http.c 44.3 KB
Newer Older
1
#include "git-compat-util.h"
2
#include "http.h"
3
#include "pack.h"
4
#include "sideband.h"
5
#include "run-command.h"
6
#include "url.h"
7
#include "urlmatch.h"
8
#include "credential.h"
9
#include "version.h"
10
#include "pkt-line.h"
11
#include "gettext.h"
12

J
Junio C Hamano 已提交
13
int active_requests;
14
int http_is_verbose;
15
size_t http_post_buffer = 16 * LARGE_PACKET_MAX;
16

17 18 19 20
#if LIBCURL_VERSION_NUM >= 0x070a06
#define LIBCURL_CAN_HANDLE_AUTH_ANY
#endif

T
Tay Ray Chuan 已提交
21 22
static int min_curl_sessions = 1;
static int curl_session_count;
23
#ifdef USE_CURL_MULTI
M
Mike Hommey 已提交
24 25
static int max_requests = -1;
static CURLM *curlm;
26 27
#endif
#ifndef NO_CURL_EASY_DUPHANDLE
M
Mike Hommey 已提交
28
static CURL *curl_default;
29
#endif
30 31 32 33

#define PREV_BUF_SIZE 4096
#define RANGE_HEADER_SIZE 30

34 35
char curl_errorstr[CURL_ERROR_SIZE];

M
Mike Hommey 已提交
36
static int curl_ssl_verify = -1;
37
static int curl_ssl_try;
J
Junio C Hamano 已提交
38
static const char *ssl_cert;
39
static const char *ssl_cipherlist;
40
#if LIBCURL_VERSION_NUM >= 0x070903
J
Junio C Hamano 已提交
41
static const char *ssl_key;
42 43
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
J
Junio C Hamano 已提交
44
static const char *ssl_capath;
45
#endif
J
Junio C Hamano 已提交
46
static const char *ssl_cainfo;
M
Mike Hommey 已提交
47 48
static long curl_low_speed_limit = -1;
static long curl_low_speed_time = -1;
J
Junio C Hamano 已提交
49 50
static int curl_ftp_no_epsv;
static const char *curl_http_proxy;
51
static const char *curl_cookie_file;
52
static int curl_save_cookies;
53
struct credential http_auth = CREDENTIAL_INIT;
J
Jeff King 已提交
54
static int http_proactive_auth;
55
static const char *user_agent;
56

57 58 59 60 61 62 63 64
#if LIBCURL_VERSION_NUM >= 0x071700
/* Use CURLOPT_KEYPASSWD as is */
#elif LIBCURL_VERSION_NUM >= 0x070903
#define CURLOPT_KEYPASSWD CURLOPT_SSLKEYPASSWD
#else
#define CURLOPT_KEYPASSWD CURLOPT_SSLCERTPASSWD
#endif

65
static struct credential cert_auth = CREDENTIAL_INIT;
66
static int ssl_cert_password_required;
67 68 69
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
static unsigned long http_auth_methods = CURLAUTH_ANY;
#endif
70

M
Mike Hommey 已提交
71
static struct curl_slist *pragma_header;
72
static struct curl_slist *no_pragma_header;
73

J
Junio C Hamano 已提交
74
static struct active_request_slot *active_queue_head;
75

76 77
static char *cached_accept_language;

78
size_t fread_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
79 80
{
	size_t size = eltsize * nmemb;
81 82
	struct buffer *buffer = buffer_;

M
Mike Hommey 已提交
83 84 85
	if (size > buffer->buf.len - buffer->posn)
		size = buffer->buf.len - buffer->posn;
	memcpy(ptr, buffer->buf.buf + buffer->posn, size);
86
	buffer->posn += size;
M
Mike Hommey 已提交
87

88 89 90
	return size;
}

91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
#ifndef NO_CURL_IOCTL
curlioerr ioctl_buffer(CURL *handle, int cmd, void *clientp)
{
	struct buffer *buffer = clientp;

	switch (cmd) {
	case CURLIOCMD_NOP:
		return CURLIOE_OK;

	case CURLIOCMD_RESTARTREAD:
		buffer->posn = 0;
		return CURLIOE_OK;

	default:
		return CURLIOE_UNKNOWNCMD;
	}
}
#endif

110
size_t fwrite_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
111 112
{
	size_t size = eltsize * nmemb;
113 114
	struct strbuf *buffer = buffer_;

M
Mike Hommey 已提交
115
	strbuf_add(buffer, ptr, size);
116 117 118
	return size;
}

119
size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf)
120 121 122 123
{
	return eltsize * nmemb;
}

124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
static void closedown_active_slot(struct active_request_slot *slot)
{
	active_requests--;
	slot->in_use = 0;
}

static void finish_active_slot(struct active_request_slot *slot)
{
	closedown_active_slot(slot);
	curl_easy_getinfo(slot->curl, CURLINFO_HTTP_CODE, &slot->http_code);

	if (slot->finished != NULL)
		(*slot->finished) = 1;

	/* Store slot results so they can be read after the slot is reused */
	if (slot->results != NULL) {
		slot->results->curl_result = slot->curl_result;
		slot->results->http_code = slot->http_code;
#if LIBCURL_VERSION_NUM >= 0x070a08
		curl_easy_getinfo(slot->curl, CURLINFO_HTTPAUTH_AVAIL,
				  &slot->results->auth_avail);
#else
		slot->results->auth_avail = 0;
#endif
	}

	/* Run callback if appropriate */
	if (slot->callback_func != NULL)
		slot->callback_func(slot->callback_data);
}

155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
#ifdef USE_CURL_MULTI
static void process_curl_messages(void)
{
	int num_messages;
	struct active_request_slot *slot;
	CURLMsg *curl_message = curl_multi_info_read(curlm, &num_messages);

	while (curl_message != NULL) {
		if (curl_message->msg == CURLMSG_DONE) {
			int curl_result = curl_message->data.result;
			slot = active_queue_head;
			while (slot != NULL &&
			       slot->curl != curl_message->easy_handle)
				slot = slot->next;
			if (slot != NULL) {
				curl_multi_remove_handle(curlm, slot->curl);
				slot->curl_result = curl_result;
				finish_active_slot(slot);
			} else {
				fprintf(stderr, "Received DONE message for unknown request!\n");
			}
		} else {
			fprintf(stderr, "Unknown CURL message received: %d\n",
				(int)curl_message->msg);
		}
		curl_message = curl_multi_info_read(curlm, &num_messages);
	}
}
#endif

185
static int http_options(const char *var, const char *value, void *cb)
186 187
{
	if (!strcmp("http.sslverify", var)) {
188
		curl_ssl_verify = git_config_bool(var, value);
189 190
		return 0;
	}
191 192
	if (!strcmp("http.sslcipherlist", var))
		return git_config_string(&ssl_cipherlist, var, value);
193 194
	if (!strcmp("http.sslcert", var))
		return git_config_string(&ssl_cert, var, value);
195
#if LIBCURL_VERSION_NUM >= 0x070903
196 197
	if (!strcmp("http.sslkey", var))
		return git_config_string(&ssl_key, var, value);
198 199
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
200 201
	if (!strcmp("http.sslcapath", var))
		return git_config_string(&ssl_capath, var, value);
202
#endif
203 204
	if (!strcmp("http.sslcainfo", var))
		return git_config_string(&ssl_cainfo, var, value);
205
	if (!strcmp("http.sslcertpasswordprotected", var)) {
206
		ssl_cert_password_required = git_config_bool(var, value);
207 208
		return 0;
	}
209 210 211 212
	if (!strcmp("http.ssltry", var)) {
		curl_ssl_try = git_config_bool(var, value);
		return 0;
	}
T
Tay Ray Chuan 已提交
213 214 215 216 217 218 219 220
	if (!strcmp("http.minsessions", var)) {
		min_curl_sessions = git_config_int(var, value);
#ifndef USE_CURL_MULTI
		if (min_curl_sessions > 1)
			min_curl_sessions = 1;
#endif
		return 0;
	}
J
Junio C Hamano 已提交
221
#ifdef USE_CURL_MULTI
222
	if (!strcmp("http.maxrequests", var)) {
223
		max_requests = git_config_int(var, value);
224 225 226 227
		return 0;
	}
#endif
	if (!strcmp("http.lowspeedlimit", var)) {
228
		curl_low_speed_limit = (long)git_config_int(var, value);
229 230 231
		return 0;
	}
	if (!strcmp("http.lowspeedtime", var)) {
232
		curl_low_speed_time = (long)git_config_int(var, value);
233 234 235
		return 0;
	}

