http.c 44.1 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

J
Junio C Hamano 已提交
12
int active_requests;
13
int http_is_verbose;
14
size_t http_post_buffer = 16 * LARGE_PACKET_MAX;
15

16 17 18 19
#if LIBCURL_VERSION_NUM >= 0x070a06
#define LIBCURL_CAN_HANDLE_AUTH_ANY
#endif

T
Tay Ray Chuan 已提交
20 21
static int min_curl_sessions = 1;
static int curl_session_count;
22
#ifdef USE_CURL_MULTI
M
Mike Hommey 已提交
23 24
static int max_requests = -1;
static CURLM *curlm;
25 26
#endif
#ifndef NO_CURL_EASY_DUPHANDLE
M
Mike Hommey 已提交
27
static CURL *curl_default;
28
#endif
29 30 31 32

#define PREV_BUF_SIZE 4096
#define RANGE_HEADER_SIZE 30

33 34
char curl_errorstr[CURL_ERROR_SIZE];

M
Mike Hommey 已提交
35
static int curl_ssl_verify = -1;
36
static int curl_ssl_try;
J
Junio C Hamano 已提交
37
static const char *ssl_cert;
38
#if LIBCURL_VERSION_NUM >= 0x070903
J
Junio C Hamano 已提交
39
static const char *ssl_key;
40 41
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
J
Junio C Hamano 已提交
42
static const char *ssl_capath;
43
#endif
J
Junio C Hamano 已提交
44
static const char *ssl_cainfo;
M
Mike Hommey 已提交
45 46
static long curl_low_speed_limit = -1;
static long curl_low_speed_time = -1;
J
Junio C Hamano 已提交
47 48
static int curl_ftp_no_epsv;
static const char *curl_http_proxy;
49
static const char *curl_cookie_file;
50
static int curl_save_cookies;
51
struct credential http_auth = CREDENTIAL_INIT;
J
Jeff King 已提交
52
static int http_proactive_auth;
53
static const char *user_agent;
54

55 56 57 58 59 60 61 62
#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

63
static struct credential cert_auth = CREDENTIAL_INIT;
64 65
static int ssl_cert_password_required;

M
Mike Hommey 已提交
66
static struct curl_slist *pragma_header;
67
static struct curl_slist *no_pragma_header;
68

J
Junio C Hamano 已提交
69
static struct active_request_slot *active_queue_head;
70

71 72
static char *cached_accept_language;

73
size_t fread_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
74 75
{
	size_t size = eltsize * nmemb;
76 77
	struct buffer *buffer = buffer_;

M
Mike Hommey 已提交
78 79 80
	if (size > buffer->buf.len - buffer->posn)
		size = buffer->buf.len - buffer->posn;
	memcpy(ptr, buffer->buf.buf + buffer->posn, size);
81
	buffer->posn += size;
M
Mike Hommey 已提交
82

83 84 85
	return size;
}

86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104
#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

105
size_t fwrite_buffer(char *ptr, size_t eltsize, size_t nmemb, void *buffer_)
106 107
{
	size_t size = eltsize * nmemb;
108 109
	struct strbuf *buffer = buffer_;

M
Mike Hommey 已提交
110
	strbuf_add(buffer, ptr, size);
111 112 113
	return size;
}

114
size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf)
115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
{
	return eltsize * nmemb;
}

#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

149
static int http_options(const char *var, const char *value, void *cb)
150 151
{
	if (!strcmp("http.sslverify", var)) {
152
		curl_ssl_verify = git_config_bool(var, value);
153 154
		return 0;
	}
155 156
	if (!strcmp("http.sslcert", var))
		return git_config_string(&ssl_cert, var, value);
157
#if LIBCURL_VERSION_NUM >= 0x070903
158 159
	if (!strcmp("http.sslkey", var))
		return git_config_string(&ssl_key, var, value);
160 161
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
162 163
	if (!strcmp("http.sslcapath", var))
		return git_config_string(&ssl_capath, var, value);
164
#endif
165 166
	if (!strcmp("http.sslcainfo", var))
		return git_config_string(&ssl_cainfo, var, value);
167
	if (!strcmp("http.sslcertpasswordprotected", var)) {
168
		ssl_cert_password_required = git_config_bool(var, value);
169 170
		return 0;
	}
171 172 173 174
	if (!strcmp("http.ssltry", var)) {
		curl_ssl_try = git_config_bool(var, value);
		return 0;
	}
T
Tay Ray Chuan 已提交
175 176 177 178 179 180 181 182
	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
183
#ifdef USE_CURL_MULTI
184
	if (!strcmp("http.maxrequests", var)) {
185
		max_requests = git_config_int(var, value);
186 187 188 189
		return 0;
	}
#endif
	if (!strcmp("http.lowspeedlimit", var)) {
190
		curl_low_speed_limit = (long)git_config_int(var, value);
191 192 193
		return 0;
	}
	if (!strcmp("http.lowspeedtime", var)) {
194
		curl_low_speed_time = (long)git_config_int(var, value);
195 196 197
		return 0;
	}

