git/http.c
Shawn O. Pearce fe72d420ab http-fetch: Use index-pack rather than verify-pack to check packs
To ensure we don't leave a corrupt pack file positioned as though
it were a valid pack file, run index-pack on the temporary pack
before we rename it to its final name.  If index-pack crashes out
when it discovers file corruption (e.g. GitHub's error HTML at the
end of the file), simply delete the temporary files to cleanup.

By waiting until the pack has been validated before we move it
to its final name, we eliminate a race condition where another
concurrent reader might try to access the pack at the same time
that we are still trying to verify its not corrupt.

Switching from verify-pack to index-pack is a change in behavior,
but it should turn out better for users.  The index-pack algorithm
tries to minimize disk seeks, as well as the number of times any
given object is inflated, by organizing its work along delta chains.
The verify-pack logic does not attempt to do this, thrashing the
delta base cache and the filesystem cache.

By recreating the index file locally, we also can automatically
upgrade from a v1 pack table of contents to v2.  This makes the
CRC32 data available for use during later repacks, even if the
server didn't have them on hand.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Acked-by: Tay Ray Chuan <rctay89@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2010-04-19 17:56:20 -07:00

1345 lines
31 KiB
C

#include "http.h"
#include "pack.h"
#include "sideband.h"
#include "run-command.h"
int data_received;
int active_requests;
int http_is_verbose;
size_t http_post_buffer = 16 * LARGE_PACKET_MAX;
#if LIBCURL_VERSION_NUM >= 0x070a06
#define LIBCURL_CAN_HANDLE_AUTH_ANY
#endif
static int min_curl_sessions = 1;
static int curl_session_count;
#ifdef USE_CURL_MULTI
static int max_requests = -1;
static CURLM *curlm;
#endif
#ifndef NO_CURL_EASY_DUPHANDLE
static CURL *curl_default;
#endif
#define PREV_BUF_SIZE 4096
#define RANGE_HEADER_SIZE 30
char curl_errorstr[CURL_ERROR_SIZE];
static int curl_ssl_verify = -1;
static const char *ssl_cert;
#if LIBCURL_VERSION_NUM >= 0x070903
static const char *ssl_key;
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
static const char *ssl_capath;
#endif
static const char *ssl_cainfo;
static long curl_low_speed_limit = -1;
static long curl_low_speed_time = -1;
static int curl_ftp_no_epsv;
static const char *curl_http_proxy;
static char *user_name, *user_pass;
#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
static char *ssl_cert_password;
static int ssl_cert_password_required;
static struct curl_slist *pragma_header;
static struct curl_slist *no_pragma_header;
static struct active_request_slot *active_queue_head;
size_t fread_buffer(void *ptr, size_t eltsize, size_t nmemb, void *buffer_)
{
size_t size = eltsize * nmemb;
struct buffer *buffer = buffer_;
if (size > buffer->buf.len - buffer->posn)
size = buffer->buf.len - buffer->posn;
memcpy(ptr, buffer->buf.buf + buffer->posn, size);
buffer->posn += size;
return size;
}
#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
size_t fwrite_buffer(const void *ptr, size_t eltsize, size_t nmemb, void *buffer_)
{
size_t size = eltsize * nmemb;
struct strbuf *buffer = buffer_;
strbuf_add(buffer, ptr, size);
data_received++;
return size;
}
size_t fwrite_null(const void *ptr, size_t eltsize, size_t nmemb, void *strbuf)
{
data_received++;
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