236 237 238 239
	if (!strcmp("http.noepsv", var)) {
		curl_ftp_no_epsv = git_config_bool(var, value);
		return 0;
	}
240 241
	if (!strcmp("http.proxy", var))
		return git_config_string(&curl_http_proxy, var, value);
242

243 244
	if (!strcmp("http.cookiefile", var))
		return git_config_string(&curl_cookie_file, var, value);
245 246 247 248
	if (!strcmp("http.savecookies", var)) {
		curl_save_cookies = git_config_bool(var, value);
		return 0;
	}
249

250 251 252 253 254 255 256
	if (!strcmp("http.postbuffer", var)) {
		http_post_buffer = git_config_int(var, value);
		if (http_post_buffer < LARGE_PACKET_MAX)
			http_post_buffer = LARGE_PACKET_MAX;
		return 0;
	}

257 258 259
	if (!strcmp("http.useragent", var))
		return git_config_string(&user_agent, var, value);

260
	/* Fall back on the default ones */
261
	return git_default_config(var, value, cb);
262 263
}

J
Junio C Hamano 已提交
264 265
static void init_curl_http_auth(CURL *result)
{
266 267 268 269 270 271 272 273 274 275
	if (!http_auth.username)
		return;

	credential_fill(&http_auth);

#if LIBCURL_VERSION_NUM >= 0x071301
	curl_easy_setopt(result, CURLOPT_USERNAME, http_auth.username);
	curl_easy_setopt(result, CURLOPT_PASSWORD, http_auth.password);
#else
	{
276
		static struct strbuf up = STRBUF_INIT;
277 278 279 280 281 282 283 284 285
		/*
		 * Note that we assume we only ever have a single set of
		 * credentials in a given program run, so we do not have
		 * to worry about updating this buffer, only setting its
		 * initial value.
		 */
		if (!up.len)
			strbuf_addf(&up, "%s:%s",
				http_auth.username, http_auth.password);
286
		curl_easy_setopt(result, CURLOPT_USERPWD, up.buf);
J
Junio C Hamano 已提交
287
	}
288
#endif
J
Junio C Hamano 已提交
289 290
}

291 292 293 294
static int has_cert_password(void)
{
	if (ssl_cert == NULL || ssl_cert_password_required != 1)
		return 0;
295 296
	if (!cert_auth.password) {
		cert_auth.protocol = xstrdup("cert");
297
		cert_auth.username = xstrdup("");
298 299 300 301
		cert_auth.path = xstrdup(ssl_cert);
		credential_fill(&cert_auth);
	}
	return 1;
302 303
}

304 305 306 307 308 309 310
#if LIBCURL_VERSION_NUM >= 0x071900
static void set_curl_keepalive(CURL *c)
{
	curl_easy_setopt(c, CURLOPT_TCP_KEEPALIVE, 1);
}

#elif LIBCURL_VERSION_NUM >= 0x071000
E
Eric Wong 已提交
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327
static int sockopt_callback(void *client, curl_socket_t fd, curlsocktype type)
{
	int ka = 1;
	int rc;
	socklen_t len = (socklen_t)sizeof(ka);

	if (type != CURLSOCKTYPE_IPCXN)
		return 0;

	rc = setsockopt(fd, SOL_SOCKET, SO_KEEPALIVE, (void *)&ka, len);
	if (rc < 0)
		warning("unable to set SO_KEEPALIVE on socket %s",
			strerror(errno));

	return 0; /* CURL_SOCKOPT_OK only exists since curl 7.21.5 */
}

328 329 330 331 332 333 334 335 336 337 338 339
static void set_curl_keepalive(CURL *c)
{
	curl_easy_setopt(c, CURLOPT_SOCKOPTFUNCTION, sockopt_callback);
}

#else
static void set_curl_keepalive(CURL *c)
{
	/* not supported on older curl versions */
}
#endif

J
Junio C Hamano 已提交
340
static CURL *get_curl_handle(void)
341
{
J
Junio C Hamano 已提交
342
	CURL *result = curl_easy_init();
343

344 345 346
	if (!result)
		die("curl_easy_init failed");

347 348 349 350 351 352 353 354 355 356
	if (!curl_ssl_verify) {
		curl_easy_setopt(result, CURLOPT_SSL_VERIFYPEER, 0);
		curl_easy_setopt(result, CURLOPT_SSL_VERIFYHOST, 0);
	} else {
		/* Verify authenticity of the peer's certificate */
		curl_easy_setopt(result, CURLOPT_SSL_VERIFYPEER, 1);
		/* The name in the cert must match whom we tried to connect */
		curl_easy_setopt(result, CURLOPT_SSL_VERIFYHOST, 2);
	}

357 358 359
#if LIBCURL_VERSION_NUM >= 0x070907
	curl_easy_setopt(result, CURLOPT_NETRC, CURL_NETRC_OPTIONAL);
#endif
360
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
J
Junio C Hamano 已提交
361
	curl_easy_setopt(result, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
362
#endif
363

J
Jeff King 已提交
364 365 366
	if (http_proactive_auth)
		init_curl_http_auth(result);

367 368 369 370 371 372 373
	if (getenv("GIT_SSL_CIPHER_LIST"))
		ssl_cipherlist = getenv("GIT_SSL_CIPHER_LIST");

	if (ssl_cipherlist != NULL && *ssl_cipherlist)
		curl_easy_setopt(result, CURLOPT_SSL_CIPHER_LIST,
				ssl_cipherlist);

374 375
	if (ssl_cert != NULL)
		curl_easy_setopt(result, CURLOPT_SSLCERT, ssl_cert);
376
	if (has_cert_password())
377
		curl_easy_setopt(result, CURLOPT_KEYPASSWD, cert_auth.password);
378
#if LIBCURL_VERSION_NUM >= 0x070903
379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
	if (ssl_key != NULL)
		curl_easy_setopt(result, CURLOPT_SSLKEY, ssl_key);
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
	if (ssl_capath != NULL)
		curl_easy_setopt(result, CURLOPT_CAPATH, ssl_capath);
#endif
	if (ssl_cainfo != NULL)
		curl_easy_setopt(result, CURLOPT_CAINFO, ssl_cainfo);

	if (curl_low_speed_limit > 0 && curl_low_speed_time > 0) {
		curl_easy_setopt(result, CURLOPT_LOW_SPEED_LIMIT,
				 curl_low_speed_limit);
		curl_easy_setopt(result, CURLOPT_LOW_SPEED_TIME,
				 curl_low_speed_time);
	}

	curl_easy_setopt(result, CURLOPT_FOLLOWLOCATION, 1);
397 398 399 400 401
#if LIBCURL_VERSION_NUM >= 0x071301
	curl_easy_setopt(result, CURLOPT_POSTREDIR, CURL_REDIR_POST_ALL);
#elif LIBCURL_VERSION_NUM >= 0x071101
	curl_easy_setopt(result, CURLOPT_POST301, 1);
#endif
402

403 404 405
	if (getenv("GIT_CURL_VERBOSE"))
		curl_easy_setopt(result, CURLOPT_VERBOSE, 1);

406
	curl_easy_setopt(result, CURLOPT_USERAGENT,
407
		user_agent ? user_agent : git_user_agent());
408

409 410 411
	if (curl_ftp_no_epsv)
		curl_easy_setopt(result, CURLOPT_FTP_USE_EPSV, 0);

412 413 414 415 416
#ifdef CURLOPT_USE_SSL
	if (curl_ssl_try)
		curl_easy_setopt(result, CURLOPT_USE_SSL, CURLUSESSL_TRY);
#endif

417
	if (curl_http_proxy) {
418
		curl_easy_setopt(result, CURLOPT_PROXY, curl_http_proxy);
419
	}
T
Tom G. Christensen 已提交
420
#if LIBCURL_VERSION_NUM >= 0x070a07
421
	curl_easy_setopt(result, CURLOPT_PROXYAUTH, CURLAUTH_ANY);
T
Tom G. Christensen 已提交
422
#endif
423

