diff options
99 files changed, 4602 insertions, 788 deletions
diff --git a/Documentation/Makefile b/Documentation/Makefile index d47acb2e25..5e1a7f655c 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -476,8 +476,19 @@ $(LINT_DOCS_MAN_SECTION_ORDER): .build/lint-docs/man-section-order/%.ok: %.txt .PHONY: lint-docs-man-section-order lint-docs-man-section-order: $(LINT_DOCS_MAN_SECTION_ORDER) +.PHONY: lint-docs-fsck-msgids +LINT_DOCS_FSCK_MSGIDS = .build/lint-docs/fsck-msgids.ok +$(LINT_DOCS_FSCK_MSGIDS): lint-fsck-msgids.perl +$(LINT_DOCS_FSCK_MSGIDS): ../fsck.h fsck-msgids.txt + $(call mkdir_p_parent_template) + $(QUIET_GEN)$(PERL_PATH) lint-fsck-msgids.perl \ + ../fsck.h fsck-msgids.txt $@ + +lint-docs-fsck-msgids: $(LINT_DOCS_FSCK_MSGIDS) + ## Lint: list of targets above .PHONY: lint-docs +lint-docs: lint-docs-fsck-msgids lint-docs: lint-docs-gitlink lint-docs: lint-docs-man-end-blurb lint-docs: lint-docs-man-section-order diff --git a/Documentation/RelNotes/2.39.0.txt b/Documentation/RelNotes/2.39.0.txt index f87c4c442e..7096f07689 100644 --- a/Documentation/RelNotes/2.39.0.txt +++ b/Documentation/RelNotes/2.39.0.txt @@ -20,6 +20,14 @@ UI, Workflows & Features description of the branch you were on before switching to the current branch. + * "git merge-tree --stdin" is a new way to request a series of merges + and report the merge results. + + * "git shortlog" learned to group by the "format" string. + + * A new "--include-whitespace" option is added to "git patch-id", and + existing bugs in the internal patch-id logic that did not match + what "git patch-id" produces have been corrected. Performance, Internal Implementation, Development Support etc. -------------------------------------------------------------- @@ -55,6 +63,26 @@ Performance, Internal Implementation, Development Support etc. compiler. (merge 4b992f0a24 jk/unused-anno-more later to maint). + * Rewrite a deep recursion in the skipping negotiator to use a loop + with on-heap prio queue to avoid stack wastage. + + * Add documentation for message IDs in fsck error messages. + + * Define the logical elements of a "bundle list", data structure to + store them in-core, format to transfer them, and code to parse + them. + + * The role the security mailing list plays in an embargoed release + has been documented. + + * Two new facilities, "timer" and "counter", are introduced to the + trace2 API. + + * Code simplification by using strvec_pushf() instead of building an + argument in a separate strbuf. + + * Make sure generated dependency file is stably sorted to help + developers debugging their build issues. Fixes since v2.38 ----------------- @@ -162,6 +190,35 @@ Fixes since v2.38 adjust them to compute the display width assuming UTF-8 pathnames. (merge ce8529b2bb tb/diffstat-with-utf8-strwidth later to maint). + * "git branch --edit-description" can exit with status -1 which is + not a good practice; it learned to use 1 as everybody else instead. + + * "git apply" limits its input to a bit less than 1 GiB. + + * Merging a branch with directory renames into a branch that changes + the directory to a symlink was mishandled by the ort merge + strategy, which has been corrected. + + * A bugfix to "git subtree" in its split and merge features. + + * Fix some bugs in the reflog messages when rebasing and changes the + reflog messages of "rebase --apply" to match "rebase --merge" with + the aim of making the reflog easier to parse. + + * "git rebase --keep-base" used to discard the commits that are + already cherry-picked to the upstream, even when "keep-base" meant + that the base, on top of which the history is being rebuilt, does + not yet include these cherry-picked commits. The --keep-base + option now implies --reapply-cherry-picks and --no-fork-point + options. + + * The way "git repack" creared temporary files when it received a + signal was prone to deadlocking, which