diff options
45 files changed, 694 insertions, 246 deletions
diff --git a/Documentation/git-index-pack.txt b/Documentation/git-index-pack.txt index d5b7560bfe..9316d9a80b 100644 --- a/Documentation/git-index-pack.txt +++ b/Documentation/git-index-pack.txt @@ -93,6 +93,14 @@ OPTIONS --max-input-size=<size>:: Die, if the pack is larger than <size>. +--object-format=<hash-algorithm>:: + Specify the given object format (hash algorithm) for the pack. The valid + values are 'sha1' and (if enabled) 'sha256'. The default is the algorithm for + the current repository (set by `extensions.objectFormat`), or 'sha1' if no + value is set or outside a repository. ++ +This option cannot be used with --stdin. + NOTES ----- diff --git a/Documentation/git-show-index.txt b/Documentation/git-show-index.txt index 424e4ba84c..39b1d8eaa1 100644 --- a/Documentation/git-show-index.txt +++ b/Documentation/git-show-index.txt @@ -9,7 +9,7 @@ git-show-index - Show packed archive index SYNOPSIS -------- [verse] -'git show-index' +'git show-index' [--object-format=<hash-algorithm>] DESCRIPTION @@ -36,6 +36,15 @@ Note that you can get more information on a packfile by calling linkgit:git-verify-pack[1]. However, as this command considers only the index file itself, it's both faster and more flexible. +OPTIONS +------- + +--object-format=<hash-algorithm>:: + Specify the given object format (hash algorithm) for the index file. The + valid values are 'sha1' and (if enabled) 'sha256'. The default is the + algorithm for the current repository (set by `extensions.objectFormat`), or + 'sha1' if no value is set or outside a repository.. + GIT --- Part of the linkgit:git[1] suite diff --git a/Documentation/gitremote-helpers.txt b/Documentation/gitremote-helpers.txt index 93baeeb029..6f1e269ae4 100644 --- a/Documentation/gitremote-helpers.txt +++ b/Documentation/gitremote-helpers.txt @@ -238,6 +238,9 @@ the remote repository. `--signed-tags=verbatim` to linkgit:git-fast-export[1]. In the absence of this capability, Git will use `--signed-tags=warn-strip`. +'object-format':: + This indicates that the helper is able to interact with the remote + side using an explicit hash algorithm extension. COMMANDS @@ -257,12 +260,14 @@ Support for this command is mandatory. 'list':: Lists the refs, one per line, in the format "<value> <name> [<attr> ...]". The value may be a hex sha1 hash, "@<dest>" for - a symref, or "?" to indicate that the helper could not get the - value of the ref. A space-separated list of attributes follows - the name; unrecognized attributes are ignored. The list ends - with a blank line. + a symref, ":<keyword> <value>" for a key-value pair, or + "?" to indicate that the helper could not get the value of the + ref. A space-separated list of attributes follows the name; + unrecognized attributes are ignored. The list ends with a + blank line. + See REF LIST ATTRIBUTES for a list of currently defined attributes. +See REF LIST KEYWORDS for a list of currently defined keywords. + Supported if the helper has the "fetch" or "import" capability. @@ -432,6 +437,18 @@ attributes are defined. This ref is unchanged since the last import or fetch, although the helper cannot necessarily determine what value that produced. +REF LIST KEYWORDS +----------------- + +The 'list' command may produce a list of key-value pairs. +The following keys are defined. + +'object-format':: + The refs are using the given hash algorithm. This keyword is only + used if the server and client both support the object-format + extension. + + OPTIONS ------- @@ -516,6 +533,14 @@ set by Git if the remote helper has the 'option' capability. transaction. If successful, all refs will be updated, or none will. If the remote side does not support this capability, the push will fail. +'option