424
	set_curl_keepalive(result);
E
Eric Wong 已提交
425

426 427 428
	return result;
}

429 430 431 432 433 434 435
static void set_from_env(const char **var, const char *envname)
{
	const char *val = getenv(envname);
	if (val)
		*var = val;
}

J
Jeff King 已提交
436
void http_init(struct remote *remote, const char *url, int proactive_auth)
437 438 439
{
	char *low_speed_limit;
	char *low_speed_time;
440 441 442 443 444 445 446 447
	char *normalized_url;
	struct urlmatch_config config = { STRING_LIST_INIT_DUP };

	config.section = "http";
	config.key = NULL;
	config.collect_fn = http_options;
	config.cascade_fn = git_default_config;
	config.cb = NULL;
448

449
	http_is_verbose = 0;
450
	normalized_url = url_normalize(url, &config.url);
451

452 453
	git_config(urlmatch_config_entry, &config);
	free(normalized_url);
454

455 456
	if (curl_global_init(CURL_GLOBAL_ALL) != CURLE_OK)
		die("curl_global_init failed");
457

J
Jeff King 已提交
458 459
	http_proactive_auth = proactive_auth;

460 461 462
	if (remote && remote->http_proxy)
		curl_http_proxy = xstrdup(remote->http_proxy);

463
	pragma_header = curl_slist_append(pragma_header, "Pragma: no-cache");
464
	no_pragma_header = curl_slist_append(no_pragma_header, "Pragma:");
465 466 467 468 469 470 471 472 473

#ifdef USE_CURL_MULTI
	{
		char *http_max_requests = getenv("GIT_HTTP_MAX_REQUESTS");
		if (http_max_requests != NULL)
			max_requests = atoi(http_max_requests);
	}

	curlm = curl_multi_init();
474 475
	if (!curlm)
		die("curl_multi_init failed");
476 477 478 479 480
#endif

	if (getenv("GIT_SSL_NO_VERIFY"))
		curl_ssl_verify = 0;

481
	set_from_env(&ssl_cert, "GIT_SSL_CERT");
482
#if LIBCURL_VERSION_NUM >= 0x070903
483
	set_from_env(&ssl_key, "GIT_SSL_KEY");
484 485
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
486
	set_from_env(&ssl_capath, "GIT_SSL_CAPATH");
487
#endif
488
	set_from_env(&ssl_cainfo, "GIT_SSL_CAINFO");
489

490 491
	set_from_env(&user_agent, "GIT_HTTP_USER_AGENT");

492 493 494 495 496 497 498 499 500 501
	low_speed_limit = getenv("GIT_HTTP_LOW_SPEED_LIMIT");
	if (low_speed_limit != NULL)
		curl_low_speed_limit = strtol(low_speed_limit, NULL, 10);
	low_speed_time = getenv("GIT_HTTP_LOW_SPEED_TIME");
	if (low_speed_time != NULL)
		curl_low_speed_time = strtol(low_speed_time, NULL, 10);

	if (curl_ssl_verify == -1)
		curl_ssl_verify = 1;

T
Tay Ray Chuan 已提交
502
	curl_session_count = 0;
503 504 505 506 507
#ifdef USE_CURL_MULTI
	if (max_requests < 1)
		max_requests = DEFAULT_MAX_REQUESTS;
#endif

508 509 510
	if (getenv("GIT_CURL_FTP_NO_EPSV"))
		curl_ftp_no_epsv = 1;

511
	if (url) {
512
		credential_from_url(&http_auth, url);
513 514
		if (!ssl_cert_password_required &&
		    getenv("GIT_SSL_CERT_PASSWORD_PROTECTED") &&
515
		    starts_with(url, "https://"))
516 517
			ssl_cert_password_required = 1;
	}
J
Junio C Hamano 已提交
518

519 520 521 522 523 524 525 526 527 528
#ifndef NO_CURL_EASY_DUPHANDLE
	curl_default = get_curl_handle();
#endif
}

void http_cleanup(void)
{
	struct active_request_slot *slot = active_queue_head;

	while (slot != NULL) {
529
		struct active_request_slot *next = slot->next;
530
		if (slot->curl != NULL) {
531
#ifdef USE_CURL_MULTI
532
			curl_multi_remove_handle(curlm, slot->curl);
533 534
#endif
			curl_easy_cleanup(slot->curl);
535
		}
536 537
		free(slot);
		slot = next;
538
	}
539
	active_queue_head = NULL;
540 541 542 543 544 545 546 547 548

#ifndef NO_CURL_EASY_DUPHANDLE
	curl_easy_cleanup(curl_default);
#endif

#ifdef USE_CURL_MULTI
	curl_multi_cleanup(curlm);
#endif
	curl_global_cleanup();
N
Nick Hengeveld 已提交
549 550

	curl_slist_free_all(pragma_header);
551
	pragma_header = NULL;
552

553 554 555
	curl_slist_free_all(no_pragma_header);
	no_pragma_header = NULL;

556
	if (curl_http_proxy) {
557
		free((void *)curl_http_proxy);
558 559
		curl_http_proxy = NULL;
	}
560

561 562 563 564
	if (cert_auth.password != NULL) {
		memset(cert_auth.password, 0, strlen(cert_auth.password));
		free(cert_auth.password);
		cert_auth.password = NULL;
565 566
	}
	ssl_cert_password_required = 0;
567 568 569

	free(cached_accept_language);
	cached_accept_language = NULL;
570 571 572 573 574 575 576 577 578 579 580 581 582
}

struct active_request_slot *get_active_slot(void)
{
	struct active_request_slot *slot = active_queue_head;
	struct active_request_slot *newslot;

#ifdef USE_CURL_MULTI
	int num_transfers;

	/* Wait for a slot to open up if the queue is full */
	while (active_requests >= max_requests) {
		curl_multi_perform(curlm, &num_transfers);
J
Junio C Hamano 已提交
583
		if (num_transfers < active_requests)
584 585 586 587
			process_curl_messages();
	}
#endif

J
Junio C Hamano 已提交
588
	while (slot != NULL && slot->in_use)
589
		slot = slot->next;
J
Junio C Hamano 已提交
590

591 592 593 594 595 596 597 598 599 600
	if (slot == NULL) {
		newslot = xmalloc(sizeof(*newslot));
		newslot->curl = NULL;
		newslot->in_use = 0;
		newslot->next = NULL;

		slot = active_queue_head;
		if (slot == NULL) {
			active_queue_head = newslot;
		} else {
J
Junio C Hamano 已提交
601
			while (slot->next != NULL)
602 603 604 605 606 607 608 609 610 611 612 613
				slot = slot->next;
			slot->next = newslot;
		}
		slot = newslot;
	}

	if (slot->curl == NULL) {
#ifdef NO_CURL_EASY_DUPHANDLE
		slot->curl = get_curl_handle();
#else
		slot->curl = curl_easy_duphandle(curl_default);
#endif
T
Tay Ray Chuan 已提交
614
		curl_session_count++;
615 616 617 618
	}

	active_requests++;
	slot->in_use = 1;
619
	slot->results = NULL;
N
Nick Hengeveld 已提交
620
	slot->finished = NULL;
621 622
	slot->callback_data = NULL;
	slot->callback_func = NULL;
623
	curl_easy_setopt(slot->curl, CURLOPT_COOKIEFILE, curl_cookie_file);
624 625
	if (curl_save_cookies)
		curl_easy_setopt(slot->curl, CURLOPT_COOKIEJAR, curl_cookie_file);
626 627
	curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, pragma_header);
	curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, curl_errorstr);
628 629 630
	curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, NULL);
	curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, NULL);
	curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, NULL);
631
	curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, NULL);
632 633
	curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 0);
	curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1);
634
	curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 1);
635 636 637
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
	curl_easy_setopt(slot->curl, CURLOPT_HTTPAUTH, http_auth_methods);
#endif
638 639
	if (http_auth.password)
		init_curl_http_auth(slot->curl);
640 641 642 643 644 645 646 647

	return slot;
}

int start_active_slot(struct active_request_slot *slot)
{
#ifdef USE_CURL_MULTI
	CURLMcode curlm_result = curl_multi_add_handle(curlm, slot->curl);
648
	int num_transfers;
649 650 651 652 653 654 655

	if (curlm_result != CURLM_OK &&
	    curlm_result != CURLM_CALL_MULTI_PERFORM) {
		active_requests--;
		slot->in_use = 0;
		return 0;
	}
656 657 658 659 660 661

