_session_t *session);
@@ -491,6 +552,16 @@ finish_http_session(isc_nm_http_session_t *session) {
if (!session->closed) {
session->closed = true;
isc_nm_cancelread(session->handle);
+ isc__nmsocket_timer_stop(session->handle->sock);
+ }
+
+ /*
+ * Free any unprocessed incoming data in order to not process
+ * it during indirect calls to http_do_bio() that might happen
+ * when calling the failed callbacks.
+ */
+ if (session->buf != NULL) {
+ isc_buffer_free(&session->buf);
}
if (session->client) {
@@ -564,6 +635,7 @@ on_server_data_chunk_recv_callback(int32_t stream_id, const uint8_t *data,
if (new_bufsize <= MAX_DNS_MESSAGE_SIZE &&
new_bufsize <= h2->content_length)
{
+ session->processed_useful_data += len;
isc_buffer_putmem(&h2->rbuf, data, len);
break;
}
@@ -612,6 +684,9 @@ call_unlink_cstream_readcb(http_cstream_t *cstream,
isc_buffer_usedregion(cstream->rbuf, &read_data);
cstream->read_cb(session->client_httphandle, result, &read_data,
cstream->read_cbarg);
+ if (result == ISC_R_SUCCESS) {
+ isc__nmsocket_timer_restart(session->handle->sock);
+ }
put_http_cstream(session->mctx, cstream);
}
@@ -653,6 +728,9 @@ on_server_stream_close_callback(int32_t stream_id,
ISC_LIST_UNLINK(session->sstreams, &sock->h2, link);
session->nsstreams--;
+ if (sock->h2.request_received) {
+ session->submitted++;
+ }
/*
* By making a call to isc__nmsocket_prep_destroy(), we ensure that
@@ -969,6 +1047,182 @@ client_submit_request(isc_nm_http_session_t *session, http_cstream_t *stream) {
return (ISC_R_SUCCESS);
}
+static ssize_t
+http_process_input_data(isc_nm_http_session_t *session,
+ isc_buffer_t *input_data) {
+ ssize_t readlen = 0;
+ ssize_t processed = 0;
+ isc_region_t chunk = { 0 };
+ size_t before, after;
+ size_t i;
+
+ REQUIRE(VALID_HTTP2_SESSION(session));
+ REQUIRE(input_data != NULL);
+
+ if (!http_session_active(session)) {
+ return 0;
+ }
+
+ /*
+ * For clients that initiate request themselves just process
+ * everything.
+ */
+ if (session->client) {
+ isc_buffer_remainingregion(input_data, &chunk);
+ if (chunk.length == 0) {
+ return 0;
+ }
+
+ readlen = nghttp2_session_mem_recv(session->ngsession,
+ chunk.base, chunk.length);
+
+ if (readlen >= 0) {
+ isc_buffer_forward(input_data, readlen);
+ session->processed_incoming_data += readlen;
+ }
+
+ return readlen;
+ }
+
+ /*
+ * If no streams are created during processing, we might process
+ * more than one chunk at a time. Still we should not overdo that
+ * to avoid processing too much data at once as such behaviour is
+ * known for trashing the memory allocator at times.
+ */
+ for (before = after = session->nsstreams, i = 0;
+ after <= before && i < INCOMING_DATA_MAX_CHUNKS_AT_ONCE;
+ after = session->nsstreams, i++)
+ {
+ const uint64_t active_streams =
+ (session->received - session->processed);
+
+ /*
+ * If there are non completed send requests in flight -let's
+ * not process any incoming data, as it could lead to piling
+ * up too much send data in send buffers. With many clients
+ * connected it can lead to excessive memory consumption on
+ * the server instance.
+ */
+ if (session->sending > 0) {
+ break;
+ }
+
+ /*
+ * If we have reached the maximum number of streams used, we
+ * might stop processing for now, as nghttp2 will happily
+ * consume as much data as possible.
+ */
+ if (session->nsstreams >= session->max_concurrent_streams &&
+ active_streams > 0)
+ {
+ break;
+ }
+
+ if (http_too_many_active_streams(session)) {
+ break;
+ }
+
+ isc_buffer_remainingregion(input_data, &chunk);
+ if (chunk.length == 0) {
+ break;
+ }
+
+ chunk.length = ISC_MIN(chunk.length, INCOMING_DATA_CHUNK_SIZE);
+
+ readlen = nghttp2_session_mem_recv(session->ngsession,
+ chunk.base, chunk.length);
+
+ if (readlen >= 0) {
+ isc_buffer_forward(input_data, readlen);
+ session->processed_incoming_data += readlen;
+ processed += readlen;
+ } else {
+ isc_buffer_clear(input_data);
+ return readlen;
+ }
+ }
+
+ return processed;
+}
+
+static void
+http_log_flooding_peer(isc_nm_http_session_t *session) {
+ const int log_level = ISC_LOG_DEBUG(1);
+ if (session->handle != NULL && isc_log_wouldlog(isc_lctx, log_level)) {
+ char client_sabuf[ISC_SOCKADDR_FORMATSIZE];
+ char local_sabuf[ISC_SOCKADDR_FORMATSIZE];
+
+ isc_sockaddr_format(&session->handle->sock->peer, client_sabuf,
+ sizeof(client_sabuf));
+ isc_sockaddr_format(&session->handle->sock->iface, local_sabuf,
+ sizeof(local_sabuf));
+ isc_log_write(isc_lctx, ISC_LOGCATEGORY_GENERAL,
+ ISC_LOGMODULE_NETMGR, log_level,
+ "Dropping a flooding HTTP/2 peer "
+ "%s (on %s) - processed: %" PRIu64
+ " bytes, of them useful: %" PRIu64 "",
+ client_sabuf, local_sabuf,
+ session->processed_incoming_data,
+ session->processed_useful_data);
+ }
+}
+
+static bool
+http_is_flooding_peer(isc_nm_http_session_t *session) {
+ if (session->client) {
+ return false;
+ }
+
+ /*
+ * A flooding client can try to open a lot of streams before
+ * submitting a request. Let's drop such clients.
