git/http.h

228 lines
6.2 KiB
C
Raw Normal View History

#ifndef HTTP_H
#define HTTP_H
#include "cache.h"
#include <curl/curl.h>
#include <curl/easy.h>
#include "strbuf.h"
#include "remote.h"
#include "url.h"
/*
* We detect based on the cURL version if multi-transfer is
* usable in this implementation and define this symbol accordingly.
* This shouldn't be set by the Makefile or by the user (e.g. via CFLAGS).
*/
#undef USE_CURL_MULTI
#if LIBCURL_VERSION_NUM >= 0x071000
#define USE_CURL_MULTI
#define DEFAULT_MAX_REQUESTS 5
#endif
#if LIBCURL_VERSION_NUM < 0x070704
#define curl_global_cleanup() do { /* nothing */ } while (0)
#endif
#if LIBCURL_VERSION_NUM < 0x070800
#define curl_global_init(a) do { /* nothing */ } while (0)
#endif
#if (LIBCURL_VERSION_NUM < 0x070c04) || (LIBCURL_VERSION_NUM == 0x071000)
#define NO_CURL_EASY_DUPHANDLE
#endif
#if LIBCURL_VERSION_NUM < 0x070a03
#define CURLE_HTTP_RETURNED_ERROR CURLE_HTTP_NOT_FOUND
#endif
#if LIBCURL_VERSION_NUM < 0x070c03
#define NO_CURL_IOCTL
#endif
/*
* CURLOPT_USE_SSL was known as CURLOPT_FTP_SSL up to 7.16.4,
* and the constants were known as CURLFTPSSL_*
*/
#if !defined(CURLOPT_USE_SSL) && defined(CURLOPT_FTP_SSL)
#define CURLOPT_USE_SSL CURLOPT_FTP_SSL
#define CURLUSESSL_TRY CURLFTPSSL_TRY
#endif
struct slot_results {
CURLcode curl_result;
long http_code;
long auth_avail;
long http_connectcode;
};
struct active_request_slot {
CURL *curl;
int in_use;
CURLcode curl_result;
long http_code;
int *finished;
struct slot_results *results;
void *callback_data;
void (*callback_func)(void *data);
struct active_request_slot *next;
};
struct buffer {
struct strbuf buf;
size_t posn;
};
/* Curl request read/write callbacks */
extern size_t fread_buffer(char *ptr, size_t eltsize, size_t nmemb, void *strbuf);
extern size_t fwrite_buffer(char *ptr, size_t eltsize, size_t nmemb, void *strbuf);
extern size_t fwrite_null(char *ptr, size_t eltsize, size_t nmemb, void *strbuf);
#ifndef NO_CURL_IOCTL
extern curlioerr ioctl_buffer(CURL *handle, int cmd, void *clientp);
#endif
/* Slot lifecycle functions */
extern struct active_request_slot *get_active_slot(void);
extern int start_active_slot(struct active_request_slot *slot);
extern void run_active_slot(struct active_request_slot *slot);
extern void finish_all_active_slots(void);
http: never use curl_easy_perform We currently don't reuse http connections when fetching via the smart-http protocol. This is bad because the TCP handshake introduces latency, and especially because SSL connection setup may be non-trivial. We can fix it by consistently using curl's "multi" interface. The reason is rather complicated: Our http code has two ways of being used: queuing many "slots" to be fetched in parallel, or fetching a single request in a blocking manner. The parallel code is built on curl's "multi" interface. Most of the single-request code uses http_request, which is built on top of the parallel code (we just feed it one slot, and wait until it finishes). However, one could also accomplish the single-request scheme by avoiding curl's multi interface entirely and just using curl_easy_perform. This is simpler, and is used by post_rpc in the smart-http protocol. It does work to use the same curl handle in both contexts, as long as it is not at the same time. However, internally curl may not share all of the cached resources between both contexts. In particular, a connection formed using the "multi" code will go into a reuse pool connected to the "multi" object. Further requests using the "easy" interface will not be able to reuse that connection. The smart http protocol does ref discovery via http_request, which uses the "multi" interface, and then follows up with the "easy" interface for its rpc calls. As a result, we make two HTTP connections rather than reusing a single one. We could teach the ref discovery to use the "easy" interface. But it is only once we have done this discovery that we know whether the protocol will be smart or dumb. If it is dumb, then our further requests, which want to fetch objects in parallel, will not be able to reuse the same connection. Instead, this patch switches post_rpc to build on the parallel interface, which means that we use it consistently everywhere. It's a little more complicated to use, but since we have the infrastructure already, it doesn't add any code; we can just factor out the relevant bits from http_request. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-02-18 18:34:20 +08:00
/*
* This will run one slot to completion in a blocking manner, similar to how
* curl_easy_perform would work (but we don't want to use that, because
* we do not want to intermingle calls to curl_multi and curl_easy).
