diff options
Diffstat (limited to 'src/or/geoip.c')
| -rw-r--r-- | src/or/geoip.c | 346 |
1 files changed, 216 insertions, 130 deletions
diff --git a/src/or/geoip.c b/src/or/geoip.c index 5bb2410a75..73194ae9c6 100644 --- a/src/or/geoip.c +++ b/src/or/geoip.c @@ -44,6 +44,9 @@ static strmap_t *country_idxplus1_by_lc_code = NULL; /** A list of all known geoip_entry_t, sorted by ip_low. */ static smartlist_t *geoip_entries = NULL; +/** SHA1 digest of the GeoIP file to include in extra-info descriptors. */ +static char geoip_digest[DIGEST_LEN]; + /** Return the index of the <b>country</b>'s entry in the GeoIP DB * if it is a valid 2-letter country code, otherwise return -1. */ @@ -113,10 +116,10 @@ geoip_parse_entry(const char *line) ++line; if (*line == '#') return 0; - if (sscanf(line,"%u,%u,%2s", &low, &high, b) == 3) { + if (tor_sscanf(line,"%u,%u,%2s", &low, &high, b) == 3) { geoip_add_entry(low, high, b); return 0; - } else if (sscanf(line,"\"%u\",\"%u\",\"%2s\",", &low, &high, b) == 3) { + } else if (tor_sscanf(line,"\"%u\",\"%u\",\"%2s\",", &low, &high, b) == 3) { geoip_add_entry(low, high, b); return 0; } else { @@ -159,7 +162,7 @@ _geoip_compare_key_to_entry(const void *_key, const void **_member) /** Return 1 if we should collect geoip stats on bridge users, and * include them in our extrainfo descriptor. Else return 0. */ int -should_record_bridge_info(or_options_t *options) +should_record_bridge_info(const or_options_t *options) { return options->BridgeRelay && options->BridgeRecordUsageByCountry; } @@ -196,13 +199,14 @@ init_geoip_countries(void) * with '#' (comments). */ int -geoip_load_file(const char *filename, or_options_t *options) +geoip_load_file(const char *filename, const or_options_t *options) { FILE *f; const char *msg = ""; int severity = options_need_geoip_info(options, &msg) ? LOG_WARN : LOG_INFO; + crypto_digest_env_t *geoip_digest_env = NULL; clear_geoip_db(); - if (!(f = fopen(filename, "r"))) { + if (!(f = tor_fopen_cloexec(filename, "r"))) { log_fn(severity, LD_GENERAL, "Failed to open GEOIP file %s. %s", filename, msg); return -1; @@ -214,11 +218,13 @@ geoip_load_file(const char *filename, or_options_t *options) smartlist_free(geoip_entries); } geoip_entries = smartlist_create(); + geoip_digest_env = crypto_new_digest_env(); log_notice(LD_GENERAL, "Parsing GEOIP file %s.", filename); while (!feof(f)) { char buf[512]; if (fgets(buf, (int)sizeof(buf), f) == NULL) break; + crypto_digest_add_bytes(geoip_digest_env, buf, strlen(buf)); /* FFFF track full country name. */ geoip_parse_entry(buf); } @@ -231,6 +237,11 @@ geoip_load_file(const char *filename, or_options_t *options) * country. */ refresh_all_country_info(); + /* Remember file digest so that we can include it in our extra-info + * descriptors. */ + crypto_digest_get_digest(geoip_digest_env, geoip_digest, DIGEST_LEN); + crypto_free_digest_env(geoip_digest_env); + return 0; } @@ -278,6 +289,15 @@ geoip_is_loaded(void) return geoip_countries != NULL && geoip_entries != NULL; } +/** Return the hex-encoded SHA1 digest of the loaded GeoIP file. The + * result does not need to be deallocated, but will be overwritten by the + * next call of hex_str(). */ +const char * +geoip_db_digest(void) +{ + return hex_str(geoip_digest, DIGEST_LEN); +} + /** Entry in a map from IP address to the last time we've seen an incoming * connection from that IP address. Used by bridges only, to track which * countries have them blocked. */ @@ -404,7 +424,7 @@ void geoip_note_client_seen(geoip_client_action_t action, uint32_t addr, time_t now) { - or_options_t *options = get_options(); + const or_options_t *options = get_options(); clientmap_entry_t lookup, *ent; if (action == GEOIP_CLIENT_CONNECT) { /* Only remember statistics as entry guard or as bridge. */ @@ -910,10 +930,9 @@ geoip_dirreq_stats_init(time_t now) start_of_dirreq_stats_interval = now; } -/** Stop collecting directory request stats in a way that we can re-start - * doing so in geoip_dirreq_stats_init(). */ +/** Reset counters for dirreq stats. */ void -geoip_dirreq_stats_term(void) +geoip_reset_dirreq_stats(time_t now) { SMARTLIST_FOREACH(geoip_countries, geoip_country_t *, c, { c->n_v2_ns_requests = c->n_v3_ns_requests = 0; @@ -945,59 +964,44 @@ geoip_dirreq_stats_term(void) tor_free(this); } } - start_of_dirreq_stats_interval = 0; + start_of_dirreq_stats_interval = now; } -/** Write dirreq statistics to $DATADIR/stats/dirreq-stats and return when - * we would next want to write. */ -time_t -geoip_dirreq_stats_write(time_t now) +/** Stop collecting directory request stats in a way that we can re-start + * doing so in geoip_dirreq_stats_init(). */ +void +geoip_dirreq_stats_term(void) { - char *statsdir = NULL, *filename = NULL; - char *data_v2 = NULL, *data_v3 = NULL; - char written[ISO_TIME_LEN+1]; - open_file_t *open_file = NULL; + geoip_reset_dirreq_stats(0); +} + +/** Return a newly allocated string containing the dirreq statistics + * until <b>now</b>, or NULL if we're not collecting dirreq stats. Caller + * must ensure start_of_dirreq_stats_interval is in the past. */ +char * +geoip_format_dirreq_stats(time_t now) +{ + char t[ISO_TIME_LEN+1]; double v2_share = 0.0, v3_share = 0.0; - FILE *out; int i; + char *v3_ips_string, *v2_ips_string, *v3_reqs_string, *v2_reqs_string, + *v2_share_string = NULL, *v3_share_string = NULL, + *v3_direct_dl_string, *v2_direct_dl_string, + *v3_tunneled_dl_string, *v2_tunneled_dl_string; + char *result; if (!start_of_dirreq_stats_interval) - return 0; /* Not initialized. */ - if (start_of_dirreq_stats_interval + WRITE_STATS_INTERVAL > now) - goto done; /* Not ready to write. */ + return NULL; /* Not initialized. */ - /* Discard all items in the client history that are too old. */ - geoip_remove_old_clients(start_of_dirreq_stats_interval); + tor_assert(now >= start_of_dirreq_stats_interval); - statsdir = get_datadir_fname("stats"); - if (check_private_dir(statsdir, CPD_CREATE) < 0) - goto done; - filename = get_datadir_fname2("stats", "dirreq-stats"); - data_v2 = geoip_get_client_history(GEOIP_CLIENT_NETWORKSTATUS_V2); - data_v3 = geoip_get_client_history(GEOIP_CLIENT_NETWORKSTATUS); - format_iso_time(written, now); - out = start_writing_to_stdio_file(filename, OPEN_FLAGS_APPEND, - 0600, &open_file); - if (!out) - goto done; - if (fprintf(out, "dirreq-stats-end %s (%d s)\ndirreq-v3-ips %s\n" - "dirreq-v2-ips %s\n", written, - (unsigned) (now - start_of_dirreq_stats_interval), - data_v3 ? data_v3 : "", data_v2 ? data_v2 : "") < 0) - goto done; - tor_free(data_v2); - tor_free(data_v3); + format_iso_time(t, now); + v2_ips_string = geoip_get_client_history(GEOIP_CLIENT_NETWORKSTATUS_V2); + v3_ips_string = geoip_get_client_history(GEOIP_CLIENT_NETWORKSTATUS); + v2_reqs_string = geoip_get_request_history( + GEOIP_CLIENT_NETWORKSTATUS_V2); + v3_reqs_string = geoip_get_request_history(GEOIP_CLIENT_NETWORKSTATUS); - data_v2 = geoip_get_request_history(GEOIP_CLIENT_NETWORKSTATUS_V2); - data_v3 = geoip_get_request_history(GEOIP_CLIENT_NETWORKSTATUS); - if (fprintf(out, "dirreq-v3-reqs %s\ndirreq-v2-reqs %s\n", - data_v3 ? data_v3 : "", data_v2 ? data_v2 : "") < 0) - goto