	/*
	 * We know there must be something to do, since we just added
	 * something.
	 */
	curl_multi_perform(curlm, &num_transfers);
662 663 664 665 666
#endif
	return 1;
}

#ifdef USE_CURL_MULTI
667 668 669 670 671 672
struct fill_chain {
	void *data;
	int (*fill)(void *);
	struct fill_chain *next;
};

J
Junio C Hamano 已提交
673
static struct fill_chain *fill_cfg;
674 675 676

void add_fill_function(void *data, int (*fill)(void *))
{
677
	struct fill_chain *new = xmalloc(sizeof(*new));
678 679 680 681 682 683 684 685 686
	struct fill_chain **linkp = &fill_cfg;
	new->data = data;
	new->fill = fill;
	new->next = NULL;
	while (*linkp)
		linkp = &(*linkp)->next;
	*linkp = new;
}

687 688 689 690
void fill_active_slots(void)
{
	struct active_request_slot *slot = active_queue_head;

691 692 693 694 695 696 697
	while (active_requests < max_requests) {
		struct fill_chain *fill;
		for (fill = fill_cfg; fill; fill = fill->next)
			if (fill->fill(fill->data))
				break;

		if (!fill)
698
			break;
699
	}
700 701

	while (slot != NULL) {
T
Tay Ray Chuan 已提交
702 703
		if (!slot->in_use && slot->curl != NULL
			&& curl_session_count > min_curl_sessions) {
704 705
			curl_easy_cleanup(slot->curl);
			slot->curl = NULL;
T
Tay Ray Chuan 已提交
706
			curl_session_count--;
707 708 709 710 711
		}
		slot = slot->next;
	}
}

712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734
void step_active_slots(void)
{
	int num_transfers;
	CURLMcode curlm_result;

	do {
		curlm_result = curl_multi_perform(curlm, &num_transfers);
	} while (curlm_result == CURLM_CALL_MULTI_PERFORM);
	if (num_transfers < active_requests) {
		process_curl_messages();
		fill_active_slots();
	}
}
#endif

void run_active_slot(struct active_request_slot *slot)
{
#ifdef USE_CURL_MULTI
	fd_set readfds;
	fd_set writefds;
	fd_set excfds;
	int max_fd;
	struct timeval select_timeout;
N
Nick Hengeveld 已提交
735
	int finished = 0;
736

N
Nick Hengeveld 已提交
737 738
	slot->finished = &finished;
	while (!finished) {
739 740
		step_active_slots();

741
		if (slot->in_use) {
742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
#if LIBCURL_VERSION_NUM >= 0x070f04
			long curl_timeout;
			curl_multi_timeout(curlm, &curl_timeout);
			if (curl_timeout == 0) {
				continue;
			} else if (curl_timeout == -1) {
				select_timeout.tv_sec  = 0;
				select_timeout.tv_usec = 50000;
			} else {
				select_timeout.tv_sec  =  curl_timeout / 1000;
				select_timeout.tv_usec = (curl_timeout % 1000) * 1000;
			}
#else
			select_timeout.tv_sec  = 0;
			select_timeout.tv_usec = 50000;
#endif
758

759
			max_fd = -1;
760 761 762
			FD_ZERO(&readfds);
			FD_ZERO(&writefds);
			FD_ZERO(&excfds);
763
			curl_multi_fdset(curlm, &readfds, &writefds, &excfds, &max_fd);
764

765 766 767 768 769 770 771 772 773 774 775 776
			/*
			 * It can happen that curl_multi_timeout returns a pathologically
			 * long timeout when curl_multi_fdset returns no file descriptors
			 * to read.  See commit message for more details.
			 */
			if (max_fd < 0 &&
			    (select_timeout.tv_sec > 0 ||
			     select_timeout.tv_usec > 50000)) {
				select_timeout.tv_sec  = 0;
				select_timeout.tv_usec = 50000;
			}

777
			select(max_fd+1, &readfds, &writefds, &excfds, &select_timeout);
778 779 780 781 782 783 784 785 786 787
		}
	}
#else
	while (slot->in_use) {
		slot->curl_result = curl_easy_perform(slot->curl);
		finish_active_slot(slot);
	}
#endif
}

788
static void release_active_slot(struct active_request_slot *slot)
789 790
{
	closedown_active_slot(slot);
T
Tay Ray Chuan 已提交
791
	if (slot->curl && curl_session_count > min_curl_sessions) {
N
Nick Hengeveld 已提交
792
#ifdef USE_CURL_MULTI
793
		curl_multi_remove_handle(curlm, slot->curl);
N
Nick Hengeveld 已提交
794
#endif
795 796
		curl_easy_cleanup(slot->curl);
		slot->curl = NULL;
T
Tay Ray Chuan 已提交
797
		curl_session_count--;
798
	}
N
Nick Hengeveld 已提交
799
#ifdef USE_CURL_MULTI
800
	fill_active_slots();
N
Nick Hengeveld 已提交
801
#endif
802 803
}

804 805 806 807 808 809 810 811 812 813 814 815
void finish_all_active_slots(void)
{
	struct active_request_slot *slot = active_queue_head;

	while (slot != NULL)
		if (slot->in_use) {
			run_active_slot(slot);
			slot = active_queue_head;
		} else {
			slot = slot->next;
		}
}
816

817
/* Helpers for modifying and creating URLs */
818 819 820 821 822 823 824 825 826 827 828 829 830 831
static inline int needs_quote(int ch)
{
	if (((ch >= 'A') && (ch <= 'Z'))
			|| ((ch >= 'a') && (ch <= 'z'))
			|| ((ch >= '0') && (ch <= '9'))
			|| (ch == '/')
			|| (ch == '-')
			|| (ch == '.'))
		return 0;
	return 1;
}

static char *quote_ref_url(const char *base, const char *ref)
{
832
	struct strbuf buf = STRBUF_INIT;
833
	const char *cp;
834
	int ch;
835

836
	end_url_with_slash(&buf, base);
837 838

	for (cp = ref; (ch = *cp) != 0; cp++)
839
		if (needs_quote(ch))
840
			strbuf_addf(&buf, "%%%02x", ch);
841
		else
842
			strbuf_addch(&buf, *cp);
843

844
	return strbuf_detach(&buf, NULL);
845 846
}

847 848 849 850
void append_remote_object_url(struct strbuf *buf, const char *url,
			      const char *hex,
			      int only_two_digit_prefix)
{
851 852 853
	end_url_with_slash(buf, url);

	strbuf_addf(buf, "objects/%.*s/", 2, hex);
854 855 856 857 858 859 860 861 862 863 864 865
	if (!only_two_digit_prefix)
		strbuf_addf(buf, "%s", hex+2);
}

char *get_remote_object_url(const char *url, const char *hex,
			    int only_two_digit_prefix)
{
	struct strbuf buf = STRBUF_INIT;
	append_remote_object_url(&buf, url, hex, only_two_digit_prefix);
	return strbuf_detach(&buf, NULL);
}

866
static int handle_curl_result(struct slot_results *results)
867
{
J
Jeff King 已提交
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
	/*
	 * If we see a failing http code with CURLE_OK, we have turned off
	 * FAILONERROR (to keep the server's custom error response), and should
	 * translate the code into failure here.
	 */
	if (results->curl_result == CURLE_OK &&
	    results->http_code >= 400) {
		results->curl_result = CURLE_HTTP_RETURNED_ERROR;
		/*
		 * Normally curl will already have put the "reason phrase"
		 * from the server into curl_errorstr; unfortunately without
		 * FAILONERROR it is lost, so we can give only the numeric
		 * status code.
		 */
		snprintf(curl_errorstr, sizeof(curl_errorstr),
			 "The requested URL returned error: %ld",
			 results->http_code);
	}

