Git Source Code Mirror - This is a publish-only repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvements. https://git-scm.com/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
git/http-walker.c

620 lines
15 KiB

#include "cache.h"
#include "repository.h"
#include "commit.h"
#include "walker.h"
#include "http.h"
#include "list.h"
http: respect protocol.*.allow=user for http-alternates The http-walker may fetch the http-alternates (or alternates) file from a remote in order to find more objects. This should count as a "not from the user" use of the protocol. But because we implement the redirection ourselves and feed the new URL to curl, it will use the CURLOPT_PROTOCOLS rules, not the more restrictive CURLOPT_REDIR_PROTOCOLS. The ideal solution would be for each curl request we make to know whether or not is directly from the user or part of an alternates redirect, and then set CURLOPT_PROTOCOLS as appropriate. However, that would require plumbing that information through all of the various layers of the http code. Instead, let's check the protocol at the source: when we are parsing the remote http-alternates file. The only downside is that if there's any mismatch between what protocol we think it is versus what curl thinks it is, it could violate the policy. To address this, we'll make the parsing err on the picky side, and only allow protocols that it can parse definitively. So for example, you can't elude the "http" policy by asking for "HTTP://", even though curl might handle it; we would reject it as unknown. The only unsafe case would be if you have a URL that starts with "http://" but curl interprets as another protocol. That seems like an unlikely failure mode (and we are still protected by our base CURLOPT_PROTOCOL setting, so the worst you could do is trigger one of https, ftp, or ftps). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
6 years ago
#include "transport.h"
#include "packfile.h"
#include "object-store.h"
struct alt_base {
char *base;
int got_indices;
struct packed_git *packs;
struct alt_base *next;
};
enum object_request_state {
WAITING,
ABORTED,
ACTIVE,
COMPLETE
};
struct object_request {
struct walker *walker;
struct object_id oid;
struct alt_base *repo;
enum object_request_state state;
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>
13 years ago
struct http_object_request *req;
struct list_head node;
};
struct alternates_request {
struct walker *walker;
const char *base;
struct strbuf *url;
struct strbuf *buffer;
struct active_request_slot *slot;
int http_specific;
};
struct walker_data {
const char *url;
int got_alternates;
struct alt_base *alt;
};
static LIST_HEAD(object_queue_head);
static void fetch_alternates(struct walker *walker, const char *base);
static void process_object_response(void *callback_data);
static void start_object_request(struct walker *walker,
struct object_request *obj_req)
{
struct active_request_slot *slot;
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>
13 years ago
struct http_object_request *req;
req = new_http_object_request(obj_req->repo->base, &obj_req->oid);
if (!req) {
obj_req->state = ABORTED;
return;
}
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>
13 years ago
obj_req->req = req;
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>
13 years ago
slot = req->slot;
slot->callback_func = process_object_response;
slot->callback_data = obj_req;
/* Try to get the request started, abort the request on error */
obj_req->state = ACTIVE;
if (!start_active_slot(slot)) {
obj_req->state = ABORTED;
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>
13 years ago
release_http_object_request(req);
return;
}
}
static void finish_object_request(struct object_request *obj_req)
{
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>
13 years ago
if (finish_http_object_request(obj_req->req))
return;
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>
13 years ago
if (obj_req->req->rename == 0)
walker_say(obj_req->walker, "got %s\n", oid_to_hex(&obj_req->oid));
}
static void process_object_response(void *callback_data)
{
struct object_request *obj_req =
(struct object_request *)callback_data;
struct walker *walker = obj_req->walker;
struct walker_data *data = walker->data;
struct alt_base *alt = data->alt;
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>
13 years ago
process_http_object_request(obj_req->req);
obj_req->state = COMPLETE;
normalize_curl_result(&obj_req->req->curl_result,
obj_req->req->http_code,
obj_req->req->errorstr,
sizeof(obj_req->req->errorstr));
/* Use alternates if necessary */
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>
13 years ago
if (missing_target(obj_req->req)) {
fetch_alternates(walker, alt->base);
if (obj_req->repo->next) {
obj_req->repo =
obj_req->repo->next;
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>
13 years ago
release_http_object_request(obj_req->req);
start_object_request(walker, obj_req);
return;
}
}
finish_object_request(obj_req);
}
static void release_object_request(struct object_request *obj_req)
{
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>
13 years ago
if (obj_req->req !=NULL && obj_req->req->localfile != -1)
error("fd leakage in release: %d", obj_req->req->localfile);
list_del(&obj_req->node);
free(obj_req);
}
static int fill_active_slot(struct walker *walker)
{
struct object_request *obj_req;
struct list_head *pos, *tmp, *head = &object_queue_head;
list_for_each_safe(pos, tmp, head) {
obj_req = list_entry(pos, struct object_request, node);
if (obj_req->state == WAITING) {
if (has_object_file(&obj_req->oid))
obj_req->state = COMPLETE;
else {
start_object_request(walker, obj_req);
return 1;
}
}
}
return 0;
}
static void prefetch(struct walker *walker, unsigned char *sha1)
{
struct object_request *newreq;