198 199 200 201
	if (!strcmp("http.noepsv", var)) {
		curl_ftp_no_epsv = git_config_bool(var, value);
		return 0;
	}
202 203
	if (!strcmp("http.proxy", var))
		return git_config_string(&curl_http_proxy, var, value);
204

205 206
	if (!strcmp("http.cookiefile", var))
		return git_config_string(&curl_cookie_file, var, value);
207 208 209 210
	if (!strcmp("http.savecookies", var)) {
		curl_save_cookies = git_config_bool(var, value);
		return 0;
	}
211

212 213 214 215 216 217 218
	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;
	}

219 220 221
	if (!strcmp("http.useragent", var))
		return git_config_string(&user_agent, var, value);

222
	/* Fall back on the default ones */
223
	return git_default_config(var, value, cb);
224 225
}

J
Junio C Hamano 已提交
226 227
static void init_curl_http_auth(CURL *result)
{
228 229 230 231 232 233 234 235 236 237
	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
	{
238
		static struct strbuf up = STRBUF_INIT;
239 240 241 242 243 244 245 246 247
		/*
		 * 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);
248
		curl_easy_setopt(result, CURLOPT_USERPWD, up.buf);
J
Junio C Hamano 已提交
249
	}
250
#endif
J
Junio C Hamano 已提交
251 252
}

253 254 255 256
static int has_cert_password(void)
{
	if (ssl_cert == NULL || ssl_cert_password_required != 1)
		return 0;
257 258
	if (!cert_auth.password) {
		cert_auth.protocol = xstrdup("cert");
259
		cert_auth.username = xstrdup("");
260 261 262 263
		cert_auth.path = xstrdup(ssl_cert);
		credential_fill(&cert_auth);
	}
	return 1;
264 265
}

266 267 268 269 270 271 272
#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
273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
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 */
}

290 291 292 293 294 295 296 297 298 299 300 301
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
302
static CURL *get_curl_handle(void)
303
{
J
Junio C Hamano 已提交
304
	CURL *result = curl_easy_init();
305

306 307 308
	if (!result)
		die("curl_easy_init failed");

309 310 311 312 313 314 315 316 317 318
	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);
	}

319 320 321
#if LIBCURL_VERSION_NUM >= 0x070907
	curl_easy_setopt(result, CURLOPT_NETRC, CURL_NETRC_OPTIONAL);
#endif
322
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
J
Junio C Hamano 已提交
323
	curl_easy_setopt(result, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
324
#endif
325

J
Jeff King 已提交
326 327 328
	if (http_proactive_auth)
		init_curl_http_auth(result);

329 330
	if (ssl_cert != NULL)
		curl_easy_setopt(result, CURLOPT_SSLCERT, ssl_cert);
331
	if (has_cert_password())
332
		curl_easy_setopt(result, CURLOPT_KEYPASSWD, cert_auth.password);
333
#if LIBCURL_VERSION_NUM >= 0x070903
334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351
	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);
352 353 354 355 356
#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
357

358 359 360
	if (getenv("GIT_CURL_VERBOSE"))
		curl_easy_setopt(result, CURLOPT_VERBOSE, 1);

361
	curl_easy_setopt(result, CURLOPT_USERAGENT,
362
		user_agent ? user_agent : git_user_agent());
363

364 365 366
	if (curl_ftp_no_epsv)
		curl_easy_setopt(result, CURLOPT_FTP_USE_EPSV, 0);

367 368 369 370 371
#ifdef CURLOPT_USE_SSL
	if (curl_ssl_try)
		curl_easy_setopt(result, CURLOPT_USE_SSL, CURLUSESSL_TRY);
#endif

372
	if (curl_http_proxy) {
373
		curl_easy_setopt(result, CURLOPT_PROXY, curl_http_proxy);
374 375
		curl_easy_setopt(result, CURLOPT_PROXYAUTH, CURLAUTH_ANY);
	}
376