static int http_options(const char *var, const char *value, void *cb)
{
if (!strcmp("http.sslverify", var)) {
curl_ssl_verify = git_config_bool(var, value);
return 0;
}
if (!strcmp("http.sslcert", var))
return git_config_string(&ssl_cert, var, value);
#if LIBCURL_VERSION_NUM >= 0x070903
if (!strcmp("http.sslkey", var))
return git_config_string(&ssl_key, var, value);
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
if (!strcmp("http.sslcapath", var))
return git_config_string(&ssl_capath, var, value);
#endif
if (!strcmp("http.sslcainfo", var))
return git_config_string(&ssl_cainfo, var, value);
if (!strcmp("http.sslcertpasswordprotected", var)) {
if (git_config_bool(var, value))
ssl_cert_password_required = 1;
return 0;
}
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;
}
#ifdef USE_CURL_MULTI
if (!strcmp("http.maxrequests", var)) {
max_requests = git_config_int(var, value);
return 0;
}
#endif
if (!strcmp("http.lowspeedlimit", var)) {
curl_low_speed_limit = (long)git_config_int(var, value);
return 0;
}
if (!strcmp("http.lowspeedtime", var)) {
curl_low_speed_time = (long)git_config_int(var, value);
return 0;
}
if (!strcmp("http.noepsv", var)) {
curl_ftp_no_epsv = git_config_bool(var, value);
return 0;
}
if (!strcmp("http.proxy", var))
return git_config_string(&curl_http_proxy, var, value);
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;
}
/* Fall back on the default ones */
return git_default_config(var, value, cb);
}
static void init_curl_http_auth(CURL *result)
{
if (user_name) {
struct strbuf up = STRBUF_INIT;
if (!user_pass)
user_pass = xstrdup(getpass("Password: "));
strbuf_addf(&up, "%s:%s", user_name, user_pass);
curl_easy_setopt(result, CURLOPT_USERPWD,
strbuf_detach(&up, NULL));
}
}
static int has_cert_password(void)
{
if (ssl_cert_password != NULL)
return 1;
if (ssl_cert == NULL || ssl_cert_password_required != 1)
return 0;
/* Only prompt the user once. */
ssl_cert_password_required = -1;
ssl_cert_password = getpass("Certificate Password: ");
if (ssl_cert_password != NULL) {
ssl_cert_password = xstrdup(ssl_cert_password);
return 1;
} else
return 0;
}
static CURL *get_curl_handle(void)
{
CURL *result = curl_easy_init();
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);
}
#if LIBCURL_VERSION_NUM >= 0x070907
curl_easy_setopt(result, CURLOPT_NETRC, CURL_NETRC_OPTIONAL);
#endif
#ifdef LIBCURL_CAN_HANDLE_AUTH_ANY
curl_easy_setopt(result, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
#endif
init_curl_http_auth(result);
if (ssl_cert != NULL)
curl_easy_setopt(result, CURLOPT_SSLCERT, ssl_cert);
if (has_cert_password())
curl_easy_setopt(result, CURLOPT_KEYPASSWD, ssl_cert_password);
#if LIBCURL_VERSION_NUM >= 0x070903
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);
curl_easy_setopt(result, CURLOPT_FAILONERROR, 1);
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);
if (getenv("GIT_CURL_VERBOSE"))
curl_easy_setopt(result, CURLOPT_VERBOSE, 1);
curl_easy_setopt(result, CURLOPT_USERAGENT, GIT_USER_AGENT);
if (curl_ftp_no_epsv)
curl_easy_setopt(result, CURLOPT_FTP_USE_EPSV, 0);
if (curl_http_proxy)
curl_easy_setopt(result, CURLOPT_PROXY, curl_http_proxy);
return result;
}
static void http_auth_init(const char *url)
{
char *at, *colon, *cp, *slash;
int len;
cp = strstr(url, "://");
if (!cp)
return;
/*
* Ok, the URL looks like "proto://something". Which one?
* "proto://<user>:<pass>@<host>/...",
* "proto://<user>@<host>/...", or just
* "proto://<host>/..."?