+ */
+ if (session->received == 0 &&
+ session->total_opened_sstreams > MAX_STREAMS_BEFORE_FIRST_REQUEST)
+ {
+ return true;
+ }
+
+ /*
+ * We have processed enough data to open at least one stream and
+ * get some useful data.
+ */
+ if (session->processed_incoming_data >
+ INCOMING_DATA_INITIAL_STREAM_SIZE &&
+ (session->total_opened_sstreams == 0 ||
+ session->processed_useful_data == 0))
+ {
+ return true;
+ }
+
+ if (session->processed_incoming_data < INCOMING_DATA_GRACE_SIZE) {
+ return false;
+ }
+
+ /*
+ * The overhead of DoH per DNS message can be minimum 160-180
+ * bytes. We should allow more for extra information that can be
+ * included in headers, so let's use 256 bytes. Minimum DNS
+ * message size is 12 bytes. So, (256+12)/12=22. Even that can be
+ * too restricting for some edge cases, but should be good enough
+ * for any practical purposes. Not to mention that HTTP/2 may
+ * include legitimate data that is completely useless for DNS
+ * purposes...
+ *
+ * Anyway, at that point we should have processed enough requests
+ * for such clients (if any).
+ */
+ if (session->processed_useful_data == 0 ||
+ (session->processed_incoming_data /
+ session->processed_useful_data) > 22)
+ {
+ return true;
+ }
+
+ return false;
+}
+
/*
* Read callback from TLS socket.
*/
@@ -977,6 +1231,7 @@ http_readcb(isc_nmhandle_t *handle, isc_result_t result, isc_region_t *region,
void *data) {
isc_nm_http_session_t *session = (isc_nm_http_session_t *)data;
ssize_t readlen;
+ isc_buffer_t input;
REQUIRE(VALID_HTTP2_SESSION(session));
@@ -990,11 +1245,17 @@ http_readcb(isc_nmhandle_t *handle, isc_result_t result, isc_region_t *region,
return;
}
- readlen = nghttp2_session_mem_recv(session->ngsession, region->base,
- region->length);
+ isc_buffer_init(&input, region->base, region->length);
+ isc_buffer_add(&input, region->length);
+
+ readlen = http_process_input_data(session, &input);
if (readlen < 0) {
failed_read_cb(ISC_R_UNEXPECTED, session);
return;
+ } else if (http_is_flooding_peer(session)) {
+ http_log_flooding_peer(session);
+ failed_read_cb(ISC_R_RANGE, session);
+ return;
}
if ((size_t)readlen < region->length) {
@@ -1007,10 +1268,11 @@ http_readcb(isc_nmhandle_t *handle, isc_result_t result, isc_region_t *region,
isc_buffer_putmem(session->buf, region->base + readlen,
unread_size);
isc_nm_pauseread(session->handle);
+ http_do_bio_async(session);
+ } else {
+ /* We might have something to receive or send, do IO */
+ http_do_bio(session, NULL, NULL, NULL);
}
-
- /* We might have something to receive or send, do IO */
- http_do_bio(session, NULL, NULL, NULL);
}
static void
@@ -1046,14 +1308,18 @@ http_writecb(isc_nmhandle_t *handle, isc_result_t result, void *arg) {
}
isc_buffer_free(&req->pending_write_data);
+ session->processed += req->submitted;
isc_mem_put(session->mctx, req, sizeof(*req));
session->sending--;
- http_do_bio(session, NULL, NULL, NULL);
- isc_nmhandle_detach(&transphandle);
- if (result != ISC_R_SUCCESS && session->sending == 0) {
+
+ if (result == ISC_R_SUCCESS) {
+ http_do_bio(session, NULL, NULL, NULL);
+ } else {
finish_http_session(session);
}
+ isc_nmhandle_detach(&transphandle);
+
isc__nm_httpsession_detach(&session);
}
@@ -1199,7 +1465,9 @@ http_send_outgoing(isc_nm_http_session_t *session, isc_nmhandle_t *httphandle,
*send = (isc_http_send_req_t){ .pending_write_data =
session->pending_write_data,
.cb = cb,
- .cbarg = cbarg };
+ .cbarg = cbarg,
+ .submitted = session->submitted };
+ session->submitted = 0;
session->pending_write_data = NULL;
move_pending_send_callbacks(session, send);
@@ -1220,6 +1488,27 @@ nothing_to_send:
return (false);
}
+static inline bool
+http_too_many_active_streams(isc_nm_http_session_t *session) {
+ const uint64_t active_streams = session->received - session->processed;
+ const uint64_t max_active_streams = ISC_MIN(
+ STREAM_CLIENTS_PER_CONN, session->max_concurrent_streams);
+
+ if (session->client) {
+ return false;
+ }
+
+ /*
+ * Do not process incoming data if there are too many active DNS
+ * clients (streams) per connection.