377
	set_curl_keepalive(result);
E
Eric Wong 已提交
378

379 380 381
	return result;
}

382 383 384 385 386 387 388
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
389
void http_init(struct remote *remote, const char *url, int proactive_auth)
390 391 392
{
	char *low_speed_limit;
	char *low_speed_time;
393 394 395 396 397 398 399 400
	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;
401

402
	http_is_verbose = 0;
403
	normalized_url = url_normalize(url, &config.url);
404

405 406
	git_config(urlmatch_config_entry, &config);
	free(normalized_url);
407

408 409
	if (curl_global_init(CURL_GLOBAL_ALL) != CURLE_OK)
		die("curl_global_init failed");
410

J
Jeff King 已提交
411 412
	http_proactive_auth = proactive_auth;

413 414 415
	if (remote && remote->http_proxy)
		curl_http_proxy = xstrdup(remote->http_proxy);

416
	pragma_header = curl_slist_append(pragma_header, "Pragma: no-cache");
417
	no_pragma_header = curl_slist_append(no_pragma_header, "Pragma:");
418 419 420 421 422 423 424 425 426

#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();
427 428
	if (!curlm)
		die("curl_multi_init failed");
429 430 431 432 433
#endif

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

434
	set_from_env(&ssl_cert, "GIT_SSL_CERT");
435
#if LIBCURL_VERSION_NUM >= 0x070903
436
	set_from_env(&ssl_key, "GIT_SSL_KEY");
437 438
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
439
	set_from_env(&ssl_capath, "GIT_SSL_CAPATH");
440
#endif
441
	set_from_env(&ssl_cainfo, "GIT_SSL_CAINFO");
442

443 444
	set_from_env(&user_agent, "GIT_HTTP_USER_AGENT");

445 446 447 448 449 450 451 452 453 454
	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
455
	curl_session_count = 0;
456 457 458 459 460
#ifdef USE_CURL_MULTI
	if (max_requests < 1)
		max_requests = DEFAULT_MAX_REQUESTS;
#endif

461 462 463
	if (getenv("GIT_CURL_FTP_NO_EPSV"))
		curl_ftp_no_epsv = 1;

464
	if (url) {
465
		credential_from_url(&http_auth, url);
466 467
		if (!ssl_cert_password_required &&
		    getenv("GIT_SSL_CERT_PASSWORD_PROTECTED") &&
468
		    starts_with(url, "https://"))
469 470
			ssl_cert_password_required = 1;
	}
J
Junio C Hamano 已提交
471

472 473 474 475 476 477 478 479 480 481
#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) {
482
		struct active_request_slot *next = slot->next;
483
		if (slot->curl != NULL) {
484
#ifdef USE_CURL_MULTI
485
			curl_multi_remove_handle(curlm, slot->curl);
486 487
#endif
			curl_easy_cleanup(slot->curl);
488
		}
489 490
		free(slot);
		slot = next;
491
	}
492
	active_queue_head = NULL;
493 494 495 496 497 498 499 500 501

#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
502 503

	curl_slist_free_all(pragma_header);
504
	pragma_header = NULL;
505

506 507 508
	curl_slist_free_all(no_pragma_header);
	no_pragma_header = NULL;

509
	if (curl_http_proxy) {
510
		free((void *)curl_http_proxy);
511 512
		curl_http_proxy = NULL;
	}
513

514 515 516 517
	if (cert_auth.password != NULL) {
		memset(cert_auth.password, 0, strlen(cert_auth.password));
		free(cert_auth.password);
		cert_auth.password = NULL;
518 519
	}
	ssl_cert_password_required = 0;
520 521 522

	free(cached_accept_language);
	cached_accept_language = NULL;
523 524 525 526 527 528 529 530 531 532 533 534 535
}

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
536
		if (num_transfers < active_requests)
537 538 539 540
			process_curl_messages();
	}
#endif

J
Junio C Hamano 已提交
541
	while (slot != NULL && slot->in_use)
542
		slot = slot->next;
J
Junio C Hamano 已提交
543