*/
cp += 3;
at = strchr(cp, '@');
colon = strchr(cp, ':');
slash = strchrnul(cp, '/');
if (!at || slash <= at)
return; /* No credentials */
if (!colon || at <= colon) {
/* Only username */
len = at - cp;
user_name = xmalloc(len + 1);
memcpy(user_name, cp, len);
user_name[len] = '\0';
user_pass = NULL;
} else {
len = colon - cp;
user_name = xmalloc(len + 1);
memcpy(user_name, cp, len);
user_name[len] = '\0';
len = at - (colon + 1);
user_pass = xmalloc(len + 1);
memcpy(user_pass, colon + 1, len);
user_pass[len] = '\0';
}
}
static void set_from_env(const char **var, const char *envname)
{
const char *val = getenv(envname);
if (val)
*var = val;
}
void http_init(struct remote *remote)
{
char *low_speed_limit;
char *low_speed_time;
http_is_verbose = 0;
git_config(http_options, NULL);
curl_global_init(CURL_GLOBAL_ALL);
if (remote && remote->http_proxy)
curl_http_proxy = xstrdup(remote->http_proxy);
pragma_header = curl_slist_append(pragma_header, "Pragma: no-cache");
no_pragma_header = curl_slist_append(no_pragma_header, "Pragma:");
#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();
if (curlm == NULL) {
fprintf(stderr, "Error creating curl multi handle.\n");
exit(1);
}
#endif
if (getenv("GIT_SSL_NO_VERIFY"))
curl_ssl_verify = 0;
set_from_env(&ssl_cert, "GIT_SSL_CERT");
#if LIBCURL_VERSION_NUM >= 0x070903
set_from_env(&ssl_key, "GIT_SSL_KEY");
#endif
#if LIBCURL_VERSION_NUM >= 0x070908
set_from_env(&ssl_capath, "GIT_SSL_CAPATH");
#endif
set_from_env(&ssl_cainfo, "GIT_SSL_CAINFO");
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;
curl_session_count = 0;
#ifdef USE_CURL_MULTI
if (max_requests < 1)
max_requests = DEFAULT_MAX_REQUESTS;
#endif
if (getenv("GIT_CURL_FTP_NO_EPSV"))
curl_ftp_no_epsv = 1;
if (remote && remote->url && remote->url[0]) {
http_auth_init(remote->url[0]);
if (!ssl_cert_password_required &&
getenv("GIT_SSL_CERT_PASSWORD_PROTECTED") &&
!prefixcmp(remote->url[0], "https://"))
ssl_cert_password_required = 1;
}
#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) {
struct active_request_slot *next = slot->next;
if (slot->curl != NULL) {
#ifdef USE_CURL_MULTI
curl_multi_remove_handle(curlm, slot->curl);
#endif
curl_easy_cleanup(slot->curl);
}
free(slot);
slot = next;
}
active_queue_head = NULL;
#ifndef NO_CURL_EASY_DUPHANDLE
curl_easy_cleanup(curl_default);
#endif
#ifdef USE_CURL_MULTI
curl_multi_cleanup(curlm);
#endif
curl_global_cleanup();
curl_slist_free_all(pragma_header);
pragma_header = NULL;
curl_slist_free_all(no_pragma_header);
no_pragma_header = NULL;
if (curl_http_proxy) {
free((void *)curl_http_proxy);
curl_http_proxy = NULL;
}
if (ssl_cert_password != NULL) {
memset(ssl_cert_password, 0, strlen(ssl_cert_password));
free(ssl_cert_password);
ssl_cert_password = NULL;
}
ssl_cert_password_required = 0;
}
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);
if (num_transfers < active_requests)
process_curl_messages();
}
#endif
while (slot != NULL && slot->in_use)
slot = slot->next;
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 {
while (slot->next != NULL)
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
curl_session_count++;
}
active_requests++;
slot->in_use = 1;
slot->local = NULL;
slot->results = NULL;
slot->finished = NULL;
slot->callback_data = NULL;
slot->callback_func = NULL;
curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, pragma_header);
curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, curl_errorstr);
curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, NULL);
curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, NULL);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, NULL);
curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 0);
curl_easy_setopt(slot->curl, CURLOPT_HTTPGET, 1);
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);
int num_transfers;
if (curlm_result != CURLM_OK &&
curlm_result != CURLM_CALL_MULTI_PERFORM) {
active_requests--;
slot->in_use = 0;
return 0;
}
/*
* We know there must be something to do, since we just added
* something.