object-format' {'true'|algorithm}:: + If 'true', indicate that the caller wants hash algorithm information + to be passed back from the remote. This mode is used when fetching + refs. ++ +If set to an algorithm, indicate that the caller wants to interact with +the remote side using that algorithm. + SEE ALSO -------- linkgit:git-remote[1] diff --git a/Documentation/technical/protocol-capabilities.txt b/Documentation/technical/protocol-capabilities.txt index 2b267c0da6..36ccd14f97 100644 --- a/Documentation/technical/protocol-capabilities.txt +++ b/Documentation/technical/protocol-capabilities.txt @@ -176,6 +176,21 @@ agent strings are purely informative for statistics and debugging purposes, and MUST NOT be used to programmatically assume the presence or absence of particular features. +object-format +------------- + +This capability, which takes a hash algorithm as an argument, indicates +that the server supports the given hash algorithms. It may be sent +multiple times; if so, the first one given is the one used in the ref +advertisement. + +When provided by the client, this indicates that it intends to use the +given hash algorithm to communicate. The algorithm provided must be one +that the server supports. + +If this capability is not provided, it is assumed that the only +supported algorithm is SHA-1. + symref ------ diff --git a/Documentation/technical/protocol-v2.txt b/Documentation/technical/protocol-v2.txt index 5852f499a6..e597b74da3 100644 --- a/Documentation/technical/protocol-v2.txt +++ b/Documentation/technical/protocol-v2.txt @@ -483,3 +483,12 @@ included in a request. This is done by sending each option as a a request. The provided options must not contain a NUL or LF character. + + object-format +~~~~~~~~~~~~~~~ + +The server can advertise the `object-format` capability with a value `X` (in the +form `object-format=X`) to notify the client that the server is able to deal +with objects using hash algorithm X. If not specified, the server is assumed to +only handle SHA-1. If the client would like to use a hash algorithm other than +SHA-1, it should specify its object-format string. diff --git a/builtin/clone.c b/builtin/clone.c index 2a8e3aaaed..e3519a8355 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -1220,6 +1220,15 @@ int cmd_clone(int argc, const char **argv, const char *prefix) refs = transport_get_remote_refs(transport, &ref_prefixes); if (refs) { + int hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport)); + + /* + * Now that we know what algorithm the remote side is using, + * let's set ours to the same thing. + */ + initialize_repository_version(hash_algo); + repo_set_hash_algo(the_repository, hash_algo); + mapped_refs = wanted_peer_refs(refs, &remote->fetch); /* * transport_get_remote_refs() may return refs with null sha-1 diff --git a/builtin/index-pack.c b/builtin/index-pack.c index f176dd28c8..f865666db9 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1555,13 +1555,9 @@ static void read_v2_anomalous_offsets(struct packed_git *p, { const uint32_t *idx1, *idx2; uint32_t i; - const uint32_t hashwords = the_hash_algo->rawsz / sizeof(uint32_t); /* The address of the 4-byte offset table */ - idx1 = (((const uint32_t *)p->index_data) - + 2 /* 8-byte header */ - + 256 /* fan out */ - + hashwords * p->num_objects /* object ID table */ + idx1 = (((const uint32_t *)((const uint8_t *)p->index_data + p->crc_offset)) + p->num_objects /* CRC32 table */ ); @@ -1671,6 +1667,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) unsigned char pack_hash[GIT_MAX_RAWSZ]; unsigned foreign_nr = 1; /* zero is a "good" value, assume bad */ int report_end_of_input = 0; + int hash_algo = 0; /* * index-pack never needs to fetch missing objects except when @@ -1764,6 +1761,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) die(_("bad %s"), arg); } else if (skip_prefix(arg, "--max-input-size=", &arg)) { max_input_size = strtoumax(arg, NULL, 10); + } else if (skip_prefix(arg, "--object-format=", &arg)) { + hash_algo = hash_algo_by_name(arg); + if (hash_algo == GIT_HASH_UNKNOWN) + die(_("unknown hash algorithm '%s'"), arg); + repo_set_hash_algo(the_repository, hash_algo); } else usage(index_pack_usage); continue; @@ -1780,6 +1782,8 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix) die(_("--fix-thin cannot be used without --stdin")); if (from_stdin && !startup_info->have_repository) die(_("--stdin requires a git repository")); + if (from_stdin && hash_algo) + die(_("--object-format cannot be used with --stdin")); if (!index_name && pack_name) index_name = derive_filename(pack_name, "idx", &index_name_buf); diff --git a/builtin/ls-remote.c b/builtin/ls-remote.c index 6ef519514b..3a4dd12903 100644 --- a/builtin/ls-remote.c +++ b/builtin/ls-remote.c @@ -118,6 +118,10 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix) transport->server_options = &server_options; ref = transport_get_remote_refs(transport, &ref_prefixes); + if (ref) { + int hash_algo = hash_algo_by_ptr(transport_get_hash_algo(transport)); + repo_set_hash_algo(the_repository, hash_algo); + } if (transport_disconnect(transport)) { UNLEAK(sorting); return 1; diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index ea3d0f01af..d43663bb0a 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -249,6 +249,7 @@ static void show_ref(const char *path, const struct object_id *oid) strbuf_addf(&cap, " push-cert=%s", push_cert_nonce); if (advertise_push_options) strbuf_addstr(&cap, " push-options"); + strbuf_addf(&cap, " object-format=%s", the_hash_algo->name); strbuf_addf(&cap, " agent=%s", git_user_agent_sanitized()); packet_write_fmt(1, "%s %s%c%s\n", oid_to_hex(oid), path, 0, cap.buf); @@ -1624,6 +1625,8 @@ static struct command *read_head_info(struct packet_reader *reader, linelen = strlen(reader->line); if (linelen < reader->pktlen) { const char *feature_list = reader->line + linelen + 1; + const char *hash = NULL; + int len = 0; if (parse_feature_request(feature_list, "report-status")) report_status = 1; if (parse_feature_request(feature_list, "side-band-64k")) @@ -1636,6 +1639,13 @@ static struct command *read_head_info(struct packet_reader *reader, if (advertise_push_options && parse_feature_request(feature_list, "push-options")) use_push_options = 1; + hash = parse_feature_value(feature_list, "object-format", &len, NULL); + if (!hash) { + hash = hash_algos[GIT_HASH_SHA1].name; + len = strlen(hash); + } + if (xstrncmpz(the_hash_algo->name, hash, len)) + die("error: unsupported object format '%s'", hash); } if (!strcmp(reader->line, "push-cert")) { diff --git a/builtin/show-index.c b/builtin/show-index.c index 0826f6a5a2..8106b03a6b 100644 --- a/builtin/show-index.c +++ b/builtin/show-index.c @@ -1,9 +1,12 @@ #include "builtin.h" #include "cache.h" #include "pack.h" +#include "parse-options.h" -static const char show_index_usage[] = -"git show-index"; +static const char *const show_index_usage[] = { + "git show-index [--object-format=<hash-algorithm>]", + NULL +}; int cmd_show_index(int argc, const char **argv, const char *prefix) { @@ -11,10 +14,26 @@ int cmd_show_index(int argc, const char **argv, const char *prefix) unsigned nr; unsigned int version; static unsigned int top_index[256]; - const unsigned hashsz = the_hash_algo->rawsz; + unsigned hashsz; + const char *hash_name = NULL; + int hash_algo; + const struct option show_index_options[] = { + OPT_STRING(0, "object-format", &hash_name, N_("hash-algorithm"), + N_("specify the hash algorithm to use")), + OPT_END() + }; + + argc = parse_options(argc, argv, prefix, show_index_options, show_index_usage, 