#define _POSIX_C_SOURCE 200809L #include "deliver.h" #include "module-text.h" #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include enum { TIMEOUT_S = 10, FIRST_PAUSE_MS = 100, LONGEST_PAUSE_MS = 10000, GROUPS = PURE_MODULE_NAME / 2, BATCH_MOST = 256 }; enum { DELIVERED, AGAIN, REFUSED_BY_PEER, TLS_FAILED }; typedef struct { char *body; size_t size; uint64_t seq; } Pending; struct PureWire { const PureModule *module; uint32_t output; char host[256], port[8], path[1024], source[PURE_SOURCE + 1]; pthread_mutex_t lock; pthread_cond_t changed; Pending *queue; /* the sends to deliver, in order, from head */ size_t head, count, capacity; uint64_t queued, delivered, attempts, deliveries; unsigned batch; /* how many a request may carry, as the receiver said (X-Pure-Batch); 0: one */ bool stopping, started, stuck; pthread_t thread; void (*notify)(void *); void *context; int fd; /* the connection kept for the next send, or -1; changed under the lock */ bool tls; /* https: the connection is TLS */ SSL *ssl; /* its TLS session */ }; /* ---- TLS: one client context, verifying the receiver's certificate against * the system's CAs or the file pure_wire_trust named, and its name. */ static pthread_once_t tls_once = PTHREAD_ONCE_INIT; static SSL_CTX *tls_context; static const char *tls_ca; void pure_wire_trust(const char *ca_file) { tls_ca = ca_file; } static void make_tls_context(void) { SSL_CTX *context = SSL_CTX_new(TLS_client_method()); if (!context) return; if (!SSL_CTX_set_min_proto_version(context, TLS1_2_VERSION) || !(tls_ca ? SSL_CTX_load_verify_locations(context, tls_ca, NULL) : SSL_CTX_set_default_verify_paths(context))) { SSL_CTX_free(context); return; } SSL_CTX_set_verify(context, SSL_VERIFY_PEER, NULL); SSL_CTX_set_mode(context, SSL_MODE_AUTO_RETRY); tls_context = context; } /* ---- A send as JSON: its fields in order, a group's fields as an object. */ typedef struct { char *bytes; size_t size, capacity; bool failed; } Text; static void put(Text *t, const void *bytes, size_t size) { if (t->failed) return; if (size > t->capacity - t->size) { size_t capacity = t->capacity ? t->capacity : 256; while (size > capacity - t->size) capacity *= 2; char *grown = realloc(t->bytes, capacity); if (!grown) { t->failed = true; return; } t->bytes = grown; t->capacity = capacity; } memcpy(t->bytes + t->size, bytes, size); t->size += size; } static void put_string(Text *t, const unsigned char *bytes, size_t size) { put(t, "\"", 1); size_t run = 0; for (size_t i = 0; i < size; ++i) { unsigned char b = bytes[i]; if (b != '"' && b != '\\' && b >= 0x20) continue; put(t, bytes + run, i - run); char escaped[8]; if (b == '"' || b == '\\') put(t, (char[]){'\\', (char)b}, 2); else put(t, escaped, (size_t)snprintf(escaped, sizeof(escaped), "\\u%04x", b)); run = i + 1; } put(t, bytes + run, size - run); put(t, "\"", 1); } static uint32_t read_u32(const unsigned char *p) { return p[0] | p[1] << 8 | (uint32_t)p[2] << 16 | (uint32_t)p[3] << 24; } /* The group a field is in: the length of its name before the last dot (0: none). */ static size_t group_of(const char *name) { const char *dot = strrchr(name, '.'); return dot ? (size_t)(dot - name) : 0; } /* Whether the group path open (length open_size) holds the group of name (length size). */ static bool holds(const char *open, size_t open_size, const char *name, size_t size) { return open_size <= size && !memcmp(open, name, open_size) && (open_size == size || !open_size || name[open_size] == '.'); } static bool encode(const PureWire *w, PureSpan payload, Text *t) { const PureModule *m = w->module; const PureInputShape *shape = &m->input[w->output]; if (payload.size < shape->prefix) return false; char open[PURE_MODULE_NAME] = ""; size_t open_size = 0, at = shape->prefix; unsigned depth = 0; bool first[GROUPS + 1] = {true}; put(t, "{", 1); for (uint32_t f = 0; f < shape->field_count; ++f) { const PureField *field = &m->field[shape->field_start + f]; size_t group = group_of(field->name); while (depth && !holds(open, open_size, field->name, group)) { put(t, "}", 1); --depth; open_size = group_of(open) < open_size ? group_of(open) : 0; open[open_size] = 0; } while (open_size < group) { size_t start = open_size ? open_size + 1 : 0, end = start; while (end < group && field->name[end] != '.') ++end; if (!first[depth]) put(t, ",", 1); first[depth] = false; put_string(t, (const unsigned char *)field->name + start, end - start); put(t, ":{", 2); first[++depth] = true; memcpy(open, field->name, end); open[open_size = end] = 0; } if (!first[depth]) put(t, ",", 1); first[depth] = false; const char *key = field->name + (group ? group + 1 : 0); put_string(t, (const unsigned char *)key, strlen(key)); put(t, ":", 1); char digits[32]; if (field->type == PURE_FIELD_U32) { put(t, digits, (size_t)snprintf(digits, sizeof(digits), "%u", (unsigned)read_u32(payload.data + field->offset))); } else if (field->type == PURE_FIELD_NUMBER) { uint64_t bits = read_u32(payload.data + field->offset) | (uint64_t)read_u32(payload.data + field->offset + 4) << 32; double value; memcpy(&value, &bits, sizeof(value)); put(t, digits, pure_format_number(value, digits)); } else { size_t size = field->offset == PURE_FIELD_REST ? payload.size - at : read_u32(payload.data + field->offset); if (size > payload.size - at) return false; PureSpan value = {payload.data + at, size}; if (!pure_utf8_valid(value)) return false; /* bytes that are not text have no JSON form */ put_string(t, value.data, size); at += size; } } while (depth--) put(t, "}", 1); put(t, "}", 1); return !t->failed; } /* ---- The wire. */ PureWire *pure_wire_open(const PureModule *m, const char *output, const char *url, const char *source, char *error, size_t size) { int index = pure_module_input(m, output); if (index < 0 || m->input[index].kind != PURE_KIND_OUTPUT) { snprintf(error, size, "no output '%s'", output); return NULL; } /* A group's fields are together, so each group is one object. */ const PureInputShape *shape = &m->input[index]; for (uint32_t f = 1; f < shape->field_count; ++f) { const char *name = m->field[shape->field_start + f].name; for (uint32_t e = 0; e + 1 < f; ++e) { const char *earlier = m->field[shape->field_start + e].name, *between = m->field[shape->field_start + f - 1].name; size_t shared = 0; while (earlier[shared] && earlier[shared] == name[shared]) ++shared; while (shared && earlier[shared - 1] != '.') --shared; /* the groups both are in */ if (shared && strncmp(between, name, shared)) { snprintf(error, size, "the fields of output '%s' in one group are not together", output); return NULL; } } } size_t length = strlen(source); if (!length || length > PURE_SOURCE) { snprintf(error, size, "a source name has 1 to %d bytes", PURE_SOURCE); return NULL; } bool tls = !strncmp(url, "https://", 8); if (!tls && strncmp(url, "http://", 7)) { snprintf(error, size, "a URL is http[s]://host[:port]/path"); return NULL; } if (tls) { pthread_once(&tls_once, make_tls_context); if (!tls_context) { snprintf(error, size, "no TLS context: %s cannot be read", tls_ca ? tls_ca : "the system's CAs"); return NULL; } } const char *host = url + (tls ? 8 : 7), *slash = strchr(host, '/'), *colon = memchr(host, ':', slash ? (size_t)(slash - host) : strlen(host)); const char *host_end = colon ? colon : slash ? slash : host + strlen(host); const char *port = colon ? colon + 1 : tls ? "443" : "80"; size_t port_size = colon ? (size_t)((slash ? slash : host + strlen(host)) - port) : strlen(port); if (host_end == host || (size_t)(host_end - host) >= 256 || !port_size || port_size >= 8 || (slash && strlen(slash) >= 1024)) { snprintf(error, size, "a URL is http://host[:port]/path"); return NULL; } PureWire *w = calloc(1, sizeof(*w)); if (!w) { snprintf(error, size, "out of memory"); return NULL; } w->module = m; w->output = (uint32_t)index; memcpy(w->host, host, (size_t)(host_end - host)); memcpy(w->port, port, port_size); snprintf(w->path, sizeof(w->path), "%s", slash ? slash : "/"); memcpy(w->source, source, length + 1); w->fd = -1; w->tls = tls; pthread_mutex_init(&w->lock, NULL); pthread_cond_init(&w->changed, NULL); return w; } uint32_t pure_wire_output(const PureWire *w) { return w->output; } uint64_t pure_wire_queued(const PureWire *w) { return w->queued; } uint64_t pure_wire_delivered(PureWire *w) { pthread_mutex_lock(&w->lock); uint64_t delivered = w->delivered; pthread_mutex_unlock(&w->lock); return delivered; } void pure_wire_counts(PureWire *w, uint64_t *delivered, uint64_t *attempts) { pthread_mutex_lock(&w->lock); *delivered = w->deliveries; *attempts = w->attempts; pthread_mutex_unlock(&w->lock); } bool pure_wire_queue(PureWire *w, uint64_t seq, PureSpan payload) { if (w->stuck) return false; Text t = {0}; if (!encode(w, payload, &t)) { free(t.bytes); w->stuck = true; fprintf(stderr, "{\"wire\":\"%s\",\"seq\":%llu,\"error\":\"no JSON form: its bytes are not text\"}\n", w->source, (unsigned long long)seq); return false; } pthread_mutex_lock(&w->lock); if (w->head + w->count == w->capacity) { if (w->head) { memmove(w->queue, w->queue + w->head, w->count * sizeof(*w->queue)); w->head = 0; } else { size_t capacity = w->capacity ? 2 * w->capacity : 16; Pending *grown = realloc(w->queue, capacity * sizeof(*grown)); if (!grown) { pthread_mutex_unlock(&w->lock); free(t.bytes); return false; /* it stays in the outbox: queued after the next save */ } w->queue = grown; w->capacity = capacity; } } w->queue[w->head + w->count++] = (Pending){t.bytes, t.size, seq}; w->queued = seq; pthread_cond_signal(&w->changed); pthread_mutex_unlock(&w->lock); return true; } /* ---- HTTP/1.1, one request at a time on a kept connection. */ typedef struct { PureWire *wire; char bytes[4096]; size_t at, end; } Reader; static bool fill(Reader *r) { if (r->at == r->end) r->at = r->end = 0; if (r->end == sizeof(r->bytes)) return false; PureWire *w = r->wire; ssize_t n; if (w->ssl) n = SSL_read(w->ssl, r->bytes + r->end, (int)(sizeof(r->bytes) - r->end)); else do n = recv(w->fd, r->bytes + r->end, sizeof(r->bytes) - r->end, 0); while (n < 0 && errno == EINTR); if (n <= 0) return false; r->end += (size_t)n; return true; } /* A line without its CRLF, in line (at most size - 1 bytes). */ static bool read_line(Reader *r, char *line, size_t size) { for (;;) { char *end = memchr(r->bytes + r->at, '\n', r->end - r->at); if (end) { size_t length = (size_t)(end - (r->bytes + r->at)); if (length && end[-1] == '\r') --length; if (length >= size) return false; memcpy(line, r->bytes + r->at, length); line[length] = 0; r->at = (size_t)(end - r->bytes) + 1; return true; } if (r->at) { memmove(r->bytes, r->bytes + r->at, r->end - r->at); r->end -= r->at; r->at = 0; } if (!fill(r)) return false; } } static bool skip(Reader *r, uint64_t size) { while (size) { if (r->at == r->end && !fill(r)) return false; size_t n = r->end - r->at < size ? r->end - r->at : (size_t)size; r->at += n; size -= n; } return true; } static bool send_all(PureWire *w, const char *bytes, size_t size) { while (size) { ssize_t n = w->ssl ? SSL_write(w->ssl, bytes, (int)(size < INT32_MAX ? size : INT32_MAX)) : send(w->fd, bytes, size, MSG_NOSIGNAL); if (n < 0 && !w->ssl && errno == EINTR) continue; if (n <= 0) return false; bytes += n; size -= (size_t)n; } return true; } /* TLS over a connected socket: the receiver's certificate must name the host * (a DNS name, or an IP address written as one). */ static SSL *start_tls(const PureWire *w, int fd) { SSL *ssl = SSL_new(tls_context); if (!ssl) return NULL; unsigned char address[16]; bool literal = inet_pton(AF_INET, w->host, address) == 1 || inet_pton(AF_INET6, w->host, address) == 1; bool named = literal ? X509_VERIFY_PARAM_set1_ip_asc(SSL_get0_param(ssl), w->host) == 