*
*/
int run_one_slot(struct active_request_slot *slot,
struct slot_results *results);
#ifdef USE_CURL_MULTI
extern void fill_active_slots(void);
extern void add_fill_function(void *data, int (*fill)(void *));
extern void step_active_slots(void);
#endif
extern void http_init(struct remote *remote, const char *url,
int proactive_auth);
extern void http_cleanup(void);
extern long int git_curl_ipresolve;
extern int active_requests;
extern int http_is_verbose;
extern size_t http_post_buffer;
http: hoist credential request out of handle_curl_result When we are handling a curl response code in http_request or in the remote-curl RPC code, we use the handle_curl_result helper to translate curl's response into an easy-to-use code. When we see an HTTP 401, we do one of two things: 1. If we already had a filled-in credential, we mark it as rejected, and then return HTTP_NOAUTH to indicate to the caller that we failed. 2. If we didn't, then we ask for a new credential and tell the caller HTTP_REAUTH to indicate that they may want to try again. Rejecting in the first case makes sense; it is the natural result of the request we just made. However, prompting for more credentials in the second step does not always make sense. We do not know for sure that the caller is going to make a second request, and nor are we sure that it will be to the same URL. Logically, the prompt belongs not to the request we just finished, but to the request we are (maybe) about to make. In practice, it is very hard to trigger any bad behavior. Currently, if we make a second request, it will always be to the same URL (even in the face of redirects, because curl handles the redirects internally). And we almost always retry on HTTP_REAUTH these days. The one exception is if we are streaming a large RPC request to the server (e.g., a pushed packfile), in which case we cannot restart. It's extremely unlikely to see a 401 response at this stage, though, as we would typically have seen it when we sent a probe request, before streaming the data. This patch drops the automatic prompt out of case 2, and instead requires the caller to do it. This is a few extra lines of code, and the bug it fixes is unlikely to come up in practice. But it is conceptually cleaner, and paves the way for better handling of credentials across redirects. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
2013-09-28 16:31:45 +08:00
extern struct credential http_auth;
extern char curl_errorstr[CURL_ERROR_SIZE];
static inline int missing__target(int code, int result)
{
return /* file:// URL -- do we ever use one??? */
(result == CURLE_FILE_COULDNT_READ_FILE) ||
/* http:// and https:// URL */
(code == 404 && result == CURLE_HTTP_RETURNED_ERROR) ||
/* ftp:// URL */
(code == 550 && result == CURLE_FTP_COULDNT_RETR_FILE)
;
}
#define missing_target(a) missing__target((a)->http_code, (a)->curl_result)
http*: add helper methods for fetching objects (loose) The code handling the fetching of loose objects in http-push.c and http-walker.c have been refactored into new methods and a new struct (object_http_request) in http.c. They are not meant to be invoked elsewhere. The new methods in http.c are - new_http_object_request - process_http_object_request - finish_http_object_request - abort_http_object_request - release_http_object_request and the new struct is http_object_request. RANGER_HEADER_SIZE and no_pragma_header is no longer made available outside of http.c, since after the above changes, there are no other instances of usage outside of http.c. Remove members of the transfer_request struct in http-push.c and http-walker.c, including filename, real_sha1 and zret, as they are used no longer used. Move the methods append_remote_object_url() and get_remote_object_url() from http-push.c to http.c. Additionally, get_remote_object_url() is no longer defined only when USE_CURL_MULTI is defined, since non-USE_CURL_MULTI code in http.c uses it (namely, in new_http_object_request()). Refactor code from http-push.c::start_fetch_loose() and http-walker.c::start_object_fetch_request() that deals with the details of coming up with the filename to store the retrieved object, resuming a previously aborted request, and making a new curl request, into a new function, new_http_object_request(). Refactor code from http-walker.c::process_object_request() into the function, process_http_object_request(). Refactor code from http-push.c::finish_request() and http-walker.c::finish_object_request() into a new function, finish_http_object_request(). It returns the result of the move_temp_to_file() invocation. Add a function, release_http_object_request(), which cleans up object request data. http-push.c and http-walker.c invoke this function separately; http-push.c::release_request() and http-walker.c::release_object_request() do not invoke this function. Add a function, abort_http_object_request(), which unlink()s the object file and invokes release_http_object_request(). Update http-walker.c::abort_object_request() to use this. Signed-off-by: Tay Ray Chuan <rctay89@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-06-06 16:44:02 +08:00
/* Helpers for modifying and creating URLs */
extern void append_remote_object_url(struct strbuf *buf, const char *url,
const char *hex,
int only_two_digit_prefix);
extern char *get_remote_object_url(const char *url, const char *hex,
int only_two_digit_prefix);
/* Options for http_get_*() */
struct http_get_options {
unsigned no_cache:1,
keep_error:1;
/* If non-NULL, returns the content-type of the response. */
struct strbuf *content_type;
/*
* If non-NULL, and content_type above is non-NULL, returns
* the charset parameter from the content-type. If none is
* present, returns an empty string.