+ */
+ if (active_streams >= max_active_streams) {
+ return true;
+ }
+
+ return false;
+}
+
static void
http_do_bio(isc_nm_http_session_t *session, isc_nmhandle_t *send_httphandle,
isc_nm_cb_t send_cb, void *send_cbarg) {
@@ -1235,59 +1524,140 @@ http_do_bio(isc_nm_http_session_t *session, isc_nmhandle_t *send_httphandle,
finish_http_session(session);
}
return;
- } else if (nghttp2_session_want_read(session->ngsession) == 0 &&
- nghttp2_session_want_write(session->ngsession) == 0 &&
- session->pending_write_data == NULL)
- {
- session->closing = true;
+ }
+
+ if (send_cb != NULL) {
+ INSIST(VALID_NMHANDLE(send_httphandle));
+ (void)http_send_outgoing(session, send_httphandle, send_cb,
+ send_cbarg);
+ return;
+ }
+
+ INSIST(send_httphandle == NULL);
+ INSIST(send_cb == NULL);
+ INSIST(send_cbarg == NULL);
+
+ if (session->pending_write_data != NULL && session->sending == 0) {
+ (void)http_send_outgoing(session, NULL, NULL, NULL);
return;
}
if (nghttp2_session_want_read(session->ngsession) != 0) {
if (!session->reading) {
/* We have not yet started reading from this handle */
+ isc__nmsocket_timer_start(session->handle->sock);
isc_nm_read(session->handle, http_readcb, session);
session->reading = true;
} else if (session->buf != NULL) {
size_t remaining =
isc_buffer_remaininglength(session->buf);
/* Leftover data in the buffer, use it */
- size_t readlen = nghttp2_session_mem_recv(
- session->ngsession,
- isc_buffer_current(session->buf), remaining);
+ size_t remaining_after = 0;
+ ssize_t readlen = 0;
+ isc_nm_http_session_t *tmpsess = NULL;
- if (readlen == remaining) {
+ /*
+ * Let's ensure that HTTP/2 session and its associated
+ * data will not go "out of scope" too early.
+ */
+ isc__nm_httpsession_attach(session, &tmpsess);
+
+ readlen = http_process_input_data(session,
+ session->buf);
+
+ remaining_after =
+ isc_buffer_remaininglength(session->buf);
+
+ if (readlen < 0) {
+ failed_read_cb(ISC_R_UNEXPECTED, session);
+ } else if (http_is_flooding_peer(session)) {
+ http_log_flooding_peer(session);
+ failed_read_cb(ISC_R_RANGE, session);
+ } else if ((size_t)readlen == remaining) {
isc_buffer_free(&session->buf);
+ http_do_bio(session, NULL, NULL, NULL);
+ } else if (remaining_after > 0 &&
+ remaining_after < remaining)
+ {
+ /*
+ * We have processed a part of the data, now
+ * let's delay processing of whatever is left
+ * here. We want it to be an async operation so
+ * that we will:
+ *
+ * a) let other things run;
+ * b) have finer grained control over how much
+ * data is processed at once, because nghttp2
+ * would happily consume as much data we pass to
+ * it and that could overwhelm the server.
+ */
+ http_do_bio_async(session);
} else {
- isc_buffer_forward(session->buf, readlen);
+ (void)http_send_outgoing(session, NULL, NULL,
+ NULL);
}
- http_do_bio(session, send_httphandle, send_cb,
- send_cbarg);
+ isc__nm_httpsession_detach(&tmpsess);
return;
} else {
/* Resume reading, it's idempotent, wait for more */
isc_nm_resumeread(session->handle);
+ isc__nmsocket_timer_start(session->handle->sock);
}
} else {
/* We don't want more data, stop reading for now */
isc_nm_pauseread(session->handle);
}
- if (send_cb != NULL) {
- INSIST(VALID_NMHANDLE(send_httphandle));
- (void)http_send_outgoing(session, send_httphandle, send_cb,
- send_cbarg);
- } else {
- INSIST(send_httphandle == NULL);
- INSIST(send_cb == NULL);
- INSIST(send_cbarg == NULL);
- (void)http_send_outgoing(session, NULL, NULL, NULL);
+ /* we might have some data to send after processing */
+ (void)http_send_outgoing(session, NULL, NULL, NULL);
+
+ if (nghttp2_session_want_read(session->ngsession) == 0 &&
+ nghttp2_session_want_write(session->ngsession) == 0 &&
+ session->pending_write_data == NULL)
+ {
+ session->closing = true;
+ isc_nm_pauseread(session->handle);
+ if (session->sending == 0) {
+ finish_http_session(session);
+ }
}
return;
}
+static void
+http_do_bio_async_cb(void *arg) {
+ isc_nm_http_session_t *session = arg;
+
+ REQUIRE(VALID_HTTP2_SESSION(session));
+
+ if (session->handle != NULL &&
+ !isc__nmsocket_closing(session->handle->sock))
+ {
+ http_do_bio(session, NULL, NULL, NULL);
+ }
+
+ isc__nm_httpsession_detach(&session);
+}
+
+static void
+http_do_bio_async(isc_nm_http_session_t *session) {
+ isc_nm_http_session_t *tmpsess = NULL;
+
+ REQUIRE(VALID_HTTP2_SESSION(session));
+
+ if (session->handle == NULL ||
+ isc__nmsocket_closing(session->handle->sock))
+ {
+ return;
+ }
+ isc__nm_httpsession_attach(session, &tmpsess);
+ isc__nm_async_run(
+ &session->handle->sock->mgr->workers[session->handle->sock->tid],
+ http_do_bio_async_cb, tmpsess);
+}
+
static isc_result_t
get_http_cstream(isc_nmsocket_t *sock, http_cstream_t **streamp) {