887 888 889 890 891 892 893 894 895 896
	if (results->curl_result == CURLE_OK) {
		credential_approve(&http_auth);
		return HTTP_OK;
	} else if (missing_target(results))
		return HTTP_MISSING_TARGET;
	else if (results->http_code == 401) {
		if (http_auth.username && http_auth.password) {
			credential_reject(&http_auth);
			return HTTP_NOAUTH;
		} else {
897 898 899
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
			http_auth_methods &= ~CURLAUTH_GSSNEGOTIATE;
#endif
900 901 902
			return HTTP_REAUTH;
		}
	} else {
903
#if LIBCURL_VERSION_NUM >= 0x070c00
904 905 906 907
		if (!curl_errorstr[0])
			strlcpy(curl_errorstr,
				curl_easy_strerror(results->curl_result),
				sizeof(curl_errorstr));
908
#endif
909 910 911 912
		return HTTP_ERROR;
	}
}

J
Jeff King 已提交
913 914 915 916 917 918 919 920 921 922 923 924 925 926
int run_one_slot(struct active_request_slot *slot,
		 struct slot_results *results)
{
	slot->results = results;
	if (!start_active_slot(slot)) {
		snprintf(curl_errorstr, sizeof(curl_errorstr),
			 "failed to start HTTP request");
		return HTTP_START_FAILED;
	}

	run_active_slot(slot);
	return handle_curl_result(results);
}

927 928 929 930 931 932 933 934 935 936 937 938
static CURLcode curlinfo_strbuf(CURL *curl, CURLINFO info, struct strbuf *buf)
{
	char *ptr;
	CURLcode ret;

	strbuf_reset(buf);
	ret = curl_easy_getinfo(curl, info, &ptr);
	if (!ret && ptr)
		strbuf_addstr(buf, ptr);
	return ret;
}

939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
/*
 * Check for and extract a content-type parameter. "raw"
 * should be positioned at the start of the potential
 * parameter, with any whitespace already removed.
 *
 * "name" is the name of the parameter. The value is appended
 * to "out".
 */
static int extract_param(const char *raw, const char *name,
			 struct strbuf *out)
{
	size_t len = strlen(name);

	if (strncasecmp(raw, name, len))
		return -1;
	raw += len;

	if (*raw != '=')
		return -1;
	raw++;

960
	while (*raw && !isspace(*raw) && *raw != ';')
961 962 963 964
		strbuf_addch(out, *raw++);
	return 0;
}

965 966 967 968 969 970 971 972 973 974
/*
 * Extract a normalized version of the content type, with any
 * spaces suppressed, all letters lowercased, and no trailing ";"
 * or parameters.
 *
 * Note that we will silently remove even invalid whitespace. For
 * example, "text / plain" is specifically forbidden by RFC 2616,
 * but "text/plain" is the only reasonable output, and this keeps
 * our code simple.
 *
975 976 977
 * If the "charset" argument is not NULL, store the value of any
 * charset parameter there.
 *
978
 * Example:
979
 *   "TEXT/PLAIN; charset=utf-8" -> "text/plain", "utf-8"
980 981
 *   "text / plain" -> "text/plain"
 */
982 983
static void extract_content_type(struct strbuf *raw, struct strbuf *type,
				 struct strbuf *charset)
984 985 986 987 988 989 990 991
{
	const char *p;

	strbuf_reset(type);
	strbuf_grow(type, raw->len);
	for (p = raw->buf; *p; p++) {
		if (isspace(*p))
			continue;
992 993
		if (*p == ';') {
			p++;
994
			break;
995
		}
996 997
		strbuf_addch(type, tolower(*p));
	}
998 999 1000 1001 1002 1003

	if (!charset)
		return;

	strbuf_reset(charset);
	while (*p) {
1004
		while (isspace(*p) || *p == ';')
1005 1006 1007 1008 1009 1010
			p++;
		if (!extract_param(p, "charset", charset))
			return;
		while (*p && !isspace(*p))
			p++;
	}
1011 1012 1013

	if (!charset->len && starts_with(type->buf, "text/"))
		strbuf_addstr(charset, "ISO-8859-1");
1014 1015
}

1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126
static void write_accept_language(struct strbuf *buf)
{
	/*
	 * MAX_DECIMAL_PLACES must not be larger than 3. If it is larger than
	 * that, q-value will be smaller than 0.001, the minimum q-value the
	 * HTTP specification allows. See
	 * http://tools.ietf.org/html/rfc7231#section-5.3.1 for q-value.
	 */
	const int MAX_DECIMAL_PLACES = 3;
	const int MAX_LANGUAGE_TAGS = 1000;
	const int MAX_ACCEPT_LANGUAGE_HEADER_SIZE = 4000;
	char **language_tags = NULL;
	int num_langs = 0;
	const char *s = get_preferred_languages();
	int i;
	struct strbuf tag = STRBUF_INIT;

	/* Don't add Accept-Language header if no language is preferred. */
	if (!s)
		return;

	/*
	 * Split the colon-separated string of preferred languages into
	 * language_tags array.
	 */
	do {
		/* collect language tag */
		for (; *s && (isalnum(*s) || *s == '_'); s++)
			strbuf_addch(&tag, *s == '_' ? '-' : *s);

		/* skip .codeset, @modifier and any other unnecessary parts */
		while (*s && *s != ':')
			s++;

		if (tag.len) {
			num_langs++;
			REALLOC_ARRAY(language_tags, num_langs);
			language_tags[num_langs - 1] = strbuf_detach(&tag, NULL);
			if (num_langs >= MAX_LANGUAGE_TAGS - 1) /* -1 for '*' */
				break;
		}
	} while (*s++);

	/* write Accept-Language header into buf */
	if (num_langs) {
		int last_buf_len = 0;
		int max_q;
		int decimal_places;
		char q_format[32];

		/* add '*' */
		REALLOC_ARRAY(language_tags, num_langs + 1);
		language_tags[num_langs++] = "*"; /* it's OK; this won't be freed */

		/* compute decimal_places */
		for (max_q = 1, decimal_places = 0;
		     max_q < num_langs && decimal_places <= MAX_DECIMAL_PLACES;
		     decimal_places++, max_q *= 10)
			;

		sprintf(q_format, ";q=0.%%0%dd", decimal_places);

		strbuf_addstr(buf, "Accept-Language: ");

		for (i = 0; i < num_langs; i++) {
			if (i > 0)
				strbuf_addstr(buf, ", ");

			strbuf_addstr(buf, language_tags[i]);

			if (i > 0)
				strbuf_addf(buf, q_format, max_q - i);

			if (buf->len > MAX_ACCEPT_LANGUAGE_HEADER_SIZE) {
				strbuf_remove(buf, last_buf_len, buf->len - last_buf_len);
				break;
			}

			last_buf_len = buf->len;
		}
	}

	/* free language tags -- last one is a static '*' */
	for (i = 0; i < num_langs - 1; i++)
		free(language_tags[i]);
	free(language_tags);
}

/*
 * Get an Accept-Language header which indicates user's preferred languages.
 *
 * Examples:
 *   LANGUAGE= -> ""
 *   LANGUAGE=ko:en -> "Accept-Language: ko, en; q=0.9, *; q=0.1"
 *   LANGUAGE=ko_KR.UTF-8:sr@latin -> "Accept-Language: ko-KR, sr; q=0.9, *; q=0.1"
 *   LANGUAGE=ko LANG=en_US.UTF-8 -> "Accept-Language: ko, *; q=0.1"
 *   LANGUAGE= LANG=en_US.UTF-8 -> "Accept-Language: en-US, *; q=0.1"
 *   LANGUAGE= LANG=C -> ""
 */
static const char *get_accept_language(void)
{
	if (!cached_accept_language) {
		struct strbuf buf = STRBUF_INIT;
		write_accept_language(&buf);
		if (buf.len > 0)
			cached_accept_language = strbuf_detach(&buf, NULL);
	}

	return cached_accept_language;
}

1127 1128 1129 1130
/* http_request() targets */
#define HTTP_REQUEST_STRBUF	0
#define HTTP_REQUEST_FILE	1