*/
curl_multi_perform(curlm, &num_transfers);
#endif
return 1;
}
#ifdef USE_CURL_MULTI
struct fill_chain {
void *data;
int (*fill)(void *);
struct fill_chain *next;
};
static struct fill_chain *fill_cfg;
void add_fill_function(void *data, int (*fill)(void *))
{
struct fill_chain *new = xmalloc(sizeof(*new));
struct fill_chain **linkp = &fill_cfg;
new->data = data;
new->fill = fill;
new->next = NULL;
while (*linkp)
linkp = &(*linkp)->next;
*linkp = new;
}
void fill_active_slots(void)
{
struct active_request_slot *slot = active_queue_head;
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)
break;
}
while (slot != NULL) {
if (!slot->in_use && slot->curl != NULL
&& curl_session_count > min_curl_sessions) {
curl_easy_cleanup(slot->curl);
slot->curl = NULL;
curl_session_count--;
}
slot = slot->next;
}
}
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
long last_pos = 0;
long current_pos;
fd_set readfds;
fd_set writefds;
fd_set excfds;
int max_fd;
struct timeval select_timeout;
int finished = 0;
slot->finished = &finished;
while (!finished) {
data_received = 0;
step_active_slots();
if (!data_received && slot->local != NULL) {
current_pos = ftell(slot->local);
if (current_pos > last_pos)
data_received++;
last_pos = current_pos;
}
if (slot->in_use && !data_received) {
max_fd = 0;
FD_ZERO(&readfds);
FD_ZERO(&writefds);
FD_ZERO(&excfds);
select_timeout.tv_sec = 0;
select_timeout.tv_usec = 50000;
select(max_fd, &readfds, &writefds,
&excfds, &select_timeout);
}
}
#else
while (slot->in_use) {
slot->curl_result = curl_easy_perform(slot->curl);
finish_active_slot(slot);
}
#endif
}
static void closedown_active_slot(struct active_request_slot *slot)
{
active_requests--;
slot->in_use = 0;
}
static void release_active_slot(struct active_request_slot *slot)
{
closedown_active_slot(slot);
if (slot->curl && curl_session_count > min_curl_sessions) {
#ifdef USE_CURL_MULTI
curl_multi_remove_handle(curlm, slot->curl);
#endif
curl_easy_cleanup(slot->curl);
slot->curl = NULL;
curl_session_count--;
}
#ifdef USE_CURL_MULTI
fill_active_slots();
#endif
}
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;
}
/* Run callback if appropriate */
if (slot->callback_func != NULL)
slot->callback_func(slot->callback_data);
}
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;
}
}
/* Helpers for modifying and creating URLs */
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 inline int hex(int v)
{
if (v < 10)
return '0' + v;
else
return 'A' + v - 10;
}
static void end_url_with_slash(struct strbuf *buf, const char *url)
{
strbuf_addstr(buf, url);
if (buf->len && buf->buf[buf->len - 1] != '/')
strbuf_addstr(buf, "/");
}
static char *quote_ref_url(const char *base, const char *ref)
{
struct strbuf buf = STRBUF_INIT;
const char *cp;
int ch;
end_url_with_slash(&buf, base);
for (cp = ref; (ch = *cp) != 0; cp++)
if (needs_quote(ch))
strbuf_addf(&buf, "%%%02x", ch);
else
strbuf_addch(&buf, *cp);
return strbuf_detach(&buf, NULL);
}
void append_remote_object_url(struct strbuf *buf, const char *url,
const char *hex,
int only_two_digit_prefix)
{
end_url_with_slash(buf, url);
strbuf_addf(buf, "objects/%.*s/", 2, hex);
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);
}
/* http_request() targets */
#define HTTP_REQUEST_STRBUF 0
#define HTTP_REQUEST_FILE 1
static int http_request(const char *url, void *result, int target, int options)
{
struct active_request_slot *slot;
struct slot_results results;
struct curl_slist *headers = NULL;
struct strbuf buf = STRBUF_INIT;
int ret;
slot = get_active_slot();
slot->results = &results;
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);