has been corrected. + + * Various tests exercising the transfer.credentialsInUrl + configuration are taught to avoid making requests which require + resolving localhost to reduce CI-flakiness. + * Other code cleanup, docfix, build fix, etc. (merge 413bc6d20a ds/cmd-main-reorder later to maint). (merge 8d2863e4ed nw/t1002-cleanup later to maint). diff --git a/Documentation/build-docdep.perl b/Documentation/build-docdep.perl index ba4205e030..1b3ac8fdd9 100755 --- a/Documentation/build-docdep.perl +++ b/Documentation/build-docdep.perl @@ -38,9 +38,10 @@ while ($changed) { } } -while (my ($text, $included) = each %include) { +foreach my $text (sort keys %include) { + my $included = $include{$text}; if (! exists $included{$text} && (my $base = $text) =~ s/\.txt$//) { - print "$base.html $base.xml : ", join(" ", keys %$included), "\n"; + print "$base.html $base.xml : ", join(" ", sort keys %$included), "\n"; } } diff --git a/Documentation/config.txt b/Documentation/config.txt index 1e20583165..0e93aef862 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -387,6 +387,8 @@ include::config/branch.txt[] include::config/browser.txt[] +include::config/bundle.txt[] + include::config/checkout.txt[] include::config/clean.txt[] diff --git a/Documentation/config/bundle.txt b/Documentation/config/bundle.txt new file mode 100644 index 0000000000..daa21eb674 --- /dev/null +++ b/Documentation/config/bundle.txt @@ -0,0 +1,24 @@ +bundle.*:: + The `bundle.*` keys may appear in a bundle list file found via the + `git clone --bundle-uri` option. These keys currently have no effect + if placed in a repository config file, though this will change in the + future. See link:technical/bundle-uri.html[the bundle URI design + document] for more details. + +bundle.version:: + This integer value advertises the version of the bundle list format + used by the bundle list. Currently, the only accepted value is `1`. + +bundle.mode:: + This string value should be either `all` or `any`. This value describes + whether all of the advertised bundles are required to unbundle a + complete understanding of the bundled information (`all`) or if any one + of the listed bundle URIs is sufficient (`any`). + +bundle.<id>.*:: + The `bundle.<id>.*` keys are used to describe a single item in the + bundle list, grouped under `<id>` for identification purposes. + +bundle.<id>.uri:: + This string value defines the URI by which Git can reach the contents + of this `<id>`. This URI may be a bundle file or another bundle list. diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt index 37afbaf5a4..dfbdaf00b8 100644 --- a/Documentation/config/core.txt +++ b/Documentation/config/core.txt @@ -618,7 +618,7 @@ but risks losing recent work in the event of an unclean system shutdown. * `loose-object` hardens objects added to the repo in loose-object form. * `pack` hardens objects added to the repo in packfile form. * `pack-metadata` hardens packfile bitmaps and indexes. -* `commit-graph` hardens the commit graph file. +* `commit-graph` hardens the commit-graph file. * `index` hardens the index when it is modified. * `objects` is an aggregate option that is equivalent to `loose-object,pack`. diff --git a/Documentation/config/feature.txt b/Documentation/config/feature.txt index cdecd04e5b..95975e5091 100644 --- a/Documentation/config/feature.txt +++ b/Documentation/config/feature.txt @@ -14,6 +14,9 @@ feature.experimental:: + * `fetch.negotiationAlgorithm=skipping` may improve fetch negotiation times by skipping more commits at a time, reducing the number of round trips. ++ +* `gc.cruftPacks=true` reduces disk space used by unreachable objects during +garbage collection, preventing loose object explosions. feature.manyFiles:: Enable config options that optimize for repos with many files in the diff --git a/Documentation/config/fsck.txt b/Documentation/config/fsck.txt index 450e8c38e3..a3c865df56 100644 --- a/Documentation/config/fsck.txt +++ b/Documentation/config/fsck.txt @@ -35,6 +35,10 @@ allow new instances of the same breakages go unnoticed. Setting an unknown `fsck.