1 : SSL_set_tlsext_host_name(ssl, w->host) == 1 && SSL_set1_host(ssl, w->host) == 1; if (!named || SSL_set_fd(ssl, fd) != 1 || SSL_connect(ssl) != 1 || SSL_get_verify_result(ssl) != X509_V_OK) { SSL_free(ssl); return NULL; } return ssl; } static int connect_to(const PureWire *w) { struct addrinfo hints = {.ai_family = AF_UNSPEC, .ai_socktype = SOCK_STREAM}, *list; if (getaddrinfo(w->host, w->port, &hints, &list)) return -1; int fd = -1; for (struct addrinfo *a = list; a && fd < 0; a = a->ai_next) { fd = socket(a->ai_family, a->ai_socktype | SOCK_CLOEXEC, a->ai_protocol); if (fd < 0) continue; struct timeval limit = {TIMEOUT_S, 0}; int one = 1; setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &limit, sizeof(limit)); setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &limit, sizeof(limit)); setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, &one, sizeof(one)); if (connect(fd, a->ai_addr, a->ai_addrlen)) { close(fd); fd = -1; } } freeaddrinfo(list); return fd; } static void drop_connection(PureWire *w) { pthread_mutex_lock(&w->lock); if (w->ssl) SSL_free(w->ssl); if (w->fd >= 0) close(w->fd); w->ssl = NULL; w->fd = -1; pthread_mutex_unlock(&w->lock); } /* A fault a Pure receiver answers when its app refused the message. */ static bool refusal(const char *error) { static const char *const faults[] = {"divide", "non_finite", "clamp", "limit", "not_found", "encoding", "exists"}; for (size_t i = 0; i < sizeof(faults) / sizeof(*faults); ++i) if (!strcmp(error, faults[i])) return true; return false; } /* The answer to one request: its status, whether a Pure receiver refused it, * and whether the connection may carry the next. */ static bool read_answer(PureWire *w, int *status, bool *refused, bool *keep, unsigned *batch) { Reader r = {.wire = w}; char line[1024]; if (!read_line(&r, line, sizeof(line)) || strncmp(line, "HTTP/1.", 7) || strlen(line) < 12) return false; *status = atoi(line + 9); *keep = line[7] == '1'; *refused = false; uint64_t length = 0; bool sized = false, chunked = false; while (read_line(&r, line, sizeof(line))) { if (!*line) { if (chunked) { for (;;) { uint64_t chunk; if (!read_line(&r, line, sizeof(line))) return false; chunk = strtoull(line, NULL, 16); if (!chunk) break; if (!skip(&r, chunk) || !read_line(&r, line, sizeof(line))) return false; } while (read_line(&r, line, sizeof(line)) && *line) {} return true; } if (*status == 204 || *status == 304 || *status < 200) return true; if (sized) return skip(&r, length); *keep = false; /* the body runs to the close */ while (fill(&r)) r.at = r.end; return true; } char *value = strchr(line, ':'); if (!value) return false; *value++ = 0; while (*value == ' ' || *value == '\t') ++value; if (!strcasecmp(line, "Content-Length")) { length = strtoull(value, NULL, 10); sized = true; } else if (!strcasecmp(line, "Transfer-Encoding")) chunked = !strcasecmp(value, "chunked"); else if (!strcasecmp(line, "Connection")) *keep = strcasecmp(value, "close") != 0 && *keep; else if (!strcasecmp(line, "X-Pure-Error")) *refused = refusal(value); else if (!strcasecmp(line, "X-Pure-Batch")) *batch = (unsigned)strtoul(value, NULL, 10); } return false; } /* One request for count sends from p (numbered in a row): one object, or * an array of them for a receiver that takes batches. */ static int post(PureWire *w, const Pending *p, unsigned count) { size_t body = count > 1 ? count + 1 : 0; for (unsigned i = 0; i < count; ++i) body += p[i].size; char head[2048], batch[32] = ""; if (count > 1) snprintf(batch, sizeof(batch), "X-Pure-Count: %u\r\n", count); int size = snprintf(head, sizeof(head), "POST %s HTTP/1.1\r\nHost: %s:%s\r\nContent-Type: application/json\r\nContent-Length: %zu\r\n" "X-Pure-Source: %s\r\nX-Pure-Sequence: %llu\r\n%sIdempotency-Key: %s-%llu\r\n\r\n", w->path, w->host, w->port, body, w->source, (unsigned long long)p->seq, batch, w->source, (unsigned