struct walker_data *data = walker->data;
newreq = xmalloc(sizeof(*newreq));
newreq->walker = walker;
oidread(&newreq->oid, sha1);
newreq->repo = data->alt;
newreq->state = WAITING;
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>
13 years ago
newreq->req = NULL;
http_is_verbose = walker->get_verbosely;
list_add_tail(&newreq->node, &object_queue_head);
fill_active_slots();
step_active_slots();
}
http: respect protocol.*.allow=user for http-alternates The http-walker may fetch the http-alternates (or alternates) file from a remote in order to find more objects. This should count as a "not from the user" use of the protocol. But because we implement the redirection ourselves and feed the new URL to curl, it will use the CURLOPT_PROTOCOLS rules, not the more restrictive CURLOPT_REDIR_PROTOCOLS. The ideal solution would be for each curl request we make to know whether or not is directly from the user or part of an alternates redirect, and then set CURLOPT_PROTOCOLS as appropriate. However, that would require plumbing that information through all of the various layers of the http code. Instead, let's check the protocol at the source: when we are parsing the remote http-alternates file. The only downside is that if there's any mismatch between what protocol we think it is versus what curl thinks it is, it could violate the policy. To address this, we'll make the parsing err on the picky side, and only allow protocols that it can parse definitively. So for example, you can't elude the "http" policy by asking for "HTTP://", even though curl might handle it; we would reject it as unknown. The only unsafe case would be if you have a URL that starts with "http://" but curl interprets as another protocol. That seems like an unlikely failure mode (and we are still protected by our base CURLOPT_PROTOCOL setting, so the worst you could do is trigger one of https, ftp, or ftps). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
6 years ago
static int is_alternate_allowed(const char *url)
{
const char *protocols[] = {
"http", "https", "ftp", "ftps"
};
int i;
if (http_follow_config != HTTP_FOLLOW_ALWAYS) {
warning("alternate disabled by http.followRedirects: %s", url);
return 0;
}
http: respect protocol.*.allow=user for http-alternates The http-walker may fetch the http-alternates (or alternates) file from a remote in order to find more objects. This should count as a "not from the user" use of the protocol. But because we implement the redirection ourselves and feed the new URL to curl, it will use the CURLOPT_PROTOCOLS rules, not the more restrictive CURLOPT_REDIR_PROTOCOLS. The ideal solution would be for each curl request we make to know whether or not is directly from the user or part of an alternates redirect, and then set CURLOPT_PROTOCOLS as appropriate. However, that would require plumbing that information through all of the various layers of the http code. Instead, let's check the protocol at the source: when we are parsing the remote http-alternates file. The only downside is that if there's any mismatch between what protocol we think it is versus what curl thinks it is, it could violate the policy. To address this, we'll make the parsing err on the picky side, and only allow protocols that it can parse definitively. So for example, you can't elude the "http" policy by asking for "HTTP://", even though curl might handle it; we would reject it as unknown. The only unsafe case would be if you have a URL that starts with "http://" but curl interprets as another protocol. That seems like an unlikely failure mode (and we are still protected by our base CURLOPT_PROTOCOL setting, so the worst you could do is trigger one of https, ftp, or ftps). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
6 years ago
for (i = 0; i < ARRAY_SIZE(protocols); i++) {
const char *end;
if (skip_prefix(url, protocols[i], &end) &&
starts_with(end, "://"))
break;
}
if (i >= ARRAY_SIZE(protocols)) {
warning("ignoring alternate with unknown protocol: %s", url);
return 0;
}
if (!is_transport_allowed(protocols[i], 0)) {
warning("ignoring alternate with restricted protocol: %s", url);
return 0;
}
return 1;
}
static void process_alternates_response(void *callback_data)
{
struct alternates_request *alt_req =
(struct alternates_request *)callback_data;
struct walker *walker = alt_req->walker;
struct walker_data *cdata = walker->data;
struct active_request_slot *slot = alt_req->slot;
struct alt_base *tail = cdata->alt;
const char *base = alt_req->base;
const char null_byte = '\0';
char *data;
int i = 0;
normalize_curl_result(&slot->curl_result, slot->http_code,
curl_errorstr, sizeof(curl_errorstr));
if (alt_req->http_specific) {
if (slot->curl_result != CURLE_OK ||
!alt_req->buffer->len) {
/* Try reusing the slot to get non-http alternates */
alt_req->http_specific = 0;
strbuf_reset(alt_req->url);
strbuf_addf(alt_req->url, "%s/objects/info/alternates",
base);
curl_easy_setopt(slot->curl, CURLOPT_URL,
alt_req->url->buf);
active_requests++;
slot->in_use = 1;
if (slot->finished)
(*slot->finished) = 0;
if (!start_active_slot(slot)) {
cdata->got_alternates = -1;
slot->in_use = 0;
if (slot->finished)
(*slot->finished) = 1;
}
return;
}
} else if (slot->curl_result != CURLE_OK) {
if (!missing_target(slot)) {
cdata->got_alternates = -1;
return;
}
}
fwrite_buffer((char *)&null_byte, 1, 1, alt_req->buffer);
alt_req->buffer->len--;
data = alt_req->buffer->buf;
while (i < alt_req->buffer->len) {
int posn = i;
while (posn < alt_req->buffer->len && data[posn] != '\n')
posn++;
if (data[posn] == '\n') {
int okay = 0;
int serverlen = 0;
struct alt_base *newalt;
if (data[i] == '/') {
/*
* This counts
* http://git.host/pub/scm/linux.git/
* -----------here^
* so memcpy(dst, base, serverlen) will
* copy up to "...git.host".
