1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-06-28 07:11:21 +02:00
git/builtin/commit-graph.c

284 lines
7.9 KiB
C
Raw Normal View History

#include "builtin.h"
#include "config.h"
#include "dir.h"
#include "lockfile.h"
#include "parse-options.h"
#include "repository.h"
#include "commit-graph.h"
#include "object-store.h"
static char const * const builtin_commit_graph_usage[] = {
N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
N_("git commit-graph write [--object-dir <objdir>] [--append] "
"[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
"[--changed-paths] [--[no-]progress] <split options>"),
NULL
};
static const char * const builtin_commit_graph_verify_usage[] = {
N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
NULL
};
static const char * const builtin_commit_graph_write_usage[] = {
N_("git commit-graph write [--object-dir <objdir>] [--append] "
"[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
"[--changed-paths] [--[no-]progress] <split options>"),
NULL
};
static struct opts_commit_graph {
const char *obj_dir;
int reachable;
int stdin_packs;
int stdin_commits;
int append;
int split;
int shallow;
int progress;
int enable_changed_paths;
} opts;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
static struct object_directory *find_odb(struct repository *r,
const char *obj_dir)
{
struct object_directory *odb;
char *obj_dir_real = real_pathdup(obj_dir, 1);
struct strbuf odb_path_real = STRBUF_INIT;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
prepare_alt_odb(r);
for (odb = r->objects->odb; odb; odb = odb->next) {
strbuf_realpath(&odb_path_real, odb->path, 1);
if (!strcmp(obj_dir_real, odb_path_real.buf))
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
break;
}
free(obj_dir_real);
strbuf_release(&odb_path_real);
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
if (!odb)
die(_("could not find object directory matching %s"), obj_dir);
return odb;
}
static int graph_verify(int argc, const char **argv)
{
struct commit_graph *graph = NULL;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
struct object_directory *odb = NULL;
char *graph_name;
commit-graph: don't early exit(1) on e.g. "git status" Make the commit-graph loading code work as a library that returns an error code instead of calling exit(1) when the commit-graph is corrupt. This means that e.g. "status" will now report commit-graph corruption as an "error: [...]" at the top of its output, but then proceed to work normally. This required splitting up the load_commit_graph_one() function so that the code that deals with open()-ing and stat()-ing the graph can now be called independently as open_commit_graph(). This is needed because "commit-graph verify" where the graph doesn't exist isn't an error. See the third paragraph in 283e68c72f ("commit-graph: add 'verify' subcommand", 2018-06-27). There's a bug in that logic where we conflate the intended ENOENT with other errno values (e.g. EACCES), but this change doesn't address that. That'll be addressed in a follow-up change. I'm then splitting most of the logic out of load_commit_graph_one() into load_commit_graph_one_fd_st(), which allows for providing an existing file descriptor and stat information to the loading code. This isn't strictly needed, but it would be redundant and confusing to open() and stat() the file twice for some of the codepaths, this allows for calling open_commit_graph() followed by load_commit_graph_one_fd_st(). The "graph_file" still needs to be passed to that function for the the "graph file %s is too small" error message. This leaves load_commit_graph_one() unused by everything except the internal prepare_commit_graph_one() function, so let's mark it as "static". If someone needs it in the future we can remove the "static" attribute. I could also rewrite its sole remaining user ("prepare_commit_graph_one()") to use load_commit_graph_one_fd_st() instead, but let's leave it at this. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:30 +01:00
int open_ok;
int fd;
struct stat st;
int flags = 0;
static struct option builtin_commit_graph_verify_options[] = {
OPT_STRING(0, "object-dir", &opts.obj_dir,
N_("dir"),
N_("The object directory to store the graph")),
OPT_BOOL(0, "shallow", &opts.shallow,
N_("if the commit-graph is split, only verify the tip file")),
OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
OPT_END(),
};
trace2_cmd_mode("verify");
opts.progress = isatty(2);
argc = parse_options(argc, argv, NULL,
builtin_commit_graph_verify_options,
builtin_commit_graph_verify_usage, 0);
if (!opts.obj_dir)
opts.obj_dir = get_object_directory();
if (opts.shallow)
flags |= COMMIT_GRAPH_VERIFY_SHALLOW;
if (opts.progress)
flags |= COMMIT_GRAPH_WRITE_PROGRESS;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
odb = find_odb(the_repository, opts.obj_dir);