544 545 546 547 548 549 550 551 552 553
	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
554
			while (slot->next != NULL)
555 556 557 558 559 560 561 562 563 564 565 566
				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
567
		curl_session_count++;
568 569 570 571
	}

	active_requests++;
	slot->in_use = 1;
572
	slot->results = NULL;
N
Nick Hengeveld 已提交
573
	slot->finished = NULL;
574 575
	slot->callback_data = NULL;
	slot->callback_func = NULL;
576
	curl_easy_setopt(slot->curl, CURLOPT_COOKIEFILE, curl_cookie_file);
577 578
	if (curl_save_cookies)
		curl_easy_setopt(slot->curl, CURLOPT_COOKIEJAR, curl_cookie_file);
579 580
	curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, pragma_header);
	curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, curl_errorstr);
581 582 583
	curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, NULL);
	curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, NULL);
	curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, NULL);
584
	curl_easy_setopt(slot->curl, CURLOPT_POSTFIELDS, NULL);
585 586
	curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 0);
	curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1);
587
	curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 1);
588 589
	if (http_auth.password)
		init_curl_http_auth(slot->curl);
590 591 592 593 594 595 596 597

	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);
598
	int num_transfers;
599 600 601 602 603 604 605

	if (curlm_result != CURLM_OK &&
	    curlm_result != CURLM_CALL_MULTI_PERFORM) {
		active_requests--;
		slot->in_use = 0;
		return 0;
	}
606 607 608 609 610 611

	/*
	 * We know there must be something to do, since we just added
	 * something.
	 */
	curl_multi_perform(curlm, &num_transfers);
612 613 614 615 616
#endif
	return 1;
}

#ifdef USE_CURL_MULTI
617 618 619 620 621 622
struct fill_chain {
	void *data;
	int (*fill)(void *);
	struct fill_chain *next;
};

J
Junio C Hamano 已提交
623
static struct fill_chain *fill_cfg;
624 625 626

void add_fill_function(void *data, int (*fill)(void *))
{
627
	struct fill_chain *new = xmalloc(sizeof(*new));
628 629 630 631 632 633 634 635 636
	struct fill_chain **linkp = &fill_cfg;
	new->data = data;
	new->fill = fill;
	new->next = NULL;
	while (*linkp)
		linkp = &(*linkp)->next;
	*linkp = new;
}

637 638 639 640
void fill_active_slots(void)
{
	struct active_request_slot *slot = active_queue_head;

641 642 643 644 645 646 647
	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)
648
			break;
649
	}
650 651

	while (slot != NULL) {
T
Tay Ray Chuan 已提交
652 653
		if (!slot->in_use && slot->curl != NULL
			&& curl_session_count > min_curl_sessions) {
654 655
			curl_easy_cleanup(slot->curl);
			slot->curl = NULL;
T
Tay Ray Chuan 已提交
656
			curl_session_count--;
657 658 659 660 661
		}
		slot = slot->next;
	}
}

662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684
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
685
	int finished = 0;
686

N
Nick Hengeveld 已提交
687 688
	slot->finished = &finished;
	while (!finished) {
689 690
		step_active_slots();

691
		if (slot->in_use) {
692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
#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
708

709
			max_fd = -1;
710 711 712
			FD_ZERO(&readfds);
			FD_ZERO(&writefds);
			FD_ZERO(&excfds);
713
			curl_multi_fdset(curlm, &readfds, &writefds, &excfds, &max_fd);
714

715 716 717 718 719 720 721 722 723 724 725 726
			/*
			 * 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;
			}

727
			select(max_fd+1, &readfds, &writefds, &excfds, &select_timeout);
728 729 730 731 732 733 734 735 736 737
		}
	}
#else
	while (slot->in_use) {
		slot->curl_result = curl_easy_perform(slot->curl);
		finish_active_slot(slot);
	}
#endif
}

738
static void closedown_active_slot(struct active_request_slot *slot)
739
{
M
Mike Hommey 已提交
740 741
	active_requests--;
	slot->in_use = 0;
742 743
}

744
static void release_active_slot(struct active_request_slot *slot)
745 746
{
	closedown_active_slot(slot);
T
Tay Ray Chuan 已提交
747
	if (slot->curl && curl_session_count > min_curl_sessions) {
N
Nick Hengeveld 已提交
748
#ifdef USE_CURL_MULTI
749
		curl_multi_remove_handle(curlm, slot->curl);
N
Nick Hengeveld 已提交
750
#endif
751 752
		curl_easy_cleanup(slot->curl);
		slot->curl = NULL;
T
Tay Ray Chuan 已提交
753
		curl_session_count--;
754
	}
N
Nick Hengeveld 已提交
755
#ifdef USE_CURL_MULTI
756
	fill_active_slots();
N
Nick Hengeveld 已提交
757
#endif
758 759
}