*/
const char *colon_ss = strstr(base,"://");
if (colon_ss) {
serverlen = (strchr(colon_ss + 3, '/')
- base);
okay = 1;
}
} else if (!memcmp(data + i, "../", 3)) {
/*
* Relative URL; chop the corresponding
* number of subpath from base (and ../
* from data), and concatenate the result.
*
* The code first drops ../ from data, and
* then drops one ../ from data and one path
* from base. IOW, one extra ../ is dropped
* from data than path is dropped from base.
*
* This is not wrong. The alternate in
* http://git.host/pub/scm/linux.git/
* to borrow from
* http://git.host/pub/scm/linus.git/
* is ../../linus.git/objects/. You need
* two ../../ to borrow from your direct
* neighbour.
*/
i += 3;
serverlen = strlen(base);
while (i + 2 < posn &&
!memcmp(data + i, "../", 3)) {
do {
serverlen--;
} while (serverlen &&
base[serverlen - 1] != '/');
i += 3;
}
/* If the server got removed, give up. */
okay = strchr(base, ':') - base + 3 <
serverlen;
} else if (alt_req->http_specific) {
char *colon = strchr(data + i, ':');
char *slash = strchr(data + i, '/');
if (colon && slash && colon < data + posn &&
slash < data + posn && colon < slash) {
okay = 1;
}
}
if (okay) {
struct strbuf target = STRBUF_INIT;
strbuf_add(&target, base, serverlen);
strbuf_add(&target, data + i, posn - i);
if (!strbuf_strip_suffix(&target, "objects")) {
warning("ignoring alternate that does"
" not end in 'objects': %s",
target.buf);
strbuf_release(&target);
} else if (is_alternate_allowed(target.buf)) {
http: respect protocol.*.allow=user for http-alternates The http-walker may fetch the http-alternates (or alternates) file from a remote in order to find more objects. This should count as a "not from the user" use of the protocol. But because we implement the redirection ourselves and feed the new URL to curl, it will use the CURLOPT_PROTOCOLS rules, not the more restrictive CURLOPT_REDIR_PROTOCOLS. The ideal solution would be for each curl request we make to know whether or not is directly from the user or part of an alternates redirect, and then set CURLOPT_PROTOCOLS as appropriate. However, that would require plumbing that information through all of the various layers of the http code. Instead, let's check the protocol at the source: when we are parsing the remote http-alternates file. The only downside is that if there's any mismatch between what protocol we think it is versus what curl thinks it is, it could violate the policy. To address this, we'll make the parsing err on the picky side, and only allow protocols that it can parse definitively. So for example, you can't elude the "http" policy by asking for "HTTP://", even though curl might handle it; we would reject it as unknown. The only unsafe case would be if you have a URL that starts with "http://" but curl interprets as another protocol. That seems like an unlikely failure mode (and we are still protected by our base CURLOPT_PROTOCOL setting, so the worst you could do is trigger one of https, ftp, or ftps). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
6 years ago
warning("adding alternate object store: %s",
target.buf);
newalt = xmalloc(sizeof(*newalt));
newalt->next = NULL;
newalt->base = strbuf_detach(&target, NULL);
newalt->got_indices = 0;
newalt->packs = NULL;
while (tail->next != NULL)
tail = tail->next;
tail->next = newalt;
} else {
strbuf_release(&target);
http: respect protocol.*.allow=user for http-alternates The http-walker may fetch the http-alternates (or alternates) file from a remote in order to find more objects. This should count as a "not from the user" use of the protocol. But because we implement the redirection ourselves and feed the new URL to curl, it will use the CURLOPT_PROTOCOLS rules, not the more restrictive CURLOPT_REDIR_PROTOCOLS. The ideal solution would be for each curl request we make to know whether or not is directly from the user or part of an alternates redirect, and then set CURLOPT_PROTOCOLS as appropriate. However, that would require plumbing that information through all of the various