*/
struct strbuf *charset;
/*
* If non-NULL, returns the URL we ended up at, including any
* redirects we followed.
*/
struct strbuf *effective_url;
http: update base URLs when we see redirects If a caller asks the http_get_* functions to go to a particular URL and we end up elsewhere due to a redirect, the effective_url field can tell us where we went. It would be nice to remember this redirect and short-cut further requests for two reasons: 1. It's more efficient. Otherwise we spend an extra http round-trip to the server for each subsequent request, just to get redirected. 2. If we end up with an http 401 and are going to ask for credentials, it is to feed them to the redirect target. If the redirect is an http->https upgrade, this means our credentials may be provided on the http leg, just to end up redirected to https. And if the redirect crosses server boundaries, then curl will drop the credentials entirely as it follows the redirect. However, it, it is not enough to simply record the effective URL we saw and use that for subsequent requests. We were originally fed a "base" url like: http://example.com/foo.git and we want to figure out what the new base is, even though the URLs we see may be: original: http://example.com/foo.git/info/refs effective: http://example.com/bar.git/info/refs Subsequent requests will not be for "info/refs", but for other paths relative to the base. We must ask the caller to pass in the original base, and we must pass the redirected base back to the caller (so that it can generate more URLs from it). Furthermore, we need to feed the new base to the credential code, so that requests to credential helpers (or to the user) match the URL we will be requesting. This patch teaches http_request_reauth to do this munging. Since it is the caller who cares about making more URLs, it seems at first glance that callers could simply check effective_url themselves and handle it. However, since we need to update the credential struct before the second re-auth request, we have to do it inside http_request_reauth. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
2013-09-28 16:34:05 +08:00
/*
* If both base_url and effective_url are non-NULL, the base URL will
* be munged to reflect any redirections going from the requested url
* to effective_url. See the definition of update_url_from_redirect
* for details.
*/
struct strbuf *base_url;
};
/* Return values for http_get_*() */
#define HTTP_OK 0
#define HTTP_MISSING_TARGET 1
#define HTTP_ERROR 2
#define HTTP_START_FAILED 3
#define HTTP_REAUTH 4
#define HTTP_NOAUTH 5
/*
* Requests a URL and stores the result in a strbuf.
*
* If the result pointer is NULL, a HTTP HEAD request is made instead of GET.
*/
int http_get_strbuf(const char *url, struct strbuf *result, struct http_get_options *options);
extern int http_fetch_ref(const char *base, struct ref *ref);
/* Helpers for fetching packs */
extern int http_get_info_packs(const char *base_url,
struct packed_git **packs_head);
struct http_pack_request {
char *url;
struct packed_git *target;
struct packed_git **lst;
FILE *packfile;
char tmpfile[PATH_MAX];
struct active_request_slot *slot;
};
extern struct http_pack_request *new_http_pack_request(
struct packed_git *target, const char *base_url);
extern int finish_http_pack_request(struct http_pack_request *preq);
extern void release_http_pack_request(struct http_pack_request *preq);
http*: add helper methods for fetching objects (loose) The code handling the fetching of loose objects in http-push.c and http-walker.c have been refactored into new methods and a new struct (object_http_request) in http.c. They are not meant to be invoked elsewhere. The new methods in http.c are - new_http_object_request - process_http_object_request - finish_http_object_request - abort_http_object_request - release_http_object_request and the new struct is http_object_request. RANGER_HEADER_SIZE and no_pragma_header is no longer made available outside of http.c, since after the above changes, there are no other instances of usage outside of http.c. Remove members of the transfer_request struct in http-push.c and http-walker.c, including filename, real_sha1 and zret, as they are used no longer used. Move the methods append_remote_object_url() and get_remote_object_url() from http-push.c to http.c. Additionally, get_remote_object_url() is no longer defined only when USE_CURL_MULTI is defined, since non-USE_CURL_MULTI code in http.c uses it (namely, in new_http_object_request()). Refactor code from http-push.c::start_fetch_loose() and http-walker.c::start_object_fetch_request() that deals with the details of coming up with the filename to store the retrieved object, resuming a previously aborted request, and making a new curl request, into a new function, new_http_object_request(). Refactor code from http-walker.c::process_object_request() into the function, process_http_object_request(). Refactor code from http-push.c::finish_request() and http-walker.c::finish_object_request() into a new function, finish_http_object_request(). It returns the result of the move_temp_to_file() invocation. Add a function, release_http_object_request(), which cleans up object request data. http-push.c and http-walker.c invoke this function separately; http-push.c::release_request() and http-walker.c::release_object_request() do not invoke this function. Add a function, abort_http_object_request(), which unlink()s the object file and invokes release_http_object_request(). Update http-walker.c::abort_object_request() to use this. Signed-off-by: Tay Ray Chuan <rctay89@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-06-06 16:44:02 +08:00