760
void finish_active_slot(struct active_request_slot *slot)
761 762
{
	closedown_active_slot(slot);
M
Mike Hommey 已提交
763
	curl_easy_getinfo(slot->curl, CURLINFO_HTTP_CODE, &slot->http_code);
764

N
Nick Hengeveld 已提交
765 766 767
	if (slot->finished != NULL)
		(*slot->finished) = 1;

768 769 770 771
	/* 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;
772 773 774 775 776 777
#if LIBCURL_VERSION_NUM >= 0x070a08
		curl_easy_getinfo(slot->curl, CURLINFO_HTTPAUTH_AVAIL,
				  &slot->results->auth_avail);
#else
		slot->results->auth_avail = 0;
#endif
778 779
	}

M
Mike Hommey 已提交
780
	/* Run callback if appropriate */
J
Junio C Hamano 已提交
781
	if (slot->callback_func != NULL)
M
Mike Hommey 已提交
782
		slot->callback_func(slot->callback_data);
783 784 785 786 787 788 789 790 791 792 793 794 795 796
}

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;
		}
}
797

798
/* Helpers for modifying and creating URLs */
799 800 801 802 803 804 805 806 807 808 809 810 811 812
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)
{
813
	struct strbuf buf = STRBUF_INIT;
814
	const char *cp;
815
	int ch;
816

817
	end_url_with_slash(&buf, base);
818 819

	for (cp = ref; (ch = *cp) != 0; cp++)
820
		if (needs_quote(ch))
821
			strbuf_addf(&buf, "%%%02x", ch);
822
		else
823
			strbuf_addch(&buf, *cp);
824

825
	return strbuf_detach(&buf, NULL);
826 827
}

828 829 830 831
void append_remote_object_url(struct strbuf *buf, const char *url,
			      const char *hex,
			      int only_two_digit_prefix)
{
832 833 834
	end_url_with_slash(buf, url);

	strbuf_addf(buf, "objects/%.*s/", 2, hex);
835 836 837 838 839 840 841 842 843 844 845 846
	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);
}

847
int handle_curl_result(struct slot_results *results)
848
{
J
Jeff King 已提交
849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
	/*
	 * 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);
	}

868 869 870 871 872 873 874 875 876 877 878 879 880
	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 {
			return HTTP_REAUTH;
		}
	} else {
881
#if LIBCURL_VERSION_NUM >= 0x070c00
882 883 884 885
		if (!curl_errorstr[0])
			strlcpy(curl_errorstr,
				curl_easy_strerror(results->curl_result),
				sizeof(curl_errorstr));
886
#endif
887 888 889 890
		return HTTP_ERROR;
	}
}

J
Jeff King 已提交
891 892 893 894 895 896 897 898 899 900 901 902 903 904
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);
}

905 906 907 908 909 910 911 912 913 914 915 916
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;
}

917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
/*
 * 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++;

938
	while (*raw && !isspace(*raw) && *raw != ';')
939 940 941 942
		strbuf_addch(out, *raw++);
	return 0;
}

943 944 945 946 947 948 949 950 951 952
/*
 * 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.
 *
953 954 955
 * If the "charset" argument is not NULL, store the value of any
 * charset parameter there.
 *
956
 * Example:
957
 *   "TEXT/PLAIN; charset=utf-8" -> "text/plain", "utf-8"
958 959
 *   "text / plain" -> "text/plain"
 */
960 961
static void extract_content_type(struct strbuf *raw, struct strbuf *type,
				 struct strbuf *charset)
962 963 964 965 966 967 968 969
{
	const char *p;

	strbuf_reset(type);
	strbuf_grow(type, raw->len);
	for (p = raw->buf; *p; p++) {
		if (isspace(*p))
			continue;
970 971
		if (*p == ';') {
			p++;
972
			break;
973
		}
974 975
		strbuf_addch(type, tolower(*p));
	}
976 977 978 979 980 981

	if (!charset)
		return;

	strbuf_reset(charset);
	while (*p) {
982
		while (isspace(*p) || *p == ';')
983 984 985 986 987 988
			p++;
		if (!extract_param(p, "charset", charset))
			return;
		while (*p && !isspace(*p))
			p++;
	}
989 990 991

	if (!charset->len && starts_with(type->buf, "text/"))
		strbuf_addstr(charset, "ISO-8859-1");
992 993
}