J
Jeff King 已提交
1131 1132 1133
static int http_request(const char *url,
			void *result, int target,
			const struct http_get_options *options)
1134 1135 1136 1137 1138
{
	struct active_request_slot *slot;
	struct slot_results results;
	struct curl_slist *headers = NULL;
	struct strbuf buf = STRBUF_INIT;
1139
	const char *accept_language;
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
	int ret;

	slot = get_active_slot();
	curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1);

	if (result == NULL) {
		curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 1);
	} else {
		curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 0);
		curl_easy_setopt(slot->curl, CURLOPT_FILE, result);

		if (target == HTTP_REQUEST_FILE) {
			long posn = ftell(result);
			curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION,
					 fwrite);
			if (posn > 0) {
				strbuf_addf(&buf, "Range: bytes=%ld-", posn);
				headers = curl_slist_append(headers, buf.buf);
				strbuf_reset(&buf);
			}
		} else
			curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION,
					 fwrite_buffer);
	}

1165 1166 1167 1168 1169
	accept_language = get_accept_language();

	if (accept_language)
		headers = curl_slist_append(headers, accept_language);

1170
	strbuf_addstr(&buf, "Pragma:");
J
Jeff King 已提交
1171
	if (options && options->no_cache)
1172
		strbuf_addstr(&buf, " no-cache");
J
Jeff King 已提交
1173
	if (options && options->keep_error)
J
Jeff King 已提交
1174
		curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 0);
1175 1176 1177 1178 1179

	headers = curl_slist_append(headers, buf.buf);

	curl_easy_setopt(slot->curl, CURLOPT_URL, url);
	curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers);
1180
	curl_easy_setopt(slot->curl, CURLOPT_ENCODING, "gzip");
1181

J
Jeff King 已提交
1182
	ret = run_one_slot(slot, &results);
1183

1184 1185 1186
	if (options && options->content_type) {
		struct strbuf raw = STRBUF_INIT;
		curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE, &raw);
1187 1188
		extract_content_type(&raw, options->content_type,
				     options->charset);
1189 1190
		strbuf_release(&raw);
	}
1191

J
Jeff King 已提交
1192 1193 1194
	if (options && options->effective_url)
		curlinfo_strbuf(slot->curl, CURLINFO_EFFECTIVE_URL,
				options->effective_url);
1195

1196 1197 1198 1199 1200 1201
	curl_slist_free_all(headers);
	strbuf_release(&buf);

	return ret;
}

1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
/*
 * Update the "base" url to a more appropriate value, as deduced by
 * redirects seen when requesting a URL starting with "url".
 *
 * The "asked" parameter is a URL that we asked curl to access, and must begin
 * with "base".
 *
 * The "got" parameter is the URL that curl reported to us as where we ended
 * up.
 *
 * Returns 1 if we updated the base url, 0 otherwise.
 *
 * Our basic strategy is to compare "base" and "asked" to find the bits
 * specific to our request. We then strip those bits off of "got" to yield the
 * new base. So for example, if our base is "http://example.com/foo.git",
 * and we ask for "http://example.com/foo.git/info/refs", we might end up
 * with "https://other.example.com/foo.git/info/refs". We would want the
 * new URL to become "https://other.example.com/foo.git".
 *
 * Note that this assumes a sane redirect scheme. It's entirely possible
 * in the example above to end up at a URL that does not even end in
 * "info/refs".  In such a case we simply punt, as there is not much we can
 * do (and such a scheme is unlikely to represent a real git repository,
 * which means we are likely about to abort anyway).
 */
static int update_url_from_redirect(struct strbuf *base,
				    const char *asked,
				    const struct strbuf *got)
{
	const char *tail;
	size_t tail_len;

	if (!strcmp(asked, got->buf))
		return 0;

1237
	if (!skip_prefix(asked, base->buf, &tail))
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251
		die("BUG: update_url_from_redirect: %s is not a superset of %s",
		    asked, base->buf);

	tail_len = strlen(tail);

	if (got->len < tail_len ||
	    strcmp(tail, got->buf + got->len - tail_len))
		return 0; /* insane redirect scheme */

	strbuf_reset(base);
	strbuf_add(base, got->buf, got->len - tail_len);
	return 1;
}

1252 1253
static int http_request_reauth(const char *url,
			       void *result, int target,
J
Jeff King 已提交
1254
			       struct http_get_options *options)
1255
{
J
Jeff King 已提交
1256
	int ret = http_request(url, result, target, options);
1257 1258 1259 1260 1261 1262 1263 1264 1265

	if (options && options->effective_url && options->base_url) {
		if (update_url_from_redirect(options->base_url,
					     url, options->effective_url)) {
			credential_from_url(&http_auth, options->base_url->buf);
			url = options->effective_url->buf;
		}
	}

1266 1267
	if (ret != HTTP_REAUTH)
		return ret;
J
Jeff King 已提交
1268 1269 1270 1271 1272 1273 1274

	/*
	 * If we are using KEEP_ERROR, the previous request may have
	 * put cruft into our output stream; we should clear it out before
	 * making our next request. We only know how to do this for
	 * the strbuf case, but that is enough to satisfy current callers.
	 */
J
Jeff King 已提交
1275
	if (options && options->keep_error) {
J
Jeff King 已提交
1276 1277 1278 1279 1280 1281 1282 1283
		switch (target) {
		case HTTP_REQUEST_STRBUF:
			strbuf_reset(result);
			break;
		default:
			die("BUG: HTTP_KEEP_ERROR is only supported with strbufs");
		}
	}
1284 1285 1286

	credential_fill(&http_auth);

J
Jeff King 已提交
1287
	return http_request(url, result, target, options);
1288 1289
}

1290
int http_get_strbuf(const char *url,
J
Jeff King 已提交
1291 1292
		    struct strbuf *result,
		    struct http_get_options *options)
1293
{
J
Jeff King 已提交
1294
	return http_request_reauth(url, result, HTTP_REQUEST_STRBUF, options);
1295 1296
}

1297
/*
J
Jim Meyering 已提交
1298
 * Downloads a URL and stores the result in the given file.
1299 1300 1301 1302
 *
 * If a previous interrupted download is detected (i.e. a previous temporary
 * file is still around) the download is resumed.
 */
J
Jeff King 已提交
1303 1304
static int http_get_file(const char *url, const char *filename,
			 struct http_get_options *options)
1305 1306 1307 1308 1309 1310 1311
{
	int ret;
	struct strbuf tmpfile = STRBUF_INIT;
	FILE *result;

	strbuf_addf(&tmpfile, "%s.temp", filename);
	result = fopen(tmpfile.buf, "a");
J
Jeff King 已提交
1312
	if (!result) {
1313 1314 1315 1316 1317
		error("Unable to open local file %s", tmpfile.buf);
		ret = HTTP_ERROR;
		goto cleanup;
	}

J
Jeff King 已提交
1318
	ret = http_request_reauth(url, result, HTTP_REQUEST_FILE, options);
1319 1320
	fclose(result);

1321
	if (ret == HTTP_OK && finalize_object_file(tmpfile.buf, filename))
1322 1323 1324 1325 1326 1327
		ret = HTTP_ERROR;
cleanup:
	strbuf_release(&tmpfile);
	return ret;
}

1328
int http_fetch_ref(const char *base, struct ref *ref)
1329
{
J
Jeff King 已提交
1330
	struct http_get_options options = {0};
1331 1332
	char *url;
	struct strbuf buffer = STRBUF_INIT;
1333
	int ret = -1;
1334

J
Jeff King 已提交
1335 1336
	options.no_cache = 1;

1337
	url = quote_ref_url(base, ref->name);
J
Jeff King 已提交
1338
	if (http_get_strbuf(url, &buffer, &options) == HTTP_OK) {
1339 1340 1341
		strbuf_rtrim(&buffer);
		if (buffer.len == 40)
			ret = get_sha1_hex(buffer.buf, ref->old_sha1);
1342
		else if (starts_with(buffer.buf, "ref: ")) {
1343 1344
			ref->symref = xstrdup(buffer.buf + 5);
			ret = 0;
1345 1346 1347 1348 1349 1350 1351
		}
	}

	strbuf_release(&buffer);
	free(url);
	return ret;
}
T
Tay Ray Chuan 已提交
1352 1353