}
slot->local = result;
} else
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION,
fwrite_buffer);
}
strbuf_addstr(&buf, "Pragma:");
if (options & HTTP_NO_CACHE)
strbuf_addstr(&buf, " no-cache");
headers = curl_slist_append(headers, buf.buf);
curl_easy_setopt(slot->curl, CURLOPT_URL, url);
curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers);
if (start_active_slot(slot)) {
run_active_slot(slot);
if (results.curl_result == CURLE_OK)
ret = HTTP_OK;
else if (missing_target(&results))
ret = HTTP_MISSING_TARGET;
else
ret = HTTP_ERROR;
} else {
error("Unable to start HTTP request for %s", url);
ret = HTTP_START_FAILED;
}
slot->local = NULL;
curl_slist_free_all(headers);
strbuf_release(&buf);
return ret;
}
int http_get_strbuf(const char *url, struct strbuf *result, int options)
{
return http_request(url, result, HTTP_REQUEST_STRBUF, options);
}
/*
* Downloads an url and stores the result in the given file.
*
* If a previous interrupted download is detected (i.e. a previous temporary
* file is still around) the download is resumed.
*/
static int http_get_file(const char *url, const char *filename, int options)
{
int ret;
struct strbuf tmpfile = STRBUF_INIT;
FILE *result;
strbuf_addf(&tmpfile, "%s.temp", filename);
result = fopen(tmpfile.buf, "a");
if (! result) {
error("Unable to open local file %s", tmpfile.buf);
ret = HTTP_ERROR;
goto cleanup;
}
ret = http_request(url, result, HTTP_REQUEST_FILE, options);
fclose(result);
if ((ret == HTTP_OK) && move_temp_to_file(tmpfile.buf, filename))
ret = HTTP_ERROR;
cleanup:
strbuf_release(&tmpfile);
return ret;
}
int http_error(const char *url, int ret)
{
/* http_request has already handled HTTP_START_FAILED. */
if (ret != HTTP_START_FAILED)
error("%s while accessing %s\n", curl_errorstr, url);
return ret;
}
int http_fetch_ref(const char *base, struct ref *ref)
{
char *url;
struct strbuf buffer = STRBUF_INIT;
int ret = -1;
url = quote_ref_url(base, ref->name);
if (http_get_strbuf(url, &buffer, HTTP_NO_CACHE) == HTTP_OK) {
strbuf_rtrim(&buffer);
if (buffer.len == 40)
ret = get_sha1_hex(buffer.buf, ref->old_sha1);
else if (!prefixcmp(buffer.buf, "ref: ")) {
ref->symref = xstrdup(buffer.buf + 5);
ret = 0;
}
}
strbuf_release(&buffer);
free(url);
return ret;
}
/* Helpers for fetching packs */
static int fetch_pack_index(unsigned char *sha1, const char *base_url)
{
int ret = 0;
char *filename;
char *url = NULL;
struct strbuf buf = STRBUF_INIT;
if (has_pack_index(sha1)) {
ret = 0;
goto cleanup;
}
if (http_is_verbose)
fprintf(stderr, "Getting index for pack %s\n", sha1_to_hex(sha1));
end_url_with_slash(&buf, base_url);
strbuf_addf(&buf, "objects/pack/pack-%s.idx", sha1_to_hex(sha1));
url = strbuf_detach(&buf, NULL);
filename = sha1_pack_index_name(sha1);
if (http_get_file(url, filename, 0) != HTTP_OK)
ret = error("Unable to get pack index %s\n", url);
cleanup:
free(url);
return ret;
}
static int fetch_and_setup_pack_index(struct packed_git **packs_head,
unsigned char *sha1, const char *base_url)
{
struct packed_git *new_pack;
if (fetch_pack_index(sha1, base_url))
return -1;
new_pack = parse_pack_index(sha1, sha1_pack_index_name(sha1));
if (!new_pack)
return -1; /* parse_pack_index() already issued error message */
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)
{
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);
ret = http_get_strbuf(url, &buf, HTTP_NO_CACHE);
if (ret != HTTP_OK)
goto cleanup;
data = buf.buf;
while (i < buf.len) {
switch (data[i]) {
case 'P':
i++;
if (i + 52 <= buf.len &&
!prefixcmp(data + i, " pack-") &&
!prefixcmp(data + i + 46, ".pack\n")) {