commit-graph.c: remove path normalization, comparison As of the previous patch, all calls to 'commit-graph.c' functions which perform path normalization (for e.g., 'get_commit_graph_filename()') are of the form 'ctx->odb->path', which is always in normalized form. Now that there are no callers passing non-normalized paths to these functions, ensure that future callers are bound by the same restrictions by making these functions take a 'struct object_directory *' instead of a 'const char *'. To match, replace all calls with arguments of the form 'ctx->odb->path' with 'ctx->odb' To recover the path, functions that perform path manipulation simply use 'odb->path'. Further, avoid string comparisons with arguments of the form 'odb->path', and instead prefer raw pointer comparisons, which accomplish the same effect, but are far less brittle. This has a pleasant side-effect of making these functions much more robust to paths that cannot be normalized by 'normalize_path_copy()', i.e., because they are outside of the current working directory. For example, prior to this patch, Valgrind reports that the following uninitialized memory read [1]: $ ( cd t && GIT_DIR=../.git valgrind git rev-parse HEAD^ ) because 'normalize_path_copy()' can't normalize '../.git' (since it's relative to but above of the current working directory) [2]. By using a 'struct object_directory *' directly, 'get_commit_graph_filename()' does not need to normalize, because all paths are relative to the current working directory since they are always read from the '->path' of an object directory. [1]: https://lore.kernel.org/git/20191027042116.GA5801@sigill.intra.peff.net. [2]: The bug here is that 'get_commit_graph_filename()' returns the result of 'normalize_path_copy()' without checking the return value. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-03 22:18:02 +01:00
graph_name = get_commit_graph_filename(odb);
commit-graph: don't early exit(1) on e.g. "git status" Make the commit-graph loading code work as a library that returns an error code instead of calling exit(1) when the commit-graph is corrupt. This means that e.g. "status" will now report commit-graph corruption as an "error: [...]" at the top of its output, but then proceed to work normally. This required splitting up the load_commit_graph_one() function so that the code that deals with open()-ing and stat()-ing the graph can now be called independently as open_commit_graph(). This is needed because "commit-graph verify" where the graph doesn't exist isn't an error. See the third paragraph in 283e68c72f ("commit-graph: add 'verify' subcommand", 2018-06-27). There's a bug in that logic where we conflate the intended ENOENT with other errno values (e.g. EACCES), but this change doesn't address that. That'll be addressed in a follow-up change. I'm then splitting most of the logic out of load_commit_graph_one() into load_commit_graph_one_fd_st(), which allows for providing an existing file descriptor and stat information to the loading code. This isn't strictly needed, but it would be redundant and confusing to open() and stat() the file twice for some of the codepaths, this allows for calling open_commit_graph() followed by load_commit_graph_one_fd_st(). The "graph_file" still needs to be passed to that function for the the "graph file %s is too small" error message. This leaves load_commit_graph_one() unused by everything except the internal prepare_commit_graph_one() function, so let's mark it as "static". If someone needs it in the future we can remove the "static" attribute. I could also rewrite its sole remaining user ("prepare_commit_graph_one()") to use load_commit_graph_one_fd_st() instead, but let's leave it at this. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:30 +01:00
open_ok = open_commit_graph(graph_name, &fd, &st);
if (!open_ok && errno != ENOENT)
die_errno(_("Could not open commit-graph '%s'"), graph_name);
FREE_AND_NULL(graph_name);
if (open_ok)
graph = load_commit_graph_one_fd_st(fd, &st, odb);
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
else
graph = read_commit_graph_one(the_repository, odb);
/* Return failure if open_ok predicted success */
if (!graph)
return !!open_ok;
UNLEAK(graph);
return verify_commit_graph(the_repository, graph, flags);
}
extern int read_replace_refs;
static struct split_commit_graph_opts split_opts;
static int write_option_parse_split(const struct option *opt, const char *arg,
int unset)
{
enum commit_graph_split_flags *flags = opt->value;
opts.split = 1;
if (!arg)
return 0;
if (!strcmp(arg, "no-merge"))
*flags = COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED;