http_cstream_t *cstream = sock->h2.connect.cstream;
@@ -1417,6 +1787,7 @@ transport_connect_cb(isc_nmhandle_t *handle, isc_result_t result, void *cbarg) {
}
http_transpost_tcp_nodelay(handle);
+ isc__nmhandle_set_manual_timer(session->handle, true);
http_call_connect_cb(http_sock, session, result);
@@ -1660,6 +2031,7 @@ server_on_begin_headers_callback(nghttp2_session *ngsession,
socket->tid = session->handle->sock->tid;
ISC_LINK_INIT(&socket->h2, link);
ISC_LIST_APPEND(session->sstreams, &socket->h2, link);
+ session->total_opened_sstreams++;
nghttp2_session_set_stream_user_data(ngsession, frame->hd.stream_id,
socket);
@@ -1736,6 +2108,8 @@ server_handle_path_header(isc_nmsocket_t *socket, const uint8_t *value,
socket->mgr->mctx, dns_value,
dns_value_len,
&socket->h2.query_data_len);
+ socket->h2.session->processed_useful_data +=
+ dns_value_len;
} else {
socket->h2.query_too_large = true;
return (ISC_HTTP_ERROR_PAYLOAD_TOO_LARGE);
@@ -2043,6 +2417,15 @@ server_call_cb(isc_nmsocket_t *socket, isc_nm_http_session_t *session,
addr = isc_nmhandle_peeraddr(session->handle);
handle = isc__nmhandle_get(socket, &addr, NULL);
+ if (result != ISC_R_SUCCESS) {
+ data = NULL;
+ } else if (socket->h2.session->handle != NULL) {
+ isc__nmsocket_timer_restart(socket->h2.session->handle->sock);
+ }
+ if (result == ISC_R_SUCCESS) {
+ socket->h2.request_received = true;
+ socket->h2.session->received++;
+ }
socket->h2.cb(handle, result, data, socket->h2.cbarg);
isc_nmhandle_detach(&handle);
}
@@ -2058,6 +2441,12 @@ isc__nm_http_bad_request(isc_nmhandle_t *handle) {
REQUIRE(!atomic_load(&sock->client));
REQUIRE(VALID_HTTP2_SESSION(sock->h2.session));
+ if (sock->h2.response_submitted ||
+ !http_session_active(sock->h2.session))
+ {
+ return;
+ }
+
(void)server_send_error_response(ISC_HTTP_ERROR_BAD_REQUEST,
sock->h2.session->ngsession, sock);
}
@@ -2480,6 +2869,8 @@ httplisten_acceptcb(isc_nmhandle_t *handle, isc_result_t result, void *cbarg) {
isc__nmsocket_attach(httplistensock, &session->serversocket);
server_send_connection_header(session);
+ isc__nmhandle_set_manual_timer(session->handle, true);
+
/* TODO H2 */
http_do_bio(session, NULL, NULL, NULL);
return (ISC_R_SUCCESS);
diff --git a/lib/isc/netmgr/netmgr-int.h b/lib/isc/netmgr/netmgr-int.h
index bc1ba73..3935a4a 100644
--- a/lib/isc/netmgr/netmgr-int.h
+++ b/lib/isc/netmgr/netmgr-int.h
@@ -337,6 +337,7 @@ typedef enum isc__netievent_type {
netievent_privilegedtask,
netievent_settlsctx,
+ netievent_asyncrun,
/*
* event type values higher than this will be treated
@@ -708,6 +709,42 @@ typedef struct isc__netievent__tlsctx {
}
#ifdef HAVE_LIBNGHTTP2
+typedef void (*isc__nm_asyncrun_cb_t)(void *);
+
+typedef struct isc__netievent__asyncrun {
+ isc__netievent_type type;
+ ISC_LINK(isc__netievent_t) link;
+ isc__nm_asyncrun_cb_t cb;
+ void *cbarg;
+} isc__netievent__asyncrun_t;
+
+#define NETIEVENT_ASYNCRUN_TYPE(type) \
+ typedef isc__netievent__asyncrun_t isc__netievent_##type##_t;
+
+#define NETIEVENT_ASYNCRUN_DECL(type) \
+ isc__netievent_##type##_t *isc__nm_get_netievent_##type( \
+ isc_nm_t *nm, isc__nm_asyncrun_cb_t cb, void *cbarg); \
+ void isc__nm_put_netievent_##type(isc_nm_t *nm, \
+ isc__netievent_##type##_t *ievent);
+
+#define NETIEVENT_ASYNCRUN_DEF(type) \
+ isc__netievent_##type##_t *isc__nm_get_netievent_##type( \
+ isc_nm_t *nm, isc__nm_asyncrun_cb_t cb, void *cbarg) { \
+ isc__netievent_##type##_t *ievent = \
+ isc__nm_get_netievent(nm, netievent_##type); \
+ ievent->cb = cb; \
+ ievent->cbarg = cbarg; \
+ \
+ return (ievent); \
+ } \
+ \
+ void isc__nm_put_netievent_##type(isc_nm_t *nm, \
+ isc__netievent_##type##_t *ievent) { \
+ ievent->cb = NULL; \
+ ievent->cbarg = NULL; \
+ isc__nm_put_netievent(nm, ievent); \
+ }
+
typedef struct isc__netievent__http_eps {
NETIEVENT__SOCKET;
isc_nm_http_endpoints_t *endpoints;
@@ -752,6 +789,7 @@ typedef union {
isc__netievent_tlsconnect_t nitc;
isc__netievent__tlsctx_t nitls;
#ifdef HAVE_LIBNGHTTP2
+ isc__netievent__asyncrun_t niasync;
isc__netievent__http_eps_t nihttpeps;
#endif /* HAVE_LIBNGHTTP2 */
} isc__netievent_storage_t;
@@ -948,6 +986,7 @@ typedef struct isc_nmsocket_h2 {
isc_nm_http_endpoints_t **listener_endpoints;
size_t n_listener_endpoints;
+ bool request_received;
bool response_submitted;
struct {
char *uri;
@@ -1232,6 +1271,7 @@ struct isc_nmsocket {
isc_barrier_t barrier;
bool barrier_initialised;
+ atomic_bool manual_read_timer;
#ifdef NETMGR_TRACE
void *backtrace[TRACE_SIZE];
int backtrace_size;
@@ -1550,6 +1590,9 @@ isc__nm_tcp_settimeout(isc_nmhandle_t *handle, uint32_t timeout);
* Set the read timeout for the TCP socket associated with 'handle'.