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;
}
void release_http_pack_request(struct http_pack_request *preq)
{
if (preq->packfile != NULL) {
fclose(preq->packfile);
preq->packfile = NULL;
preq->slot->local = 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;
struct packed_git *p = preq->target;
char *tmp_idx;
struct child_process ip;
const char *ip_argv[8];
close_pack_index(p);
fclose(preq->packfile);
preq->packfile = NULL;
preq->slot->local = NULL;
lst = preq->lst;
while (*lst != p)
lst = &((*lst)->next);
*lst = (*lst)->next;
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;
memset(&ip, 0, sizeof(ip));
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);
return -1;
}
unlink(sha1_pack_index_name(p->sha1));
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);
return -1;
}
install_packed_git(p);
free(tmp_idx);
return 0;
}
struct http_pack_request *new_http_pack_request(
struct packed_git *target, const char *base_url)
{
char *filename;
long prev_posn = 0;
char range[RANGE_HEADER_SIZE];
struct strbuf buf = STRBUF_INIT;
struct http_pack_request *preq;
preq = xmalloc(sizeof(*preq));
preq->target = target;
preq->range_header = NULL;
end_url_with_slash(&buf, base_url);
strbuf_addf(&buf, "objects/pack/pack-%s.pack",
sha1_to_hex(target->sha1));
preq->url = strbuf_detach(&buf, NULL);
filename = sha1_pack_name(target->sha1);
snprintf(preq->tmpfile, sizeof(preq->tmpfile), "%s.temp", filename);
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();
preq->slot->local = preq->packfile;
curl_easy_setopt(preq->slot->curl, CURLOPT_FILE, preq->packfile);
curl_easy_setopt(preq->slot->curl, CURLOPT_WRITEFUNCTION, fwrite);
curl_easy_setopt(preq->slot->curl, CURLOPT_URL, preq->url);
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:
free(preq->url);
free(preq);
return NULL;
}
/* Helpers for fetching objects (loose) */
static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb,
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;
freq->stream.next_in = ptr;
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);
data_received++;
return size;
}
struct http_object_request *new_http_object_request(const char *base_url,
unsigned char *sha1)
{
char *hex = sha1_to_hex(sha1);
char *filename;
char prevfile[PATH_MAX];
int prevlocal;
unsigned char prev_buf[PREV_BUF_SIZE];
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;
freq = xmalloc(sizeof(*freq));
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) {
error("Couldn't create temporary file %s: %s",
freq->tmpfile, strerror(errno));
goto abort;
}
memset(&freq->stream, 0, sizeof(freq->stream));
git_inflate_init(&freq->stream);
git_SHA1_Init(&freq->c);
freq->url = get_remote_object_url(base_url, hex, 0);
/*
* 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);
if (ftruncate(freq->localfile, 0) < 0) {
error("Couldn't truncate temporary file %s: %s",
freq->tmpfile, strerror(errno));
goto abort;
}
}
}
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);
curl_easy_setopt(freq->slot->curl, CURLOPT_URL, freq->url);
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:
free(filename);
free(freq->url);
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) {
warning("requested range invalid; we may already have all the data.");
} 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 =
move_temp_to_file(freq->tmpfile, sha1_file_name(freq->sha1));
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;
}
if (freq->slot != NULL) {
freq->slot->callback_func = NULL;
freq->slot->callback_data = NULL;
release_active_slot(freq->slot);
freq->slot = NULL;
}
}