0); + + if (hash_name) { + hash_algo = hash_algo_by_name(hash_name); + if (hash_algo == GIT_HASH_UNKNOWN) + die(_("Unknown hash algorithm")); + repo_set_hash_algo(the_repository, hash_algo); + } + + hashsz = the_hash_algo->rawsz; - if (argc != 1) - usage(show_index_usage); if (fread(top_index, 2 * 4, 1, stdin) != 1) die("unable to read header"); if (top_index[0] == htonl(PACK_IDX_SIGNATURE)) { @@ -23,6 +23,17 @@ static void add_to_ref_list(const struct object_id *oid, const char *name, list->nr++; } +static const struct git_hash_algo *detect_hash_algo(struct strbuf *buf) +{ + size_t len = strcspn(buf->buf, " \n"); + int algo; + + algo = hash_algo_by_length(len / 2); + if (algo == GIT_HASH_UNKNOWN) + return NULL; + return &hash_algos[algo]; +} + static int parse_bundle_header(int fd, struct bundle_header *header, const char *report_path) { @@ -52,12 +63,21 @@ static int parse_bundle_header(int fd, struct bundle_header *header, } strbuf_rtrim(&buf); + if (!header->hash_algo) { + header->hash_algo = detect_hash_algo(&buf); + if (!header->hash_algo) { + error(_("unknown hash algorithm length")); + status = -1; + break; + } + } + /* * Tip lines have object name, SP, and refname. * Prerequisites have object name that is optionally * followed by SP and subject line. */ - if (parse_oid_hex(buf.buf, &oid, &p) || + if (parse_oid_hex_algop(buf.buf, &oid, &p, header->hash_algo) || (*p && !isspace(*p)) || (!is_prereq && !*p)) { if (report_path) @@ -15,6 +15,7 @@ struct ref_list { struct bundle_header { struct ref_list prerequisites; struct ref_list references; + const struct git_hash_algo *hash_algo; }; int is_bundle(const char *path, int quiet); @@ -18,7 +18,7 @@ static char *server_capabilities_v1; static struct argv_array server_capabilities_v2 = ARGV_ARRAY_INIT; -static const char *parse_feature_value(const char *, const char *, int *); +static const char *next_server_feature_value(const char *feature, int *len, int *offset); static int check_ref(const char *name, unsigned int flags) { @@ -83,6 +83,21 @@ int server_supports_v2(const char *c, int die_on_error) return 0; } +int server_feature_v2(const char *c, const char **v) +{ + int i; + + for (i = 0; i < server_capabilities_v2.argc; i++) { + const char *out; + if (skip_prefix(server_capabilities_v2.argv[i], c, &out) && + (*out == '=')) { + *v = out + 1; + return 1; + } + } + return 0; +} + int server_supports_feature(const char *c, const char *feature, int die_on_error) { @@ -181,17 +196,16 @@ reject: static void annotate_refs_with_symref_info(struct ref *ref) { struct string_list symref = STRING_LIST_INIT_DUP; - const char *feature_list = server_capabilities_v1; + int offset = 0; - while (feature_list) { + while (1) { int len; const char *val; - val = parse_feature_value(feature_list, "symref", &len); + val = next_server_feature_value("symref", &len, &offset); if (!val) break; parse_one_symref_info(&symref, val, len); - feature_list = val + 1; } string_list_sort(&symref); @@ -205,21 +219,36 @@ static void annotate_refs_with_symref_info(struct ref *ref) string_list_clear(&symref, 0); } -static void process_capabilities(const char *line, int *len) +static void process_capabilities(struct packet_reader *reader, int *linelen) { + const char *feat_val; + int feat_len; + const char *line = reader->line; int nul_location = strlen(line); - if (nul_location == *len) + if (nul_location == *linelen) return; server_capabilities_v1 = xstrdup(line + nul_location + 1); - *len = nul_location; + *linelen = nul_location; + + feat_val = server_feature_value("object-format", &feat_len); + if (feat_val) { + char *hash_name = xstrndup(feat_val, feat_len); + int hash_algo = hash_algo_by_name(hash_name); + if (hash_algo != GIT_HASH_UNKNOWN) + reader->hash_algo = &hash_algos[hash_algo]; + free(hash_name); + } else { + reader->hash_algo = &hash_algos[GIT_HASH_SHA1]; + } } -static int process_dummy_ref(const char *line) +static int process_dummy_ref(const struct packet_reader *reader) { + const char *line = reader->line; struct object_id oid; const char *name; - if (parse_oid_hex(line, &oid, &name)) + if (parse_oid_hex_algop(line, &oid, &name, reader->hash_algo)) return 0; if (*name != ' ') return 0; @@ -235,13 +264,15 @@ static void check_no_capabilities(const char *line, int len) line + strlen(line)); } -static int process_ref(const char *line, int len, struct ref ***list, - unsigned int flags, struct oid_array *extra_have) +static int process_ref(const struct packet_reader *reader, int len, + struct ref ***list, unsigned int flags, + struct oid_array *extra_have) { + const char *line = reader->line; struct object_id old_oid; const char *name; - if (parse_oid_hex(line, &old_oid, &name)) + if (parse_oid_hex_algop(line, &old_oid, &name, reader->hash_algo)) return 0; if (*name != ' ') return 0; @@ -261,16 +292,17 @@ static int process_ref(const char *line, int len, struct ref ***list, return 1; } -static int process_shallow(const char *line, int len, +static int process_shallow(const struct packet_reader *reader, int len, struct oid_array *shallow_points) { + const char *line = reader->line; const char *arg; struct object_id old_oid; if (!skip_prefix(line, "shallow ", &arg)) return 0; - if (get_oid_hex(arg, &old_oid)) + if (get_oid_hex_algop(arg, &old_oid, reader->hash_algo)) die(_("protocol error: expected shallow sha-1, got '%s'"), arg); if (!shallow_points) die(_("repository on the other end cannot be shallow")); @@ -317,20 +349,20 @@ struct ref **get_remote_heads(struct packet_reader *reader, switch (state) { case EXPECTING_FIRST_REF: - process_capabilities(reader->line, &len); - if (process_dummy_ref(reader->line)) { + process_capabilities(reader, &len); + if (process_dummy_ref(reader)) { state = EXPECTING_SHALLOW; break; } state = EXPECTING_REF; /* fallthrough */ case EXPECTING_REF: - if (process_ref(reader->line, len, &list, flags, extra_have)) + if (process_ref(reader, len, &list, flags, extra_have)) break; state = EXPECTING_SHALLOW; /* fallthrough */ case EXPECTING_SHALLOW: - if (process_shallow(reader->line, len, shallow_points)) + if (process_shallow(reader, len, shallow_points)) break; die(_("protocol error: unexpected '%s'"), reader->line); case EXPECTING_DONE: @@ -344,7 +376,7 @@ struct ref **get_remote_heads(struct packet_reader *reader, } /* Returns 1 when a valid ref has been added to `list`, 0 otherwise */ -static int process_ref_v2(const char *line, struct ref ***list) +static int process_ref_v2(struct packet_reader *reader, struct ref ***list) { int ret = 1; int i = 0; @@ -352,6 +384,7 @@ static int process_ref_v2(const char *line, struct ref ***list) struct ref *ref; struct string_list line_sections = STRING_LIST_INIT_DUP; const char *end; + const char *line = reader->line; /* * Ref lines have a number of fields which are space deliminated. The @@ -364,7 +397,7 @@ static int process_ref_v2(const char *line, struct ref ***list) goto out; } - if (parse_oid_hex(line_sections.items[i++].string, &old_oid, &end) || + if (parse_oid_hex_algop(line_sections.items[i++].string, &old_oid, &end, reader->hash_algo) || *end) { ret = 0; goto out; @@ -372,7 +405,7 @@ static int process_ref_v2(const char *line, struct ref ***list) ref = alloc_ref(line_sections.items[i++].string); - oidcpy(&ref->old_oid, &old_oid); + memcpy(ref->old_oid.hash, old_oid.hash, reader->hash_algo->rawsz); **list = ref; *list = &ref->next; @@ -385,7 +418,8 @@ static int process_ref_v2(const char *line, struct ref ***list) struct object_id peeled_oid; char *peeled_name; struct ref *peeled; - if (parse_oid_hex(arg, &peeled_oid, &end) || *end) { + if (parse_oid_hex_algop(arg, &peeled_oid, &end, + reader->hash_algo) || *end) { ret = 0; goto out; } @@ -393,7 +427,8 @@ static int process_ref_v2(const char *line, struct ref ***list) peeled_name = xstrfmt("%s^{}", ref->name); peeled = alloc_ref(peeled_name); - oidcpy(&peeled->old_oid, &peeled_oid); + memcpy(peeled->old_oid.hash, peeled_oid.hash, + reader->hash_algo->rawsz); **list = peeled; *list = &peeled->next; @@ -423,6 +458,7 @@ struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, int stateless_rpc) { int i; + const char *hash_name; *list = NULL; if (server_supports_v2("ls-refs", 1)) @@ -431,6 +467,16 @@ struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, if (server_supports_v2("agent", 0)) packet_write_fmt(fd_out, "agent=%s", git_user_agent_sanitized()); + if (server_feature_v2("object-format", &hash_name)) { + int hash_algo = hash_algo_by_name(hash_name); + if (hash_algo == GIT_HASH_UNKNOWN) + die(_("unknown object format '%s' specified by server"), hash_name); + reader->hash_algo = &hash_algos[hash_algo]; + packet_write_fmt(fd_out, "object-format=%s", reader->hash_algo->name); + } else { + reader->hash_algo = &hash_algos[GIT_HASH_SHA1]; + } + if (server_options && server_options->nr && server_supports_v2("server-option", 1)) for (i = 0; i < server_options->nr; i++) @@ -450,7 +496,7 @@ struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, /* Process response from server */ while (packet_reader_read(reader) == PACKET_READ_NORMAL) { - if (!process_ref_v2(reader->line, &list)) + if (!process_ref_v2(reader, &list)) die(_("invalid ls-refs response: %s"), reader->line); } @@ -463,7 +509,7 @@ struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, return list; } -static const char *parse_feature_value(const char *feature_list, const char *feature, int *lenp) +const char *parse_feature_value(const char *feature_list, const char *feature, int *lenp, int *offset) { int len; @@ -471,6 +517,8 @@ static const char *parse_feature_value(const char *feature_list, const char *fea return NULL; len = strlen(feature); + if (offset) + feature_list += *offset; while (*feature_list) { const char *found = strstr(feature_list, feature); if (!found) @@ -485,9 +533,14 @@ static const char *parse_feature_value(const char *feature_list, const char *fea } /* feature with a value (e.g., "agent=git/1.2.3") */ else if (*value == '=') { + int end; + value++; + end = strcspn(value, " \t\n"); if (lenp) - *lenp = strcspn(value, " \t\n"); + *lenp = end; + if (offset) + *offset = value + end - feature_list; return value; } /* @@ -500,14 +553,41 @@ static const char *parse_feature_value(const char *feature_list, const char *fea return NULL; } +int server_supports_hash(const char *desired, int *feature_supported) +{ + int offset = 0; + int len; + const char *hash; + + hash = next_server_feature_value("object-format", &len, &offset); + if (feature_supported) + *feature_supported = !!hash; + if (!hash) { + hash = hash_algos[GIT_HASH_SHA1].name; + len = strlen(hash); + } + while (hash) { + if (!xstrncmpz(desired, hash, len)) + return 1; + + hash = next_server_feature_value("object-format", &len, &offset); + } + return 0; +} + int parse_feature_request(const char *feature_list, const char *feature) { - return !!parse_feature_value(feature_list, feature, NULL); + return !!parse_feature_value(feature_list, feature, NULL, NULL); +} + +static const char *next_server_feature_value(const char *feature, int *len, int *offset) +{ + return parse_feature_value(server_capabilities_v1, feature, len, offset); } const char *server_feature_value(const char *feature, int *len) { - return parse_feature_value(server_capabilities_v1, feature, len); + return parse_feature_value(server_capabilities_v1, feature, len, NULL); } int server_supports(const char *feature) |