*/
+void
+isc__nmhandle_tcp_set_manual_timer(isc_nmhandle_t *handle, const bool manual);
+
void
isc__nm_async_tcpconnect(isc__networker_t *worker, isc__netievent_t *ev0);
void
@@ -1792,6 +1835,9 @@ isc__nm_tls_cleartimeout(isc_nmhandle_t *handle);
* around.
*/
+void
+isc__nmhandle_tls_set_manual_timer(isc_nmhandle_t *handle, const bool manual);
+
const char *
isc__nm_tls_verify_tls_peer_result_string(const isc_nmhandle_t *handle);
@@ -1809,6 +1855,15 @@ void
isc__nmhandle_tls_setwritetimeout(isc_nmhandle_t *handle,
uint64_t write_timeout);
+bool
+isc__nmsocket_tls_timer_running(isc_nmsocket_t *sock);
+
+void
+isc__nmsocket_tls_timer_restart(isc_nmsocket_t *sock);
+
+void
+isc__nmsocket_tls_timer_stop(isc_nmsocket_t *sock);
+
void
isc__nm_http_stoplistening(isc_nmsocket_t *sock);
@@ -1901,7 +1956,10 @@ void
isc__nm_http_set_max_streams(isc_nmsocket_t *listener,
const uint32_t max_concurrent_streams);
-#endif
+void
+isc__nm_async_asyncrun(isc__networker_t *worker, isc__netievent_t *ev0);
+
+#endif /* HAVE_LIBNGHTTP2 */
void
isc__nm_async_settlsctx(isc__networker_t *worker, isc__netievent_t *ev0);
@@ -2097,6 +2155,8 @@ NETIEVENT_SOCKET_TYPE(tlsdnscycle);
NETIEVENT_SOCKET_REQ_TYPE(httpsend);
NETIEVENT_SOCKET_TYPE(httpclose);
NETIEVENT_SOCKET_HTTP_EPS_TYPE(httpendpoints);
+
+NETIEVENT_ASYNCRUN_TYPE(asyncrun);
#endif /* HAVE_LIBNGHTTP2 */
NETIEVENT_SOCKET_REQ_TYPE(tcpconnect);
@@ -2171,6 +2231,8 @@ NETIEVENT_SOCKET_DECL(tlsdnscycle);
NETIEVENT_SOCKET_REQ_DECL(httpsend);
NETIEVENT_SOCKET_DECL(httpclose);
NETIEVENT_SOCKET_HTTP_EPS_DECL(httpendpoints);
+
+NETIEVENT_ASYNCRUN_DECL(asyncrun);
#endif /* HAVE_LIBNGHTTP2 */
NETIEVENT_SOCKET_REQ_DECL(tcpconnect);
@@ -2287,3 +2349,20 @@ isc__nmsocket_writetimeout_cb(void *data, isc_result_t eresult);
void
isc__nmsocket_log_tls_session_reuse(isc_nmsocket_t *sock, isc_tls_t *tls);
+
+void
+isc__nmhandle_set_manual_timer(isc_nmhandle_t *handle, const bool manual);
+/*
+ * Set manual read timer control mode - so that it will not get reset
+ * automatically on read nor get started when read is initiated.
+ */
+
+#if HAVE_LIBNGHTTP2
+void
+isc__nm_async_run(isc__networker_t *worker, isc__nm_asyncrun_cb_t cb,
+ void *cbarg);
+/*
+ * Call the given callback asynchronously by the give network manager
+ * worker, pass the given argument to it.