/* Helpers for fetching packs */
1354
static char *fetch_pack_index(unsigned char *sha1, const char *base_url)
T
Tay Ray Chuan 已提交
1355
{
1356
	char *url, *tmp;
T
Tay Ray Chuan 已提交
1357 1358 1359
	struct strbuf buf = STRBUF_INIT;

	if (http_is_verbose)
1360
		fprintf(stderr, "Getting index for pack %s\n", sha1_to_hex(sha1));
T
Tay Ray Chuan 已提交
1361 1362

	end_url_with_slash(&buf, base_url);
1363
	strbuf_addf(&buf, "objects/pack/pack-%s.idx", sha1_to_hex(sha1));
T
Tay Ray Chuan 已提交
1364 1365
	url = strbuf_detach(&buf, NULL);

1366 1367 1368
	strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(sha1));
	tmp = strbuf_detach(&buf, NULL);

1369
	if (http_get_file(url, tmp, NULL) != HTTP_OK) {
1370
		error("Unable to get pack index %s", url);
1371 1372 1373
		free(tmp);
		tmp = NULL;
	}
T
Tay Ray Chuan 已提交
1374 1375

	free(url);
1376
	return tmp;
T
Tay Ray Chuan 已提交
1377 1378 1379 1380 1381 1382
}

static int fetch_and_setup_pack_index(struct packed_git **packs_head,
	unsigned char *sha1, const char *base_url)
{
	struct packed_git *new_pack;
1383 1384
	char *tmp_idx = NULL;
	int ret;
T
Tay Ray Chuan 已提交
1385

1386
	if (has_pack_index(sha1)) {
1387
		new_pack = parse_pack_index(sha1, sha1_pack_index_name(sha1));
1388 1389 1390 1391 1392 1393 1394
		if (!new_pack)
			return -1; /* parse_pack_index() already issued error message */
		goto add_pack;
	}

	tmp_idx = fetch_pack_index(sha1, base_url);
	if (!tmp_idx)
T
Tay Ray Chuan 已提交
1395 1396
		return -1;

1397 1398 1399 1400 1401
	new_pack = parse_pack_index(sha1, tmp_idx);
	if (!new_pack) {
		unlink(tmp_idx);
		free(tmp_idx);

T
Tay Ray Chuan 已提交
1402
		return -1; /* parse_pack_index() already issued error message */
1403 1404 1405 1406 1407
	}

	ret = verify_pack_index(new_pack);
	if (!ret) {
		close_pack_index(new_pack);
1408
		ret = finalize_object_file(tmp_idx, sha1_pack_index_name(sha1));
1409 1410 1411 1412 1413 1414
	}
	free(tmp_idx);
	if (ret)
		return -1;

add_pack:
T
Tay Ray Chuan 已提交
1415 1416 1417 1418 1419 1420 1421
	new_pack->next = *packs_head;
	*packs_head = new_pack;
	return 0;
}

int http_get_info_packs(const char *base_url, struct packed_git **packs_head)
{
J
Jeff King 已提交
1422
	struct http_get_options options = {0};
T
Tay Ray Chuan 已提交
1423 1424 1425 1426 1427 1428 1429 1430 1431
	int ret = 0, i = 0;
	char *url, *data;
	struct strbuf buf = STRBUF_INIT;
	unsigned char sha1[20];

	end_url_with_slash(&buf, base_url);
	strbuf_addstr(&buf, "objects/info/packs");
	url = strbuf_detach(&buf, NULL);

J
Jeff King 已提交
1432 1433
	options.no_cache = 1;
	ret = http_get_strbuf(url, &buf, &options);
T
Tay Ray Chuan 已提交
1434 1435 1436 1437 1438 1439 1440 1441 1442
	if (ret != HTTP_OK)
		goto cleanup;

	data = buf.buf;
	while (i < buf.len) {
		switch (data[i]) {
		case 'P':
			i++;
			if (i + 52 <= buf.len &&
1443 1444
			    starts_with(data + i, " pack-") &&
			    starts_with(data + i + 46, ".pack\n")) {
T
Tay Ray Chuan 已提交
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461
				get_sha1_hex(data + i + 6, sha1);
				fetch_and_setup_pack_index(packs_head, sha1,
						      base_url);
				i += 51;
				break;
			}
		default:
			while (i < buf.len && data[i] != '\n')
				i++;
		}
		i++;
	}

cleanup:
	free(url);
	return ret;
}
1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474

void release_http_pack_request(struct http_pack_request *preq)
{
	if (preq->packfile != NULL) {
		fclose(preq->packfile);
		preq->packfile = NULL;
	}
	if (preq->range_header != NULL) {
		curl_slist_free_all(preq->range_header);
		preq->range_header = NULL;
	}
	preq->slot = NULL;
	free(preq->url);
1475
	free(preq);
1476 1477 1478 1479 1480
}

int finish_http_pack_request(struct http_pack_request *preq)
{
	struct packed_git **lst;
1481
	struct packed_git *p = preq->target;
1482
	char *tmp_idx;
1483
	struct child_process ip = CHILD_PROCESS_INIT;
1484
	const char *ip_argv[8];
1485

1486
	close_pack_index(p);
1487

1488 1489
	fclose(preq->packfile);
	preq->packfile = NULL;
1490 1491

	lst = preq->lst;
1492
	while (*lst != p)
1493 1494 1495
		lst = &((*lst)->next);
	*lst = (*lst)->next;

1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514
	tmp_idx = xstrdup(preq->tmpfile);
	strcpy(tmp_idx + strlen(tmp_idx) - strlen(".pack.temp"),
	       ".idx.temp");

	ip_argv[0] = "index-pack";
	ip_argv[1] = "-o";
	ip_argv[2] = tmp_idx;
	ip_argv[3] = preq->tmpfile;
	ip_argv[4] = NULL;

	ip.argv = ip_argv;
	ip.git_cmd = 1;
	ip.no_stdin = 1;
	ip.no_stdout = 1;

	if (run_command(&ip)) {
		unlink(preq->tmpfile);
		unlink(tmp_idx);
		free(tmp_idx);
1515
		return -1;
1516 1517 1518
	}

	unlink(sha1_pack_index_name(p->sha1));
1519

1520 1521
	if (finalize_object_file(preq->tmpfile, sha1_pack_name(p->sha1))
	 || finalize_object_file(tmp_idx, sha1_pack_index_name(p->sha1))) {
1522
		free(tmp_idx);
1523
		return -1;
1524
	}
1525

1526 1527
	install_packed_git(p);
	free(tmp_idx);
1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538
	return 0;
}

struct http_pack_request *new_http_pack_request(
	struct packed_git *target, const char *base_url)
{
	long prev_posn = 0;
	char range[RANGE_HEADER_SIZE];
	struct strbuf buf = STRBUF_INIT;
	struct http_pack_request *preq;

T
Tay Ray Chuan 已提交
1539
	preq = xcalloc(1, sizeof(*preq));
1540 1541 1542 1543 1544
	preq->target = target;

	end_url_with_slash(&buf, base_url);
	strbuf_addf(&buf, "objects/pack/pack-%s.pack",
		sha1_to_hex(target->sha1));
1545
	preq->url = strbuf_detach(&buf, NULL);
1546

1547 1548
	snprintf(preq->tmpfile, sizeof(preq->tmpfile), "%s.temp",
		sha1_pack_name(target->sha1));
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558
	preq->packfile = fopen(preq->tmpfile, "a");
	if (!preq->packfile) {
		error("Unable to open local file %s for pack",
		      preq->tmpfile);
		goto abort;
	}

	preq->slot = get_active_slot();
	curl_easy_setopt(preq->slot->curl, CURLOPT_FILE, preq->packfile);
	curl_easy_setopt(preq->slot->curl, CURLOPT_WRITEFUNCTION, fwrite);
1559
	curl_easy_setopt(preq->slot->curl, CURLOPT_URL, preq->url);
1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581
	curl_easy_setopt(preq->slot->curl, CURLOPT_HTTPHEADER,
		no_pragma_header);