/* Helpers for fetching object */
struct http_object_request {
http*: add helper methods for fetching objects (loose) The code handling the fetching of loose objects in http-push.c and http-walker.c have been refactored into new methods and a new struct (object_http_request) in http.c. They are not meant to be invoked elsewhere. The new methods in http.c are - new_http_object_request - process_http_object_request - finish_http_object_request - abort_http_object_request - release_http_object_request and the new struct is http_object_request. RANGER_HEADER_SIZE and no_pragma_header is no longer made available outside of http.c, since after the above changes, there are no other instances of usage outside of http.c. Remove members of the transfer_request struct in http-push.c and http-walker.c, including filename, real_sha1 and zret, as they are used no longer used. Move the methods append_remote_object_url() and get_remote_object_url() from http-push.c to http.c. Additionally, get_remote_object_url() is no longer defined only when USE_CURL_MULTI is defined, since non-USE_CURL_MULTI code in http.c uses it (namely, in new_http_object_request()). Refactor code from http-push.c::start_fetch_loose() and http-walker.c::start_object_fetch_request() that deals with the details of coming up with the filename to store the retrieved object, resuming a previously aborted request, and making a new curl request, into a new function, new_http_object_request(). Refactor code from http-walker.c::process_object_request() into the function, process_http_object_request(). Refactor code from http-push.c::finish_request() and http-walker.c::finish_object_request() into a new function, finish_http_object_request(). It returns the result of the move_temp_to_file() invocation. Add a function, release_http_object_request(), which cleans up object request data. http-push.c and http-walker.c invoke this function separately; http-push.c::release_request() and http-walker.c::release_object_request() do not invoke this function. Add a function, abort_http_object_request(), which unlink()s the object file and invokes release_http_object_request(). Update http-walker.c::abort_object_request() to use this. Signed-off-by: Tay Ray Chuan <rctay89@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-06-06 16:44:02 +08:00
char *url;
char tmpfile[PATH_MAX];
int localfile;
CURLcode curl_result;
char errorstr[CURL_ERROR_SIZE];
long http_code;
unsigned char sha1[20];
unsigned char real_sha1[20];
git_SHA_CTX c;
2011-06-11 02:52:15 +08:00
git_zstream stream;
http*: add helper methods for fetching objects (loose) The code handling the fetching of loose objects in http-push.c and http-walker.c have been refactored into new methods and a new struct (object_http_request) in http.c. They are not meant to be invoked elsewhere. The new methods in http.c are - new_http_object_request - process_http_object_request - finish_http_object_request - abort_http_object_request - release_http_object_request and the new struct is http_object_request. RANGER_HEADER_SIZE and no_pragma_header is no longer made available outside of http.c, since after the above changes, there are no other instances of usage outside of http.c. Remove members of the transfer_request struct in http-push.c and http-walker.c, including filename, real_sha1 and zret, as they are used no longer used. Move the methods append_remote_object_url() and get_remote_object_url() from http-push.c to http.c. Additionally, get_remote_object_url() is no longer defined only when USE_CURL_MULTI is defined, since non-USE_CURL_MULTI code in http.c uses it (namely, in new_http_object_request()). Refactor code from http-push.c::start_fetch_loose() and http-walker.c::start_object_fetch_request() that deals with the details of coming up with the filename to store the retrieved object, resuming a previously aborted request, and making a new curl request, into a new function, new_http_object_request(). Refactor code from http-walker.c::process_object_request() into the function, process_http_object_request(). Refactor code from http-push.c::finish_request() and http-walker.c::finish_object_request() into a new function, finish_http_object_request(). It returns the result of the move_temp_to_file() invocation. Add a function, release_http_object_request(), which cleans up object request data. http-push.c and http-walker.c invoke this function separately; http-push.c::release_request() and http-walker.c::release_object_request() do not invoke this function. Add a function, abort_http_object_request(), which unlink()s the object file and invokes release_http_object_request(). Update http-walker.c::abort_object_request() to use this. Signed-off-by: Tay Ray Chuan <rctay89@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-06-06 16:44:02 +08:00
int zret;
int rename;
struct active_request_slot *slot;
};
extern struct http_object_request *new_http_object_request(
const char *base_url, unsigned char *sha1);
extern void process_http_object_request(struct http_object_request *freq);
extern int finish_http_object_request(struct http_object_request *freq);
extern void abort_http_object_request(struct http_object_request *freq);
extern void release_http_object_request(struct http_object_request *freq);
#endif /* HTTP_H */