+ */
+#endif /* HAVE_LIBNGHTTP2 */
diff --git a/lib/isc/netmgr/netmgr.c b/lib/isc/netmgr/netmgr.c
index f9e3b70..9167927 100644
--- a/lib/isc/netmgr/netmgr.c
+++ b/lib/isc/netmgr/netmgr.c
@@ -996,6 +996,8 @@ process_netievent(isc__networker_t *worker, isc__netievent_t *ievent) {
NETIEVENT_CASE(httpsend);
NETIEVENT_CASE(httpclose);
NETIEVENT_CASE(httpendpoints);
+
+ NETIEVENT_CASE(asyncrun);
#endif
NETIEVENT_CASE(settlsctx);
NETIEVENT_CASE(sockstop);
@@ -1114,6 +1116,8 @@ NETIEVENT_SOCKET_DEF(tlsdnsshutdown);
NETIEVENT_SOCKET_REQ_DEF(httpsend);
NETIEVENT_SOCKET_DEF(httpclose);
NETIEVENT_SOCKET_HTTP_EPS_DEF(httpendpoints);
+
+NETIEVENT_ASYNCRUN_DEF(asyncrun);
#endif /* HAVE_LIBNGHTTP2 */
NETIEVENT_SOCKET_REQ_DEF(tcpconnect);
@@ -1625,6 +1629,7 @@ isc___nmsocket_init(isc_nmsocket_t *sock, isc_nm_t *mgr, isc_nmsocket_type type,
atomic_init(&sock->keepalive, false);
atomic_init(&sock->connected, false);
atomic_init(&sock->timedout, false);
+ atomic_init(&sock->manual_read_timer, false);
atomic_init(&sock->active_child_connections, 0);
@@ -2134,6 +2139,15 @@ void
isc__nmsocket_timer_restart(isc_nmsocket_t *sock) {
REQUIRE(VALID_NMSOCK(sock));
+ switch (sock->type) {
+#if HAVE_LIBNGHTTP2
+ case isc_nm_tlssocket:
+ return isc__nmsocket_tls_timer_restart(sock);
+#endif /* HAVE_LIBNGHTTP2 */
+ default:
+ break;
+ }
+
if (uv_is_closing((uv_handle_t *)&sock->read_timer)) {
return;
}
@@ -2168,6 +2182,15 @@ bool
isc__nmsocket_timer_running(isc_nmsocket_t *sock) {
REQUIRE(VALID_NMSOCK(sock));
+ switch (sock->type) {
+#if HAVE_LIBNGHTTP2
+ case isc_nm_tlssocket:
+ return isc__nmsocket_tls_timer_running(sock);
+#endif /* HAVE_LIBNGHTTP2 */
+ default:
+ break;
+ }
+
return (uv_is_active((uv_handle_t *)&sock->read_timer));
}
@@ -2188,6 +2211,15 @@ isc__nmsocket_timer_stop(isc_nmsocket_t *sock) {
REQUIRE(VALID_NMSOCK(sock));
+ switch (sock->type) {
+#if HAVE_LIBNGHTTP2
+ case isc_nm_tlssocket:
+ return isc__nmsocket_tls_timer_stop(sock);
+#endif /* HAVE_LIBNGHTTP2 */
+ default:
+ break;
+ }
+
/* uv_timer_stop() is idempotent, no need to check if running */
r = uv_timer_stop(&sock->read_timer);
@@ -3938,6 +3970,52 @@ isc__nmsocket_log_tls_session_reuse(isc_nmsocket_t *sock, isc_tls_t *tls) {
client_sabuf, local_sabuf);
}
+void
+isc__nmhandle_set_manual_timer(isc_nmhandle_t *handle, const bool manual) {
+ REQUIRE(VALID_NMHANDLE(handle));
+ REQUIRE(VALID_NMSOCK(handle->sock));
+
+ isc_nmsocket_t *sock = handle->sock;
+
+ switch (sock->type) {
+ case isc_nm_tcpsocket:
+ isc__nmhandle_tcp_set_manual_timer(handle, manual);
+ return;
+#if HAVE_LIBNGHTTP2
+ case isc_nm_tlssocket:
+ isc__nmhandle_tls_set_manual_timer(handle, manual);
+ return;
+#endif /* HAVE_LIBNGHTTP2 */
+ default:
+ break;
+ };
+
+ UNREACHABLE();
+}
+
+#if HAVE_LIBNGHTTP2
+void
+isc__nm_async_run(isc__networker_t *worker, isc__nm_asyncrun_cb_t cb,
+ void *cbarg) {
+ isc__netievent__asyncrun_t *ievent = NULL;
+ REQUIRE(worker != NULL);
+ REQUIRE(cb != NULL);
+
+ ievent = isc__nm_get_netievent_asyncrun(worker->mgr, cb, cbarg);
+ isc__nm_enqueue_ievent(worker, (isc__netievent_t *)ievent);
+}
+
+void
+isc__nm_async_asyncrun(isc__networker_t *worker, isc__netievent_t *ev0) {
+ isc__netievent_asyncrun_t *ievent = (isc__netievent_asyncrun_t *)ev0;
+
+ UNUSED(worker);
+
+ ievent->cb(ievent->cbarg);
+}
+
+#endif /* HAVE_LIBNGHTTP2 */
+
#ifdef NETMGR_TRACE
/*
* Dump all active sockets in netmgr. We output to stderr
diff --git a/lib/isc/netmgr/tcp.c b/lib/isc/netmgr/tcp.c
index 37d44bd..925bc85 100644
--- a/lib/isc/netmgr/tcp.c
+++ b/lib/isc/netmgr/tcp.c
@@ -784,7 +784,9 @@ isc__nm_async_tcpstartread(isc__networker_t *worker, isc__netievent_t *ev0) {
return;
}
- isc__nmsocket_timer_start(sock);
+ if (!atomic_load(&sock->manual_read_timer)) {
+ isc__nmsocket_timer_start(sock);
+ }
}
void
@@ -822,7 +824,9 @@ isc__nm_async_tcppauseread(isc__networker_t *worker, isc__netievent_t *ev0) {
REQUIRE(sock->tid == isc_nm_tid());
UNUSED(worker);
- isc__nmsocket_timer_stop(sock);
+ if (!atomic_load(&sock->manual_read_timer)) {
+ isc__nmsocket_timer_stop(sock);
+ }
isc__nm_stop_reading(sock);