builtin/commit-graph.c: introduce split strategy 'replace' When using split commit-graphs, it is sometimes useful to completely replace the commit-graph chain with a new base. For example, consider a scenario in which a repository builds a new commit-graph incremental for each push. Occasionally (say, after some fixed number of pushes), they may wish to rebuild the commit-graph chain with all reachable commits. They can do so with $ git commit-graph write --reachable but this removes the chain entirely and replaces it with a single commit-graph in 'objects/info/commit-graph'. Unfortunately, this means that the next push will have to move this commit-graph into the first layer of a new chain, and then write its new commits on top. Avoid such copying entirely by allowing the caller to specify that they wish to replace the entirety of their commit-graph chain, while also specifying that the new commit-graph should become the basis of a fresh, length-one chain. This addresses the above situation by making it possible for the caller to instead write: $ git commit-graph write --reachable --split=replace which writes a new length-one chain to 'objects/info/commit-graphs', making the commit-graph incremental generated by the subsequent push relatively cheap by avoiding the aforementioned copy. In order to do this, remove an assumption in 'write_commit_graph_file' that chains are always at least two incrementals long. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-14 06:04:17 +02:00
else if (!strcmp(arg, "replace"))
*flags = COMMIT_GRAPH_SPLIT_REPLACE;
else
die(_("unrecognized --split argument, %s"), arg);
return 0;
}
static int graph_write(int argc, const char **argv)
{
struct string_list *pack_indexes = NULL;
struct oidset commits = OIDSET_INIT;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
struct object_directory *odb = NULL;
struct string_list lines;
int result = 0;
enum commit_graph_write_flags flags = 0;
static struct option builtin_commit_graph_write_options[] = {
OPT_STRING(0, "object-dir", &opts.obj_dir,
N_("dir"),
N_("The object directory to store the graph")),
OPT_BOOL(0, "reachable", &opts.reachable,
N_("start walk at all refs")),
OPT_BOOL(0, "stdin-packs", &opts.stdin_packs,
N_("scan pack-indexes listed by stdin for commits")),
OPT_BOOL(0, "stdin-commits", &opts.stdin_commits,
N_("start walk at commits listed by stdin")),
OPT_BOOL(0, "append", &opts.append,
N_("include all commits already in the commit-graph file")),
OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
N_("enable computation for changed paths")),
OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
OPT_CALLBACK_F(0, "split", &split_opts.flags, NULL,
N_("allow writing an incremental commit-graph file"),
PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
write_option_parse_split),
OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
N_("maximum number of commits in a non-base split commit-graph")),
OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
N_("maximum ratio between two levels of a split commit-graph")),
OPT_EXPIRY_DATE(0, "expire-time", &split_opts.expire_time,
N_("only expire files older than a given date-time")),
OPT_END(),
};
opts.progress = isatty(2);
split_opts.size_multiple = 2;
split_opts.max_commits = 0;
split_opts.expire_time = 0;
trace2_cmd_mode("write");
argc = parse_options(argc, argv, NULL,
builtin_commit_graph_write_options,
builtin_commit_graph_write_usage, 0);
if (opts.reachable + opts.stdin_packs + opts.stdin_commits > 1)
die(_("use at most one of --reachable, --stdin-commits, or --stdin-packs"));
if (!opts.obj_dir)
opts.obj_dir = get_object_directory();
if (opts.append)
flags |= COMMIT_GRAPH_WRITE_APPEND;
if (opts.split)
flags |= COMMIT_GRAPH_WRITE_SPLIT;
if (opts.progress)
flags |= COMMIT_GRAPH_WRITE_PROGRESS;
if (opts.enable_changed_paths ||
git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0))
flags |= COMMIT_GRAPH_WRITE_BLOOM_FILTERS;
read_replace_refs = 0;
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
odb = find_odb(the_repository, opts.obj_dir);
if (opts.reachable) {
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
if (write_commit_graph_reachable(odb, flags, &split_opts))
return 1;
return 0;
}
string_list_init(&lines, 0);
if (opts.stdin_packs || opts.stdin_commits) {
struct strbuf buf = STRBUF_INIT;
while (strbuf_getline(&buf, stdin) != EOF)
string_list_append(&lines, strbuf_detach(&buf, NULL));
if (opts.stdin_packs)
pack_indexes = &lines;
commit-graph: error out on invalid commit oids in 'write --stdin-commits' While 'git commit-graph write --stdin-commits' expects commit object ids as input, it accepts and silently skips over any invalid commit object ids, and still exits with success: # nonsense $ echo not-a-commit-oid | git commit-graph write --stdin-commits $ echo $? 0 # sometimes I forgot that refs are not good... $ echo HEAD | git commit-graph write --stdin-commits $ echo $? 0 # valid tree OID, but not a commit OID $ git rev-parse HEAD^{tree} | git commit-graph write --stdin-commits $ echo $? 0 $ ls -l .git/objects/info/commit-graph ls: cannot access '.git/objects/info/commit-graph': No such file or directory Check that all input records are indeed valid commit object ids and return with error otherwise, the same way '--stdin-packs' handles invalid input; see e103f7276f (commit-graph: return with errors during write, 2019-06-12). Note that it should only return with error when encountering an invalid commit object id coming from standard input. However, '--reachable' uses the same code path to process object ids pointed to by all refs, and that includes tag object ids as well, which should still be skipped over. Therefore add a new flag to 'enum commit_graph_write_flags' and a corresponding field to 'struct write_commit_graph_context', so we can differentiate between those two cases. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Acked-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-08-05 10:02:40 +02:00