	/*
	 * If there is data present from a previous transfer attempt,
	 * resume where it left off
	 */
	prev_posn = ftell(preq->packfile);
	if (prev_posn>0) {
		if (http_is_verbose)
			fprintf(stderr,
				"Resuming fetch of pack %s at byte %ld\n",
				sha1_to_hex(target->sha1), prev_posn);
		sprintf(range, "Range: bytes=%ld-", prev_posn);
		preq->range_header = curl_slist_append(NULL, range);
		curl_easy_setopt(preq->slot->curl, CURLOPT_HTTPHEADER,
			preq->range_header);
	}

	return preq;

abort:
1582
	free(preq->url);
T
Tay Ray Chuan 已提交
1583
	free(preq);
1584 1585
	return NULL;
}
1586 1587

/* Helpers for fetching objects (loose) */
1588
static size_t fwrite_sha1_file(char *ptr, size_t eltsize, size_t nmemb,
1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604
			       void *data)
{
	unsigned char expn[4096];
	size_t size = eltsize * nmemb;
	int posn = 0;
	struct http_object_request *freq =
		(struct http_object_request *)data;
	do {
		ssize_t retval = xwrite(freq->localfile,
					(char *) ptr + posn, size - posn);
		if (retval < 0)
			return posn;
		posn += retval;
	} while (posn < size);

	freq->stream.avail_in = size;
1605
	freq->stream.next_in = (void *)ptr;
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619
	do {
		freq->stream.next_out = expn;
		freq->stream.avail_out = sizeof(expn);
		freq->zret = git_inflate(&freq->stream, Z_SYNC_FLUSH);
		git_SHA1_Update(&freq->c, expn,
				sizeof(expn) - freq->stream.avail_out);
	} while (freq->stream.avail_in && freq->zret == Z_OK);
	return size;
}

struct http_object_request *new_http_object_request(const char *base_url,
	unsigned char *sha1)
{
	char *hex = sha1_to_hex(sha1);
1620
	const char *filename;
1621 1622
	char prevfile[PATH_MAX];
	int prevlocal;
1623
	char prev_buf[PREV_BUF_SIZE];
1624 1625 1626 1627 1628 1629
	ssize_t prev_read = 0;
	long prev_posn = 0;
	char range[RANGE_HEADER_SIZE];
	struct curl_slist *range_header = NULL;
	struct http_object_request *freq;

T
Tay Ray Chuan 已提交
1630
	freq = xcalloc(1, sizeof(*freq));
1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662
	hashcpy(freq->sha1, sha1);
	freq->localfile = -1;

	filename = sha1_file_name(sha1);
	snprintf(freq->tmpfile, sizeof(freq->tmpfile),
		 "%s.temp", filename);

	snprintf(prevfile, sizeof(prevfile), "%s.prev", filename);
	unlink_or_warn(prevfile);
	rename(freq->tmpfile, prevfile);
	unlink_or_warn(freq->tmpfile);

	if (freq->localfile != -1)
		error("fd leakage in start: %d", freq->localfile);
	freq->localfile = open(freq->tmpfile,
			       O_WRONLY | O_CREAT | O_EXCL, 0666);
	/*
	 * This could have failed due to the "lazy directory creation";
	 * try to mkdir the last path component.
	 */
	if (freq->localfile < 0 && errno == ENOENT) {
		char *dir = strrchr(freq->tmpfile, '/');
		if (dir) {
			*dir = 0;
			mkdir(freq->tmpfile, 0777);
			*dir = '/';
		}
		freq->localfile = open(freq->tmpfile,
				       O_WRONLY | O_CREAT | O_EXCL, 0666);
	}

	if (freq->localfile < 0) {
1663 1664
		error("Couldn't create temporary file %s: %s",
		      freq->tmpfile, strerror(errno));
1665 1666 1667 1668 1669 1670 1671
		goto abort;
	}

	git_inflate_init(&freq->stream);

	git_SHA1_Init(&freq->c);

1672
	freq->url = get_remote_object_url(base_url, hex, 0);
1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707

	/*
	 * If a previous temp file is present, process what was already
	 * fetched.
	 */
	prevlocal = open(prevfile, O_RDONLY);
	if (prevlocal != -1) {
		do {
			prev_read = xread(prevlocal, prev_buf, PREV_BUF_SIZE);
			if (prev_read>0) {
				if (fwrite_sha1_file(prev_buf,
						     1,
						     prev_read,
						     freq) == prev_read) {
					prev_posn += prev_read;
				} else {
					prev_read = -1;
				}
			}
		} while (prev_read > 0);
		close(prevlocal);
	}
	unlink_or_warn(prevfile);

	/*
	 * Reset inflate/SHA1 if there was an error reading the previous temp
	 * file; also rewind to the beginning of the local file.
	 */
	if (prev_read == -1) {
		memset(&freq->stream, 0, sizeof(freq->stream));
		git_inflate_init(&freq->stream);
		git_SHA1_Init(&freq->c);
		if (prev_posn>0) {
			prev_posn = 0;
			lseek(freq->localfile, 0, SEEK_SET);
1708
			if (ftruncate(freq->localfile, 0) < 0) {
1709 1710
				error("Couldn't truncate temporary file %s: %s",
					  freq->tmpfile, strerror(errno));
1711 1712
				goto abort;
			}
1713 1714 1715 1716 1717 1718 1719 1720
		}
	}

	freq->slot = get_active_slot();

	curl_easy_setopt(freq->slot->curl, CURLOPT_FILE, freq);
	curl_easy_setopt(freq->slot->curl, CURLOPT_WRITEFUNCTION, fwrite_sha1_file);
	curl_easy_setopt(freq->slot->curl, CURLOPT_ERRORBUFFER, freq->errorstr);
1721
	curl_easy_setopt(freq->slot->curl, CURLOPT_URL, freq->url);
1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
	curl_easy_setopt(freq->slot->curl, CURLOPT_HTTPHEADER, no_pragma_header);

	/*
	 * If we have successfully processed data from a previous fetch
	 * attempt, only fetch the data we don't already have.
	 */
	if (prev_posn>0) {
		if (http_is_verbose)
			fprintf(stderr,
				"Resuming fetch of object %s at byte %ld\n",
				hex, prev_posn);
		sprintf(range, "Range: bytes=%ld-", prev_posn);
		range_header = curl_slist_append(range_header, range);
		curl_easy_setopt(freq->slot->curl,
				 CURLOPT_HTTPHEADER, range_header);
	}

	return freq;

abort:
1742
	free(freq->url);
1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765
	free(freq);
	return NULL;
}

void process_http_object_request(struct http_object_request *freq)
{
	if (freq->slot == NULL)
		return;
	freq->curl_result = freq->slot->curl_result;
	freq->http_code = freq->slot->http_code;
	freq->slot = NULL;
}

int finish_http_object_request(struct http_object_request *freq)
{
	struct stat st;

	close(freq->localfile);
	freq->localfile = -1;

	process_http_object_request(freq);

	if (freq->http_code == 416) {
1766
		warning("requested range invalid; we may already have all the data.");
1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784
	} else if (freq->curl_result != CURLE_OK) {
		if (stat(freq->tmpfile, &st) == 0)
			if (st.st_size == 0)
				unlink_or_warn(freq->tmpfile);
		return -1;
	}

	git_inflate_end(&freq->stream);
	git_SHA1_Final(freq->real_sha1, &freq->c);
	if (freq->zret != Z_STREAM_END) {
		unlink_or_warn(freq->tmpfile);
		return -1;
	}
	if (hashcmp(freq->sha1, freq->real_sha1)) {
		unlink_or_warn(freq->tmpfile);
		return -1;
	}
	freq->rename =
1785
		finalize_object_file(freq->tmpfile, sha1_file_name(freq->sha1));
1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806

	return freq->rename;
}

void abort_http_object_request(struct http_object_request *freq)
{
	unlink_or_warn(freq->tmpfile);

	release_http_object_request(freq);
}

void release_http_object_request(struct http_object_request *freq)
{
	if (freq->localfile != -1) {
		close(freq->localfile);
		freq->localfile = -1;
	}
	if (freq->url != NULL) {
		free(freq->url);
		freq->url = NULL;
	}
1807 1808 1809 1810 1811 1812
	if (freq->slot != NULL) {
		freq->slot->callback_func = NULL;
		freq->slot->callback_data = NULL;
		release_active_slot(freq->slot);
		freq->slot = NULL;
	}
1813
}