}
@@ -931,8 +935,10 @@ isc__nm_tcp_read_cb(uv_stream_t *stream, ssize_t nread, const uv_buf_t *buf) {
}
}
- /* The timer will be updated */
- isc__nmsocket_timer_restart(sock);
+ if (!atomic_load(&sock->manual_read_timer)) {
+ /* The timer will be updated */
+ isc__nmsocket_timer_restart(sock);
+ }
}
free:
@@ -1521,3 +1527,15 @@ isc__nm_tcp_listener_nactive(isc_nmsocket_t *listener) {
INSIST(nactive >= 0);
return (nactive);
}
+
+void
+isc__nmhandle_tcp_set_manual_timer(isc_nmhandle_t *handle, const bool manual) {
+ isc_nmsocket_t *sock;
+
+ REQUIRE(VALID_NMHANDLE(handle));
+ sock = handle->sock;
+ REQUIRE(VALID_NMSOCK(sock));
+ REQUIRE(sock->type == isc_nm_tcpsocket);
+
+ atomic_store(&sock->manual_read_timer, manual);
+}
diff --git a/lib/isc/netmgr/tlsstream.c b/lib/isc/netmgr/tlsstream.c
index a3fc6d2..c7137a0 100644
--- a/lib/isc/netmgr/tlsstream.c
+++ b/lib/isc/netmgr/tlsstream.c
@@ -60,6 +60,12 @@ tls_error_to_result(const int tls_err, const int tls_state, isc_tls_t *tls) {
}
}
+static void
+tls_read_start(isc_nmsocket_t *sock);
+
+static void
+tls_read_stop(isc_nmsocket_t *sock);
+
static void
tls_failed_read_cb(isc_nmsocket_t *sock, const isc_result_t result);
@@ -203,8 +209,13 @@ tls_failed_read_cb(isc_nmsocket_t *sock, const isc_result_t result) {
tls_call_connect_cb(sock, handle, result);
isc__nmsocket_clearcb(sock);
isc_nmhandle_detach(&handle);
- } else if (sock->recv_cb != NULL && sock->statichandle != NULL &&
- (sock->recv_read || result == ISC_R_TIMEDOUT))
+ goto do_destroy;
+ }
+
+ isc__nmsocket_timer_stop(sock);
+
+ if (sock->recv_cb != NULL && sock->statichandle != NULL &&
+ (sock->recv_read || result == ISC_R_TIMEDOUT))
{
isc__nm_uvreq_t *req = NULL;
INSIST(VALID_NMHANDLE(sock->statichandle));
@@ -218,13 +229,13 @@ tls_failed_read_cb(isc_nmsocket_t *sock, const isc_result_t result) {
}
isc__nm_readcb(sock, req, result);
if (result == ISC_R_TIMEDOUT &&
- (sock->outerhandle == NULL ||
- isc__nmsocket_timer_running(sock->outerhandle->sock)))
+ isc__nmsocket_timer_running(sock))
{
destroy = false;
}
}
+do_destroy:
if (destroy) {
isc__nmsocket_prep_destroy(sock);
}
@@ -344,6 +355,8 @@ tls_try_handshake(isc_nmsocket_t *sock, isc_result_t *presult) {
INSIST(sock->statichandle == NULL);
isc__nmsocket_log_tls_session_reuse(sock, sock->tlsstream.tls);
tlshandle = isc__nmhandle_get(sock, &sock->peer, &sock->iface);
+ isc__nmsocket_timer_stop(sock);
+ tls_read_stop(sock);
if (isc__nm_closing(sock)) {
result = ISC_R_SHUTTINGDOWN;
@@ -437,6 +450,7 @@ tls_do_bio(isc_nmsocket_t *sock, isc_region_t *received_data,
sock->tlsstream.state = TLS_HANDSHAKE;
rv = tls_try_handshake(sock, NULL);
INSIST(SSL_is_init_finished(sock->tlsstream.tls) == 0);
+ isc__nmsocket_timer_restart(sock);
} else if (sock->tlsstream.state == TLS_CLOSED) {
return;
} else { /* initialised and doing I/O */
@@ -502,6 +516,7 @@ tls_do_bio(isc_nmsocket_t *sock, isc_region_t *received_data,
!atomic_load(&sock->readpaused) &&
sock->statichandle != NULL && !finish)
{
+ bool was_new_data = false;
uint8_t recv_buf[TLS_BUF_SIZE];
INSIST(sock->tlsstream.state > TLS_HANDSHAKE);
while ((rv = SSL_read_ex(sock->tlsstream.tls, recv_buf,
@@ -510,7 +525,7 @@ tls_do_bio(isc_nmsocket_t *sock, isc_region_t *received_data,
isc_region_t region;
region = (isc_region_t){ .base = &recv_buf[0],
.length = len };
-
+ was_new_data = true;
INSIST(VALID_NMHANDLE(sock->statichandle));
sock->recv_cb(sock->statichandle, ISC_R_SUCCESS,
&region, sock->recv_cbarg);
@@ -547,8 +562,29 @@ tls_do_bio(isc_nmsocket_t *sock, isc_region_t *received_data,
break;
}
}
+
+ if (was_new_data && !sock->manual_read_timer) {
+ /*
+ * Some data has been decrypted, it is the right
+ * time to stop the read timer as it will be
+ * restarted on the next read attempt.
+ */
+ isc__nmsocket_timer_stop(sock);
+ }
}
}
+
+ /*
+ * Setting 'finish' to 'true' means that we are about to close the
+ * TLS stream (we intend to send TLS shutdown message to the
+ * remote side). After that no new data can be received, so we
+ * should stop the timer regardless of the
+ * 'sock->manual_read_timer' value.