if (opts.stdin_commits) {
struct string_list_item *item;
oidset_init(&commits, lines.nr);
for_each_string_list_item(item, &lines) {
struct object_id oid;
const char *end;
if (parse_oid_hex(item->string, &oid, &end)) {
error(_("unexpected non-hex object ID: "
"%s"), item->string);
return 1;
}
oidset_insert(&commits, &oid);
}
commit-graph: error out on invalid commit oids in 'write --stdin-commits' While 'git commit-graph write --stdin-commits' expects commit object ids as input, it accepts and silently skips over any invalid commit object ids, and still exits with success: # nonsense $ echo not-a-commit-oid | git commit-graph write --stdin-commits $ echo $? 0 # sometimes I forgot that refs are not good... $ echo HEAD | git commit-graph write --stdin-commits $ echo $? 0 # valid tree OID, but not a commit OID $ git rev-parse HEAD^{tree} | git commit-graph write --stdin-commits $ echo $? 0 $ ls -l .git/objects/info/commit-graph ls: cannot access '.git/objects/info/commit-graph': No such file or directory Check that all input records are indeed valid commit object ids and return with error otherwise, the same way '--stdin-packs' handles invalid input; see e103f7276f (commit-graph: return with errors during write, 2019-06-12). Note that it should only return with error when encountering an invalid commit object id coming from standard input. However, '--reachable' uses the same code path to process object ids pointed to by all refs, and that includes tag object ids as well, which should still be skipped over. Therefore add a new flag to 'enum commit_graph_write_flags' and a corresponding field to 'struct write_commit_graph_context', so we can differentiate between those two cases. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Acked-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-08-05 10:02:40 +02:00
flags |= COMMIT_GRAPH_WRITE_CHECK_OIDS;
}
UNLEAK(buf);
}
commit-graph.h: store an odb in 'struct write_commit_graph_context' There are lots of places in 'commit-graph.h' where a function either has (or almost has) a full 'struct object_directory *', accesses '->path', and then throws away the rest of the struct. This can cause headaches when comparing the locations of object directories across alternates (e.g., in the case of deciding if two commit-graph layers can be merged). These paths are normalized with 'normalize_path_copy()' which mitigates some comparison issues, but not all [1]. Replace usage of 'char *object_dir' with 'odb->path' by storing a 'struct object_directory *' in the 'write_commit_graph_context' structure. This is an intermediate step towards getting rid of all path normalization in 'commit-graph.c'. Resolving a user-provided '--object-dir' argument now requires that we compare it to the known alternates for equality. Prior to this patch, an unknown '--object-dir' argument would silently exit with status zero. This can clearly lead to unintended behavior, such as verifying commit-graphs that aren't in a repository's own object store (or one of its alternates), or causing a typo to mask a legitimate commit-graph verification failure. Make this error non-silent by 'die()'-ing when the given '--object-dir' does not match any known alternate object store. [1]: In my testing, for example, I can get one side of the commit-graph code to fill object_dir with "./objects" and the other with just "objects". Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-02-04 06:51:50 +01:00
if (write_commit_graph(odb,
pack_indexes,
opts.stdin_commits ? &commits : NULL,
flags,
&split_opts))
result = 1;
UNLEAK(lines);
return result;
}
int cmd_commit_graph(int argc, const char **argv, const char *prefix)
{
static struct option builtin_commit_graph_options[] = {
OPT_STRING(0, "object-dir", &opts.obj_dir,
N_("dir"),
N_("The object directory to store the graph")),
OPT_END(),
};
if (argc == 2 && !strcmp(argv[1], "-h"))
usage_with_options(builtin_commit_graph_usage,
builtin_commit_graph_options);
git_config(git_default_config, NULL);
argc = parse_options(argc, argv, prefix,
builtin_commit_graph_options,
builtin_commit_graph_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
save_commit_buffer = 0;
if (argc > 0) {
if (!strcmp(argv[0], "verify"))
return graph_verify(argc, argv);
if (!strcmp(argv[0], "write"))
return graph_write(argc, argv);
}
usage_with_options(builtin_commit_graph_usage,
builtin_commit_graph_options);
}