done; - tor_free(data_v2); - tor_free(data_v3); - SMARTLIST_FOREACH(geoip_countries, geoip_country_t *, c, { - c->n_v2_ns_requests = c->n_v3_ns_requests = 0; - }); #define RESPONSE_GRANULARITY 8 for (i = 0; i < GEOIP_NS_RESPONSE_NUM; i++) { ns_v2_responses[i] = round_uint32_to_next_multiple_of( @@ -1006,61 +1010,117 @@ geoip_dirreq_stats_write(time_t now) ns_v3_responses[i], RESPONSE_GRANULARITY); } #undef RESPONSE_GRANULARITY - if (fprintf(out, "dirreq-v3-resp ok=%u,not-enough-sigs=%u,unavailable=%u," - "not-found=%u,not-modified=%u,busy=%u\n", - ns_v3_responses[GEOIP_SUCCESS], - ns_v3_responses[GEOIP_REJECT_NOT_ENOUGH_SIGS], - ns_v3_responses[GEOIP_REJECT_UNAVAILABLE], - ns_v3_responses[GEOIP_REJECT_NOT_FOUND], - ns_v3_responses[GEOIP_REJECT_NOT_MODIFIED], - ns_v3_responses[GEOIP_REJECT_BUSY]) < 0) - goto done; - if (fprintf(out, "dirreq-v2-resp ok=%u,unavailable=%u," - "not-found=%u,not-modified=%u,busy=%u\n", - ns_v2_responses[GEOIP_SUCCESS], - ns_v2_responses[GEOIP_REJECT_UNAVAILABLE], - ns_v2_responses[GEOIP_REJECT_NOT_FOUND], - ns_v2_responses[GEOIP_REJECT_NOT_MODIFIED], - ns_v2_responses[GEOIP_REJECT_BUSY]) < 0) - goto done; - memset(ns_v2_responses, 0, sizeof(ns_v2_responses)); - memset(ns_v3_responses, 0, sizeof(ns_v3_responses)); + if (!geoip_get_mean_shares(now, &v2_share, &v3_share)) { - if (fprintf(out, "dirreq-v2-share %0.2lf%%\n", v2_share*100) < 0) - goto done; - if (fprintf(out, "dirreq-v3-share %0.2lf%%\n", v3_share*100) < 0) - goto done; + tor_asprintf(&v2_share_string, "dirreq-v2-share %0.2lf%%\n", + v2_share*100); + tor_asprintf(&v3_share_string, "dirreq-v3-share %0.2lf%%\n", + v3_share*100); } - data_v2 = geoip_get_dirreq_history(GEOIP_CLIENT_NETWORKSTATUS_V2, - DIRREQ_DIRECT); - data_v3 = geoip_get_dirreq_history(GEOIP_CLIENT_NETWORKSTATUS, - DIRREQ_DIRECT); - if (fprintf(out, "dirreq-v3-direct-dl %s\ndirreq-v2-direct-dl %s\n", - data_v3 ? data_v3 : "", data_v2 ? data_v2 : "") < 0) - goto done; - tor_free(data_v2); - tor_free(data_v3); - data_v2 = geoip_get_dirreq_history(GEOIP_CLIENT_NETWORKSTATUS_V2, - DIRREQ_TUNNELED); - data_v3 = geoip_get_dirreq_history(GEOIP_CLIENT_NETWORKSTATUS, - DIRREQ_TUNNELED); - if (fprintf(out, "dirreq-v3-tunneled-dl %s\ndirreq-v2-tunneled-dl %s\n", - data_v3 ? data_v3 : "", data_v2 ? data_v2 : "") < 0) - goto done; + v2_direct_dl_string = geoip_get_dirreq_history( + GEOIP_CLIENT_NETWORKSTATUS_V2, DIRREQ_DIRECT); + v3_direct_dl_string = geoip_get_dirreq_history( + GEOIP_CLIENT_NETWORKSTATUS, DIRREQ_DIRECT); + + v2_tunneled_dl_string = geoip_get_dirreq_history( + GEOIP_CLIENT_NETWORKSTATUS_V2, DIRREQ_TUNNELED); + v3_tunneled_dl_string = geoip_get_dirreq_history( + GEOIP_CLIENT_NETWORKSTATUS, DIRREQ_TUNNELED); + + /* Put everything together into a single string. */ + tor_asprintf(&result, "dirreq-stats-end %s (%d s)\n" + "dirreq-v3-ips %s\n" + "dirreq-v2-ips %s\n" + "dirreq-v3-reqs %s\n" + "dirreq-v2-reqs %s\n" + "dirreq-v3-resp ok=%u,not-enough-sigs=%u,unavailable=%u," + "not-found=%u,not-modified=%u,busy=%u\n" + "dirreq-v2-resp ok=%u,unavailable=%u," + "not-found=%u,not-modified=%u,busy=%u\n" + "%s" + "%s" + "dirreq-v3-direct-dl %s\n" + "dirreq-v2-direct-dl %s\n" + "dirreq-v3-tunneled-dl %s\n" + "dirreq-v2-tunneled-dl %s\n", + t, + (unsigned) (now - start_of_dirreq_stats_interval), + v3_ips_string ? v3_ips_string : "", + v2_ips_string ? v2_ips_string : "", + v3_reqs_string ? v3_reqs_string : "", + v2_reqs_string ? v2_reqs_string : "", + ns_v3_responses[GEOIP_SUCCESS], + ns_v3_responses[GEOIP_REJECT_NOT_ENOUGH_SIGS], + ns_v3_responses[GEOIP_REJECT_UNAVAILABLE], + ns_v3_responses[GEOIP_REJECT_NOT_FOUND], + ns_v3_responses[GEOIP_REJECT_NOT_MODIFIED], + ns_v3_responses[GEOIP_REJECT_BUSY], + ns_v2_responses[GEOIP_SUCCESS], + ns_v2_responses[GEOIP_REJECT_UNAVAILABLE], + ns_v2_responses[GEOIP_REJECT_NOT_FOUND], + ns_v2_responses[GEOIP_REJECT_NOT_MODIFIED], + ns_v2_responses[GEOIP_REJECT_BUSY], + v2_share_string ? v2_share_string : "", + v3_share_string ? v3_share_string : "", + v3_direct_dl_string ? v3_direct_dl_string : "", + v2_direct_dl_string ? v2_direct_dl_string : "", + v3_tunneled_dl_string ? v3_tunneled_dl_string : "", + v2_tunneled_dl_string ? v2_tunneled_dl_string : ""); + + /* Free partial strings. */ + tor_free(v3_ips_string); + tor_free(v2_ips_string); + tor_free(v3_reqs_string); + tor_free(v2_reqs_string); + tor_free(v2_share_string); + tor_free(v3_share_string); + tor_free(v3_direct_dl_string); + tor_free(v2_direct_dl_string); + tor_free(v3_tunneled_dl_string); + tor_free(v2_tunneled_dl_string); - finish_writing_to_file(open_file); - open_file = NULL; + return result; +} - start_of_dirreq_stats_interval = now; +/** If 24 hours have passed since the beginning of the current dirreq + * stats period, write dirreq stats to $DATADIR/stats/dirreq-stats + * (possibly overwriting an existing file) and reset counters. Return + * when we would next want to write dirreq stats or 0 if we never want to + * write. */ +time_t +geoip_dirreq_stats_write(time_t now) +{ + char *statsdir = NULL, *filename = NULL, *str = NULL; + + if (!start_of_dirreq_stats_interval) + return 0; /* Not initialized. */ + if (start_of_dirreq_stats_interval + WRITE_STATS_INTERVAL > now) + goto done; /* Not ready to write. */ + + /* Discard all items in the client history that are too old. */ + geoip_remove_old_clients(start_of_dirreq_stats_interval); + + /* Generate history string .*/ + str = geoip_format_dirreq_stats(now); + + /* Write dirreq-stats string to disk. */ + statsdir = get_datadir_fname("stats"); + if (check_private_dir(statsdir, CPD_CREATE, get_options()->User) < 0) { + log_warn(LD_HIST, "Unable to create stats/ directory!"); + goto done; + } + filename = get_datadir_fname2("stats", "dirreq-stats"); + if (write_str_to_file(filename, str, 0) < 0) + log_warn(LD_HIST, "Unable to write dirreq statistics to disk!"); + + /* Reset measurement interval start. */ + geoip_reset_dirreq_stats(now); done: - if (open_file) - abort_writing_to_file(open_file); - tor_free(filename); tor_free(statsdir); - tor_free(data_v2); - tor_free(data_v3); + tor_free(filename); + tor_free(str); return start_of_dirreq_stats_interval + WRITE_STATS_INTERVAL; } @@ -1140,8 +1200,8 @@ static char *bridge_stats_extrainfo = NULL; /** Return a newly allocated string holding our bridge usage stats by country * in a format suitable for inclusion in an extrainfo document. Return NULL on * failure. */ -static char * -format_bridge_stats_extrainfo(time_t now) +char * +geoip_format_bridge_stats(time_t now) { char *out = NULL, *data = NULL; long duration = now - start_of_bridge_stats_interval; @@ -1149,6 +1209,8 @@ format_bridge_stats_extrainfo(time_t now) if (duration < 0) return NULL; + if (!start_of_bridge_stats_interval) + return NULL; /* Not initialized. */ format_iso_time(written, now); data = geoip_get_client_history(GEOIP_CLIENT_CONNECT); @@ -1198,7 +1260,7 @@ geoip_bridge_stats_write(time_t now) geoip_remove_old_clients(start_of_bridge_stats_interval); /* Generate formatted string */ - val = format_bridge_stats_extrainfo(now); + val = geoip_format_bridge_stats(now); if (val == NULL) goto done; @@ -1209,7 +1271,7 @@ geoip_bridge_stats_write(time_t now) /* Write it to disk. */ statsdir = get_datadir_fname("stats"); - if (check_private_dir(statsdir, CPD_CREATE) < 0) + if (check_private_dir(statsdir, CPD_CREATE, get_options()->User) < 0) goto done; filename = get_datadir_fname2("stats", "bridge-stats"); @@ -1275,25 +1337,54 @@ geoip_entry_stats_init(time_t now) start_of_entry_stats_interval = now; } +/** Reset counters for entry stats. */ +void +geoip_reset_entry_stats(time_t now) +{ + client_history_clear(); + start_of_entry_stats_interval = now; +} + /** Stop collecting entry stats in a way that we can re-start doing so in * geoip_entry_stats_init(). */ void geoip_entry_stats_term(void) { - client_history_clear(); - start_of_entry_stats_interval = 0; + geoip_reset_entry_stats(0); } -/** Write entry statistics to $DATADIR/stats/entry-stats and return time - * when we would next want to write. */ +/** Return a newly allocated string containing the entry statistics + * until <b>now</b>, or NULL if we're not collecting entry stats. Caller + * must ensure start_of_entry_stats_interval lies in the past. */ +char * +geoip_format_entry_stats(time_t now) +{ + char t[ISO_TIME_LEN+1]; + char *data = NULL; + char *result; + + if (!start_of_entry_stats_interval) + return NULL; /* Not initialized. */ + + tor_assert(now >= start_of_entry_stats_interval); + + data = geoip_get_client_history(GEOIP_CLIENT_CONNECT); + format_iso_time(t, now); + tor_asprintf(&result, "entry-stats-end %s (%u s)\nentry-ips %s\n", + t, (unsigned) (now - start_of_entry_stats_interval), + data ? data : ""); + tor_free(data); + return result; +} + +/** If 24 hours have passed since the beginning of the current entry stats + * period, write entry stats to $DATADIR/stats/entry-stats (possibly + * overwriting an existing file) and reset counters. Return when we would + * next want to write entry stats or 0 if we never want to write. */ time_t geoip_entry_stats_write(time_t now) { - char *statsdir = NULL, *filename = NULL; - char *data = NULL; - char written[ISO_TIME_LEN+1]; - open_file_t *open_file = NULL; - FILE *out; + char *statsdir = NULL, *filename = NULL, *str = NULL; if (!start_of_entry_stats_interval) return 0; /* Not initialized. */ @@ -1303,31 +1394,26 @@ geoip_entry_stats_write(time_t now) /* Discard all items in the client history that are too old. */ geoip_remove_old_clients(start_of_entry_stats_interval); + /* Generate history string .*/ + str = geoip_format_entry_stats(now); + + /* Write entry-stats string to disk. */ statsdir = get_datadir_fname("stats"); - if (check_private_dir(statsdir, CPD_CREATE) < 0) + if (check_private_dir(statsdir, CPD_CREATE, get_options()->User) < 0) { + log_warn(LD_HIST, "Unable to create stats/ directory!"); goto done; + } filename = get_datadir_fname2("stats", "entry-stats"); - data = geoip_get_client_history(GEOIP_CLIENT_CONNECT); - format_iso_time(written, now); - out = start_writing_to_stdio_file(filename, OPEN_FLAGS_APPEND, - 0600, &open_file); - if (!out) - goto done; - if (fprintf(out, "entry-stats-end %s (%u s)\nentry-ips %s\n", - written, (unsigned) (now - start_of_entry_stats_interval), - data ? data : "") < 0) - goto done; + if (write_str_to_file(filename, str, 0) < 0) + log_warn(LD_HIST, "Unable to write entry statistics to disk!"); - start_of_entry_stats_interval = now; + /* Reset measurement interval start. */ + geoip_reset_entry_stats(now); - finish_writing_to_file(open_file); - open_file = NULL; done: - if (open_file) - abort_writing_to_file(open_file); - tor_free(filename); tor_free(statsdir); - tor_free(data); + tor_free(filename); + tor_free(str); return start_of_entry_stats_interval + WRITE_STATS_INTERVAL; } |