+ */
+ if (finish) {
+ isc__nmsocket_timer_stop(sock);
+ }
+
errno = 0;
tls_status = SSL_get_error(sock->tlsstream.tls, rv);
saved_errno = errno;
@@ -601,14 +637,7 @@ tls_do_bio(isc_nmsocket_t *sock, isc_region_t *received_data,
return;
}
- INSIST(VALID_NMHANDLE(sock->outerhandle));
-
- if (sock->tlsstream.reading) {
- isc_nm_resumeread(sock->outerhandle);
- } else if (sock->tlsstream.state == TLS_HANDSHAKE) {
- sock->tlsstream.reading = true;
- isc_nm_read(sock->outerhandle, tls_readcb, sock);
- }
+ tls_read_start(sock);
return;
default:
result = tls_error_to_result(tls_status, sock->tlsstream.state,
@@ -742,6 +771,7 @@ tlslisten_acceptcb(isc_nmhandle_t *handle, isc_result_t result, void *cbarg) {
RUNTIME_CHECK(result == ISC_R_SUCCESS);
/* TODO: catch failure code, detach tlssock, and log the error */
+ isc__nmhandle_set_manual_timer(tlssock->outerhandle, true);
tls_do_bio(tlssock, NULL, NULL, false);
return (result);
}
@@ -897,6 +927,29 @@ isc__nm_tls_read(isc_nmhandle_t *handle, isc_nm_recv_cb_t cb, void *cbarg) {
(isc__netievent_t *)ievent);
}
+static void
+tls_read_start(isc_nmsocket_t *sock) {
+ INSIST(VALID_NMHANDLE(sock->outerhandle));
+
+ if (sock->tlsstream.reading) {
+ isc_nm_resumeread(sock->outerhandle);
+ } else if (sock->tlsstream.state == TLS_HANDSHAKE) {
+ sock->tlsstream.reading = true;
+ isc_nm_read(sock->outerhandle, tls_readcb, sock);
+ }
+
+ if (!sock->manual_read_timer) {
+ isc__nmsocket_timer_start(sock);
+ }
+}
+
+static void
+tls_read_stop(isc_nmsocket_t *sock) {
+ if (sock->outerhandle != NULL) {
+ isc_nm_pauseread(sock->outerhandle);
+ }
+}
+
void
isc__nm_tls_pauseread(isc_nmhandle_t *handle) {
REQUIRE(VALID_NMHANDLE(handle));
@@ -905,9 +958,11 @@ isc__nm_tls_pauseread(isc_nmhandle_t *handle) {
if (atomic_compare_exchange_strong(&handle->sock->readpaused,
&(bool){ false }, true))
{
- if (handle->sock->outerhandle != NULL) {
- isc_nm_pauseread(handle->sock->outerhandle);
+ if (!atomic_load(&handle->sock->manual_read_timer)) {
+ isc__nmsocket_timer_stop(handle->sock);
}
+
+ tls_read_stop(handle->sock);
}
}
@@ -936,6 +991,7 @@ tls_close_direct(isc_nmsocket_t *sock) {
* external references, we can close everything.
*/
if (sock->outerhandle != NULL) {
+ isc__nmsocket_timer_stop(sock);
isc_nm_pauseread(sock->outerhandle);
isc__nmsocket_clearcb(sock->outerhandle->sock);
isc_nmhandle_detach(&sock->outerhandle);
@@ -1080,6 +1136,7 @@ tcp_connected(isc_nmhandle_t *handle, isc_result_t result, void *cbarg) {
*/
handle->sock->tlsstream.tlssocket = tlssock;
+ isc__nmhandle_set_manual_timer(tlssock->outerhandle, true);
tls_do_bio(tlssock, NULL, NULL, false);
return;
error:
@@ -1246,6 +1303,44 @@ isc__nmhandle_tls_setwritetimeout(isc_nmhandle_t *handle,
}
}
+bool
+isc__nmsocket_tls_timer_running(isc_nmsocket_t *sock) {
+ REQUIRE(VALID_NMSOCK(sock));
+ REQUIRE(sock->type == isc_nm_tlssocket);
+
+ if (sock->outerhandle != NULL) {
+ INSIST(VALID_NMHANDLE(sock->outerhandle));
+ REQUIRE(VALID_NMSOCK(sock->outerhandle->sock));
+ return isc__nmsocket_timer_running(sock->outerhandle->sock);
+ }
+
+ return false;
+}
+
+void
+isc__nmsocket_tls_timer_restart(isc_nmsocket_t *sock) {
+ REQUIRE(VALID_NMSOCK(sock));
+ REQUIRE(sock->type == isc_nm_tlssocket);
+
+ if (sock->outerhandle != NULL) {
+ INSIST(VALID_NMHANDLE(sock->outerhandle));
+ REQUIRE(VALID_NMSOCK(sock->outerhandle->sock));
+ isc__nmsocket_timer_restart(sock->outerhandle->sock);
+ }
+}
+
+void
+isc__nmsocket_tls_timer_stop(isc_nmsocket_t *sock) {
+ REQUIRE(VALID_NMSOCK(sock));
+ REQUIRE(sock->type == isc_nm_tlssocket);
+
+ if (sock->outerhandle != NULL) {
+ INSIST(VALID_NMHANDLE(sock->outerhandle));
+ REQUIRE(VALID_NMSOCK(sock->outerhandle->sock));
+ isc__nmsocket_timer_stop(sock->outerhandle->sock);
+ }
+}
+
const char *
isc__nm_tls_verify_tls_peer_result_string(const isc_nmhandle_t *handle) {
isc_nmsocket_t *sock = NULL;
@@ -1346,3 +1441,15 @@ tls_try_shutdown(isc_tls_t *tls, const bool force) {
(void)SSL_shutdown(tls);
}
}
+
+void
+isc__nmhandle_tls_set_manual_timer(isc_nmhandle_t *handle, const bool manual) {
+ isc_nmsocket_t *sock;
+
+ REQUIRE(VALID_NMHANDLE(handle));
+ sock = handle->sock;
+ REQUIRE(VALID_NMSOCK(sock));
+ REQUIRE(sock->type == isc_nm_tlssocket);
+
+ atomic_store(&sock->manual_read_timer, manual);
+}
--
2.33.0