994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 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 1127 1128 1129
/*
 * Guess the user's preferred languages from the value in LANGUAGE environment
 * variable and LC_MESSAGES locale category if NO_GETTEXT is not defined.
 *
 * The result can be a colon-separated list like "ko:ja:en".
 */
static const char *get_preferred_languages(void)
{
	const char *retval;

	retval = getenv("LANGUAGE");
	if (retval && *retval)
		return retval;

#ifndef NO_GETTEXT
	retval = setlocale(LC_MESSAGES, NULL);
	if (retval && *retval &&
		strcmp(retval, "C") &&
		strcmp(retval, "POSIX"))
		return retval;
#endif

	return NULL;
}

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;
}

1130 1131 1132 1133
/* http_request() targets */
#define HTTP_REQUEST_STRBUF	0
#define HTTP_REQUEST_FILE	1

J
Jeff King 已提交
1134 1135 1136
static int http_request(const char *url,
			void *result, int target,
			const struct http_get_options *options)
1137 1138 1139 1140 1141
{
	struct active_request_slot *slot;
	struct slot_results results;
	struct curl_slist *headers = NULL;
	struct strbuf buf = STRBUF_INIT;
1142
	const char *accept_language;
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167
	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);
	}

1168 1169 1170 1171 1172
	accept_language = get_accept_language();

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

1173
	strbuf_addstr(&buf, "Pragma:");
J
Jeff King 已提交
1174
	if (options && options->no_cache)
1175
		strbuf_addstr(&buf, " no-cache");
J
Jeff King 已提交
1176
	if (options && options->keep_error)
J
Jeff King 已提交
1177
		curl_easy_setopt(slot->curl, CURLOPT_FAILONERROR, 0);
1178 1179 1180 1181 1182

	headers = curl_slist_append(headers, buf.buf);

	curl_easy_setopt(slot->curl, CURLOPT_URL, url);
	curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers);
1183
	curl_easy_setopt(slot->curl, CURLOPT_ENCODING, "gzip");
1184

J
Jeff King 已提交
1185
	ret = run_one_slot(slot, &results);
1186

1187 1188 1189
	if (options && options->content_type) {
		struct strbuf raw = STRBUF_INIT;
		curlinfo_strbuf(slot->curl, CURLINFO_CONTENT_TYPE, &raw);
1190 1191
		extract_content_type(&raw, options->content_type,
				     options->charset);
1192 1193
		strbuf_release(&raw);
	}
1194

J
Jeff King 已提交
1195 1196 1197
	if (options && options->effective_url)
		curlinfo_strbuf(slot->curl, CURLINFO_EFFECTIVE_URL,
				options->effective_url);
1198

1199 1200 1201 1202 1203 1204
	curl_slist_free_all(headers);
	strbuf_release(&buf);

	return ret;
}

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 1237 1238 1239
/*
 * 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;

1240
	if (!skip_prefix(asked, base->buf, &tail))
1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254
		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;
}

1255 1256
static int http_request_reauth(const char *url,
			       void *result, int target,
J
Jeff King 已提交
1257
			       struct http_get_options *options)
1258
{
J
Jeff King 已提交
1259
	int ret = http_request(url, result, target, options);
1260 1261 1262 1263 1264 1265 1266 1267 1268

	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;
		}
	}

1269 1270
	if (ret != HTTP_REAUTH)
		return ret;
J
Jeff King 已提交
1271 1272 1273 1274 1275 1276 1277

	/*
	 * 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
1278
	if (options && options->keep_error) {
J
Jeff King 已提交
1279 1280 1281 1282 1283 1284 1285 1286
		switch (target) {
		case HTTP_REQUEST_STRBUF:
			strbuf_reset(result);
			break;
		default:
			die("BUG: HTTP_KEEP_ERROR is only supported with strbufs");
		}
	}
1287 1288 1289

	credential_fill(&http_auth);

J
Jeff King 已提交
1290
	return http_request(url, result, target, options);
1291 1292
}

1293
int http_get_strbuf(const char *url,
J
Jeff King 已提交
1294 1295
		    struct strbuf *result,
		    struct http_get_options *options)
1296
{
J
Jeff King 已提交
1297
	return http_request_reauth(url, result, HTTP_REQUEST_STRBUF, options);
1298 1299
}

1300
/*
J
Jim Meyering 已提交
1301
 * Downloads a URL and stores the result in the given file.
1302 1303 1304 1305
 *
 * 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
1306 1307
static int http_get_file(const char *url, const char *filename,
			 struct http_get_options *options)
1308 1309 1310 1311 1312 1313 1314
{
	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
1315
	if (!result) {
1316 1317 1318 1319 1320
		error("Unable to open local file %s", tmpfile.buf);
		ret = HTTP_ERROR;
		goto cleanup;
	}