layers of the http code. Instead, let's check the protocol at the source: when we are parsing the remote http-alternates file. The only downside is that if there's any mismatch between what protocol we think it is versus what curl thinks it is, it could violate the policy. To address this, we'll make the parsing err on the picky side, and only allow protocols that it can parse definitively. So for example, you can't elude the "http" policy by asking for "HTTP://", even though curl might handle it; we would reject it as unknown. The only unsafe case would be if you have a URL that starts with "http://" but curl interprets as another protocol. That seems like an unlikely failure mode (and we are still protected by our base CURLOPT_PROTOCOL setting, so the worst you could do is trigger one of https, ftp, or ftps). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
6 years ago
}
}
}
i = posn + 1;
}
cdata->got_alternates = 1;
}
static void fetch_alternates(struct walker *walker, const char *base)
{
struct strbuf buffer = STRBUF_INIT;
struct strbuf url = STRBUF_INIT;
struct active_request_slot *slot;
struct alternates_request alt_req;
struct walker_data *cdata = walker->data;
/*
* If another request has already started fetching alternates,
* wait for them to arrive and return to processing this request's
* curl message
*/
while (cdata->got_alternates == 0) {
step_active_slots();
}
/* Nothing to do if they've already been fetched */
if (cdata->got_alternates == 1)
return;
/* Start the fetch */
cdata->got_alternates = 0;
if (walker->get_verbosely)
fprintf(stderr, "Getting alternates list for %s\n", base);
strbuf_addf(&url, "%s/objects/info/http-alternates", base);
/*
* Use a callback to process the result, since another request
* may fail and need to have alternates loaded before continuing
*/
slot = get_active_slot();
slot->callback_func = process_alternates_response;
alt_req.walker = walker;
slot->callback_data = &alt_req;
curl_easy_setopt(slot->curl, CURLOPT_WRITEDATA, &buffer);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer);
curl_easy_setopt(slot->curl, CURLOPT_URL, url.buf);
alt_req.base = base;
alt_req.url = &url;
alt_req.buffer = &buffer;
alt_req.http_specific = 1;
alt_req.slot = slot;
if (start_active_slot(slot))
run_active_slot(slot);
else
cdata->got_alternates = -1;
strbuf_release(&buffer);
strbuf_release(&url);
}
static int fetch_indices(struct walker *walker, struct alt_base *repo)
{
int ret;
if (repo->got_indices)
return 0;
if (walker->get_verbosely)
fprintf(stderr, "Getting pack list for %s\n", repo->base);
switch (http_get_info_packs(repo->base, &repo->packs)) {
case HTTP_OK:
case HTTP_MISSING_TARGET:
repo->got_indices = 1;
ret = 0;
break;
default:
repo->got_indices = 0;
ret = -1;
}
return ret;
}
static int http_fetch_pack(struct walker *walker, struct alt_base *repo, unsigned char *sha1)
{
struct packed_git *target;
int ret;
struct slot_results results;
struct http_pack_request *preq;
if (fetch_indices(walker, repo))
return -1;
target = find_sha1_pack(sha1, repo->packs);
if (!target)
return -1;
close_pack_index(target);
if (walker->get_verbosely) {
fprintf(stderr, "Getting pack %s\n",
hash_to_hex(target->hash));
fprintf(stderr, " which contains %s\n",
hash_to_hex(sha1));
}
preq = new_http_pack_request(target->hash, repo->base);
if (!preq)
goto abort;
preq->slot->results = &results;
if (start_active_slot(preq->slot)) {
run_active_slot(preq->slot);
if (results.curl_result != CURLE_OK) {
error("Unable to get pack file %s\n%s", preq->url,
curl_errorstr);
goto abort;
}
} else {
error("Unable to start request");
goto abort;
}
ret = finish_http_pack_request(preq);
release_http_pack_request(preq);
if (ret)
return ret;
http_install_packfile(target, &repo->packs);
return 0;
abort:
return -1;
}
static void abort_object_request(struct object_request *obj_req)
{
release_object_request(obj_req);
}
static int fetch_object(struct walker *walker, unsigned char *hash)
{
char *hex = hash_to_hex(hash);
int ret = 0;
struct object_request *obj_req = NULL;