long long)p->seq); /* A kept connection the peer closed is tried once more on a new one. */ for (int attempt = 0; attempt < 2; ++attempt) { bool fresh = w->fd < 0; if (fresh) { int fd = connect_to(w); if (fd < 0) return AGAIN; pthread_mutex_lock(&w->lock); w->fd = fd; bool stopping = w->stopping; pthread_mutex_unlock(&w->lock); if (stopping) return AGAIN; SSL *ssl = w->tls ? start_tls(w, fd) : NULL; if (w->tls && !ssl) { drop_connection(w); return TLS_FAILED; } pthread_mutex_lock(&w->lock); w->ssl = ssl; pthread_mutex_unlock(&w->lock); } int status; bool refused, keep, sent = send_all(w, head, (size_t)size); unsigned batch_size = 0; for (unsigned i = 0; sent && i < count; ++i) sent = (!i || count == 1 || send_all(w, ",", 1)) && (i || count == 1 || send_all(w, "[", 1)) && send_all(w, p[i].body, p[i].size); if (sent && count > 1) sent = send_all(w, "]", 1); if (!sent || !read_answer(w, &status, &refused, &keep, &batch_size)) { drop_connection(w); if (fresh) return AGAIN; continue; } if (!keep) drop_connection(w); if (batch_size) w->batch = batch_size; if ((status >= 200 && status < 300) || (status >= 400 && status < 500 && refused)) return DELIVERED; if (status == 408 || status == 429 || status >= 500) return AGAIN; return REFUSED_BY_PEER; } return AGAIN; } static void *deliver(void *context) { PureWire *w = context; long pause_ms = 0; uint64_t reported = 0; pthread_mutex_lock(&w->lock); for (;;) { while (!w->stopping && !w->count) pthread_cond_wait(&w->changed, &w->lock); if (w->stopping) break; /* As many as the receiver takes at once; their bodies stay put while * the queue only grows behind them. */ unsigned count = w->batch > 1 ? (unsigned)(w->count < w->batch ? w->count : w->batch) : 1; Pending next[BATCH_MOST]; if (count > BATCH_MOST) count = BATCH_MOST; memcpy(next, w->queue + w->head, count * sizeof(*next)); ++w->attempts; pthread_mutex_unlock(&w->lock); int outcome = post(w, next, count); pthread_mutex_lock(&w->lock); if (outcome == DELIVERED) { for (unsigned i = 0; i < count; ++i) free(w->queue[w->head + i].body); w->head += count; w->count -= count; w->delivered = next[count - 1].seq; w->deliveries += count; pause_ms = 0; pthread_mutex_unlock(&w->lock); if (w->notify) w->notify(w->context); pthread_mutex_lock(&w->lock); continue; } if ((outcome == REFUSED_BY_PEER || outcome == TLS_FAILED) && reported != next[0].seq) { fprintf(stderr, "{\"wire\":\"%s\",\"seq\":%llu,\"error\":\"%s\"}\n", w->source, (unsigned long long)next[0].seq, outcome == TLS_FAILED ? "the receiver's certificate is not trusted; trying again" : "the receiver does not take it; trying again"); reported = next[0].seq; } pause_ms = outcome != AGAIN ? LONGEST_PAUSE_MS : pause_ms ? 2 * pause_ms : FIRST_PAUSE_MS; if (pause_ms > LONGEST_PAUSE_MS) pause_ms = LONGEST_PAUSE_MS; struct timespec until; clock_gettime(CLOCK_REALTIME, &until); until.tv_sec += pause_ms / 1000; until.tv_nsec += (pause_ms % 1000) * 1000000; if (until.tv_nsec >= 1000000000) { ++until.tv_sec; until.tv_nsec -= 1000000000; } while (!w->stopping && pthread_cond_timedwait(&w->changed, &w->lock, &until) == 0) {} } pthread_mutex_unlock(&w->lock); return NULL; } bool pure_wire_start(PureWire *w, void (*notify)(void *), void *context) { w->notify = notify; w->context = context; w->started = pthread_create(&w->thread, NULL, deliver, w) == 0; return w->started; } void pure_wire_close(PureWire *w) { if (!w) return; pthread_mutex_lock(&w->lock); w->stopping = true; if (w->fd >= 0) shutdown(w->fd, SHUT_RDWR); /* a send or an answer waited for ends now */ pthread_cond_broadcast(&w->changed); pthread_mutex_unlock(&w->lock); if (w->started) pthread_join(w->thread, NULL); if (w->ssl) SSL_free(w->ssl); if (w->fd >= 0) close(w->fd); for (size_t i = 0; i < w->count; ++i) free(w->queue[w->head + i].body); free(w->queue); pthread_cond_destroy(&w->changed); pthread_mutex_destroy(&w->lock); free(w); }