J
Jeff King 已提交
1321
	ret = http_request_reauth(url, result, HTTP_REQUEST_FILE, options);
1322 1323
	fclose(result);

J
Jeff King 已提交
1324
	if (ret == HTTP_OK && move_temp_to_file(tmpfile.buf, filename))
1325 1326 1327 1328 1329 1330
		ret = HTTP_ERROR;
cleanup:
	strbuf_release(&tmpfile);
	return ret;
}

1331
int http_fetch_ref(const char *base, struct ref *ref)
1332
{
J
Jeff King 已提交
1333
	struct http_get_options options = {0};
1334 1335
	char *url;
	struct strbuf buffer = STRBUF_INIT;
1336
	int ret = -1;
1337

J
Jeff King 已提交
1338 1339
	options.no_cache = 1;

1340
	url = quote_ref_url(base, ref->name);
J
Jeff King 已提交
1341
	if (http_get_strbuf(url, &buffer, &options) == HTTP_OK) {
1342 1343 1344
		strbuf_rtrim(&buffer);
		if (buffer.len == 40)
			ret = get_sha1_hex(buffer.buf, ref->old_sha1);
1345
		else if (starts_with(buffer.buf, "ref: ")) {
1346 1347
			ref->symref = xstrdup(buffer.buf + 5);
			ret = 0;
1348 1349 1350 1351 1352 1353 1354
		}
	}

	strbuf_release(&buffer);
	free(url);
	return ret;
}
T
Tay Ray Chuan 已提交
1355 1356

/* Helpers for fetching packs */
1357
static char *fetch_pack_index(unsigned char *sha1, const char *base_url)
T
Tay Ray Chuan 已提交
1358
{
1359
	char *url, *tmp;
T
Tay Ray Chuan 已提交
1360 1361 1362
	struct strbuf buf = STRBUF_INIT;

	if (http_is_verbose)
1363
		fprintf(stderr, "Getting index for pack %s\n", sha1_to_hex(sha1));
T
Tay Ray Chuan 已提交
1364 1365

	end_url_with_slash(&buf, base_url);
1366
	strbuf_addf(&buf, "objects/pack/pack-%s.idx", sha1_to_hex(sha1));
T
Tay Ray Chuan 已提交
1367 1368
	url = strbuf_detach(&buf, NULL);

1369 1370 1371
	strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(sha1));
	tmp = strbuf_detach(&buf, NULL);

1372
	if (http_get_file(url, tmp, NULL) != HTTP_OK) {
1373
		error("Unable to get pack index %s", url);
1374 1375 1376
		free(tmp);
		tmp = NULL;
	}
T
Tay Ray Chuan 已提交
1377 1378

	free(url);
1379
	return tmp;
T
Tay Ray Chuan 已提交
1380 1381 1382 1383 1384 1385
}

static int fetch_and_setup_pack_index(struct packed_git **packs_head,
	unsigned char *sha1, const char *base_url)
{
	struct packed_git *new_pack;
1386 1387
	char *tmp_idx = NULL;
	int ret;
T
Tay Ray Chuan 已提交
1388

1389 1390 1391 1392 1393 1394 1395 1396 1397
	if (has_pack_index(sha1)) {
		new_pack = parse_pack_index(sha1, NULL);
		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
1398 1399
		return -1;

1400 1401 1402 1403 1404
	new_pack = parse_pack_index(sha1, tmp_idx);
	if (!new_pack) {
		unlink(tmp_idx);
		free(tmp_idx);

T
Tay Ray Chuan 已提交
1405
		return -1; /* parse_pack_index() already issued error message */
1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
	}

	ret = verify_pack_index(new_pack);
	if (!ret) {
		close_pack_index(new_pack);
		ret = move_temp_to_file(tmp_idx, sha1_pack_index_name(sha1));
	}
	free(tmp_idx);
	if (ret)
		return -1;

add_pack:
T
Tay Ray Chuan 已提交
1418 1419 1420 1421 1422 1423 1424
	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
1425
	struct http_get_options options = {0};
T
Tay Ray Chuan 已提交
1426 1427 1428 1429 1430 1431 1432 1433 1434
	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
1435 1436
	options.no_cache = 1;
	ret = http_get_strbuf(url, &buf, &options);
T
Tay Ray Chuan 已提交
1437 1438 1439 1440 1441 1442 1443 1444 1445
	if (ret != HTTP_OK)
		goto cleanup;

	data = buf.buf;
	while (i < buf.len) {
		switch (data[i]) {
		case 'P':
			i++;
			if (i + 52 <= buf.len &&
1446 1447
			    starts_with(data + i, " pack-") &&
			    starts_with(data + i + 46, ".pack\n")) {
T
Tay Ray Chuan 已提交
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464
				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;
}
1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482

