diff options
author | Harald Welte <laforge@osmocom.org> | 2024-02-24 06:51:04 +0100 |
---|---|---|
committer | Vadim Yanitskiy <vyanitskiy@sysmocom.de> | 2024-03-15 00:30:22 +0700 |
commit | 0eed4b7caec1726c4facb6b2a795e73c220f4ef2 (patch) | |
tree | 0e574bcd254ea6ac90f3416eed053fa0869e258b | |
parent | a33f72e55331dd9e9be4fb7241183faf6d90e281 (diff) |
Fix critical bug in default TCP keepalive user timeout
It turns out that our calculation of the TCP_USER_TIMEOUT value was
flawed in several ways:
* there should have been parenthesis around the + operator
(line->keepalive_probe_interval + line->keepalive_idle_timeout) as the
keepalive_idle_timeout is in seconds, not milli-seconds.
* in the default case, all those values are configured to -1
(E1INP_USE_DEFAULT). This means we're using
1000 * -1 * -1 + -1 = 999
i.e. just below a second which clearly is not enough for a lossy
satellite or wifi back-haul.
This fixes a regression introduced in Ia7659c209aea0d26eb37d31e771adc91b17ae668
(libosmo-abis >= 1.4.0) when TCP keepalive user timeouts became enabled
by default.
The initial support for TCP_USER_TIMEOUT was merged in
I5e7425958472aa5d758e09bfbefc7d7d37bf6f5f (libosmo-abis >= 0.7.0) but
since TCP keepalives were not yet enabled by default, only users with
explicit TCP keepalive configuration in their config files would be
affected - and then only of the second part of the bug (operator
precedence).
In addition, let's print the actually-used values to the log, helping to
spot unintended values.
Change-Id: Idca24d3e676a45d860d9eec60dc2097d8d87f3bf
Related: OS#5785, OS#6375, SYS#6801
Fixes: Ia7659c209aea0d26eb37d31e771adc91b17ae668
(cherry picked from commit 12fae9aeebd86e242abd5c682a12fd1c9da68497)
-rw-r--r-- | src/input/ipaccess.c | 39 |
1 files changed, 18 insertions, 21 deletions
diff --git a/src/input/ipaccess.c b/src/input/ipaccess.c index acbeda1..015407d 100644 --- a/src/input/ipaccess.c +++ b/src/input/ipaccess.c @@ -599,7 +599,7 @@ struct e1inp_driver ipaccess_driver = { static void update_fd_settings(struct e1inp_line *line, int fd) { int ret; - int val; + int val, idle_val, interval_val, retry_count_val, user_timeout_val; if (line->keepalive_num_probes) { /* Enable TCP keepalive to find out if the connection is gone */ @@ -611,42 +611,39 @@ static void update_fd_settings(struct e1inp_line *line, int fd) else LOGP(DLINP, LOGL_NOTICE, "TCP Keepalive is enabled\n"); + idle_val = line->keepalive_idle_timeout > 0 ? + line->keepalive_idle_timeout : + DEFAULT_TCP_KEEPALIVE_IDLE_TIMEOUT; + interval_val = line->keepalive_probe_interval > -1 ? + line->keepalive_probe_interval : + DEFAULT_TCP_KEEPALIVE_INTERVAL; + retry_count_val = line->keepalive_num_probes > 0 ? + line->keepalive_num_probes : + DEFAULT_TCP_KEEPALIVE_RETRY_COUNT; + user_timeout_val = 1000 * retry_count_val * (interval_val + idle_val); + LOGP(DLINP, LOGL_NOTICE, + "TCP keepalive idle_timeout=%us, interval=%us, retry_count=%u user_timeout=%ums\n", + idle_val, interval_val, retry_count_val, user_timeout_val); /* The following options are not portable! */ - val = line->keepalive_idle_timeout > 0 ? - line->keepalive_idle_timeout : - DEFAULT_TCP_KEEPALIVE_IDLE_TIMEOUT; - ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPIDLE, - &val, sizeof(val)); + ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPIDLE, &idle_val, sizeof(idle_val)); if (ret < 0) { LOGP(DLINP, LOGL_ERROR, "Failed to set TCP keepalive idle time: %s\n", strerror(errno)); } - val = line->keepalive_probe_interval > -1 ? - line->keepalive_probe_interval : - DEFAULT_TCP_KEEPALIVE_INTERVAL; - ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPINTVL, - &val, sizeof(val)); + ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPINTVL, &interval_val, sizeof(interval_val)); if (ret < 0) { LOGP(DLINP, LOGL_ERROR, "Failed to set TCP keepalive interval: %s\n", strerror(errno)); } - val = line->keepalive_num_probes > 0 ? - line->keepalive_num_probes : - DEFAULT_TCP_KEEPALIVE_RETRY_COUNT; - ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPCNT, - &val, sizeof(val)); + ret = setsockopt(fd, IPPROTO_TCP, TCP_KEEPCNT, &retry_count_val, sizeof(retry_count_val)); if (ret < 0) { LOGP(DLINP, LOGL_ERROR, "Failed to set TCP keepalive count: %s\n", strerror(errno)); } - val = 1000 * line->keepalive_num_probes * - line->keepalive_probe_interval + - line->keepalive_idle_timeout; - ret = setsockopt(fd, IPPROTO_TCP, TCP_USER_TIMEOUT, - &val, sizeof(val)); + ret = setsockopt(fd, IPPROTO_TCP, TCP_USER_TIMEOUT, &user_timeout_val, sizeof(user_timeout_val)); if (ret < 0) { LOGP(DLINP, LOGL_ERROR, "Failed to set TCP user timeout: %s\n", |