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);
}

int finish_http_pack_request(struct http_pack_request *preq)
{
	struct packed_git **lst;
1483
	struct packed_git *p = preq->target;
1484
	char *tmp_idx;
1485
	struct child_process ip = CHILD_PROCESS_INIT;
1486
	const char *ip_argv[8];
1487

1488
	close_pack_index(p);
1489

1490 1491
	fclose(preq->packfile);
	preq->packfile = NULL;
1492 1493

	lst = preq->lst;
1494
	while (*lst != p)
1495 1496 1497
		lst = &((*lst)->next);
	*lst = (*lst)->next;

1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
	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);
1517
		return -1;
1518 1519 1520
	}

	unlink(sha1_pack_index_name(p->sha1));
1521

1522 1523 1524
	if (move_temp_to_file(preq->tmpfile, sha1_pack_name(p->sha1))
	 || move_temp_to_file(tmp_idx, sha1_pack_index_name(p->sha1))) {
		free(tmp_idx);
1525
		return -1;
1526
	}
1527

1528 1529
	install_packed_git(p);
	free(tmp_idx);
1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540
	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
1541
	preq = xcalloc(1, sizeof(*preq));
1542 1543 1544 1545 1546
	preq->target = target;

	end_url_with_slash(&buf, base_url);
	strbuf_addf(&buf, "objects/pack/pack-%s.pack",
		sha1_to_hex(target->sha1));
1547
	preq->url = strbuf_detach(&buf, NULL);
1548

1549 1550
	snprintf(preq->tmpfile, sizeof(preq->tmpfile), "%s.temp",
		sha1_pack_name(target->sha1));
1551 1552 1553 1554 1555 1556 1557 1558 1559 1560
	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);
1561
	curl_easy_setopt(preq->slot->curl, CURLOPT_URL, preq->url);
1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583
	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:
1584
	free(preq->url);
T
Tay Ray Chuan 已提交
1585
	free(preq);
1586 1587
	return NULL;
}
1588 1589

/* Helpers for fetching objects (loose) */
1590
static size_t fwrite_sha1_file(char *ptr, size_t eltsize, size_t nmemb,
1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606
			       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;
1607
	freq->stream.next_in = (void *)ptr;
1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621
	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);
1622
	const char *filename;
1623 1624
	char prevfile[PATH_MAX];
	int prevlocal;
1625
	char prev_buf[PREV_BUF_SIZE];
1626 1627 1628 1629 1630 1631
	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
1632
	freq = xcalloc(1, sizeof(*freq));
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 1663 1664
	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) {
1665 1666
		error("Couldn't create temporary file %s: %s",
		      freq->tmpfile, strerror(errno));
1667 1668 1669 1670 1671 1672 1673
		goto abort;
	}

	git_inflate_init(&freq->stream);

	git_SHA1_Init(&freq->c);

1674
	freq->url = get_remote_object_url(base_url, hex, 0);
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 1708 1709

	/*
	 * 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);
1710
			if (ftruncate(freq->localfile, 0) < 0) {
1711 1712
				error("Couldn't truncate temporary file %s: %s",
					  freq->tmpfile, strerror(errno));
1713 1714
				goto abort;
			}
1715 1716 1717 1718 1719 1720 1721 1722
		}
	}

	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);
1723
	curl_easy_setopt(freq->slot->curl, CURLOPT_URL, freq->url);
1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743
	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:
1744
	free(freq->url);
1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
	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) {
1768
		warning("requested range invalid; we may already have all the data.");
1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786
	} 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 =
1787
		move_temp_to_file(freq->tmpfile, sha1_file_name(freq->sha1));
1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808

	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;
	}
1809 1810 1811 1812 1813 1814
	if (freq->slot != NULL) {
		freq->slot->callback_func = NULL;
		freq->slot->callback_data = NULL;
		release_active_slot(freq->slot);
		freq->slot = NULL;
	}
1815
}