<msg-id>` value will cause fsck to die, but doing the same for `receive.fsck.<msg-id>` and `fetch.fsck.<msg-id>` will only cause git to warn. ++ +See `Fsck Messages` section of linkgit:git-fsck[1] for supported +values of `<msg-id>`. + fsck.skipList:: The path to a list of object names (i.e. one unabbreviated SHA-1 per diff --git a/Documentation/fsck-msgids.txt b/Documentation/fsck-msgids.txt new file mode 100644 index 0000000000..7af76ff99a --- /dev/null +++ b/Documentation/fsck-msgids.txt @@ -0,0 +1,161 @@ +`badDate`:: + (ERROR) Invalid date format in an author/committer line. + +`badDateOverflow`:: + (ERROR) Invalid date value in an author/committer line. + +`badEmail`:: + (ERROR) Invalid email format in an author/committer line. + +`badFilemode`:: + (INFO) A tree contains a bad filemode entry. + +`badName`:: + (ERROR) An author/committer name is empty. + +`badObjectSha1`:: + (ERROR) An object has a bad sha1. + +`badParentSha1`:: + (ERROR) A commit object has a bad parent sha1. + +`badTagName`:: + (INFO) A tag has an invalid format. + +`badTimezone`:: + (ERROR) Found an invalid time zone in an author/committer line. + +`badTree`:: + (ERROR) A tree cannot be parsed. + +`badTreeSha1`:: + (ERROR) A tree has an invalid format. + +`badType`:: + (ERROR) Found an invalid object type. + +`duplicateEntries`:: + (ERROR) A tree contains duplicate file entries. + +`emptyName`:: + (WARN) A path contains an empty name. + +`extraHeaderEntry`:: + (IGNORE) Extra headers found after `tagger`. + +`fullPathname`:: + (WARN) A path contains the full path starting with "/". + +`gitattributesSymlink`:: + (INFO) `.gitattributes` is a symlink. + +`gitignoreSymlink`:: + (INFO) `.gitignore` is a symlink. + +`gitmodulesBlob`:: + (ERROR) A non-blob found at `.gitmodules`. + +`gitmodulesLarge`:: + (ERROR) The `.gitmodules` file is too large to parse. + +`gitmodulesMissing`:: + (ERROR) Unable to read `.gitmodules` blob. + +`gitmodulesName`:: + (ERROR) A submodule name is invalid. + +`gitmodulesParse`:: + (INFO) Could not parse `.gitmodules` blob. + +`gitmodulesLarge`; + (ERROR) `.gitmodules` blob is too large to parse. + +`gitmodulesPath`:: + (ERROR) `.gitmodules` path is invalid. + +`gitmodulesSymlink`:: + (ERROR) `.gitmodules` is a symlink. + +`gitmodulesUpdate`:: + (ERROR) Found an invalid submodule update setting. + +`gitmodulesUrl`:: + (ERROR) Found an invalid submodule url. + +`hasDot`:: + (WARN) A tree contains an entry named `.`. + +`hasDotdot`:: + (WARN) A tree contains an entry named `..`. + +`hasDotgit`:: + (WARN) A tree contains an entry named `.git`. + +`mailmapSymlink`:: + (INFO) `.mailmap` is a symlink. + +`missingAuthor`:: + (ERROR) Author is missing. + +`missingCommitter`:: + (ERROR) Committer is missing. + +`missingEmail`:: + (ERROR) Email is missing in an author/committer line. + +`missingNameBeforeEmail`:: + (ERROR) Missing name before an email in an author/committer line. + +`missingObject`:: + (ERROR) Missing `object` line in tag object. + +`missingSpaceBeforeDate`:: + (ERROR) Missing space before date in an author/committer line. + +`missingSpaceBeforeEmail`:: + (ERROR) Missing space before the email in author/committer line. + +`missingTag`:: + (ERROR) Unexpected end after `type` line in a tag object. + +`missingTagEntry`:: + (ERROR) Missing `tag` line in a tag object. + +`missingTaggerEntry`:: + (INFO) Missing `tagger` line in a tag object. + +`missingTree`:: + (ERROR) Missing `tree` line in a commit object. + +`missingType`:: + (ERROR) Invalid type value on the `type` line in a tag object. + +`missingTypeEntry`:: + (ERROR) Missing `type` line in a tag object. + +`multipleAuthors`:: + (ERROR) Multiple author lines found in a commit. + +`nulInCommit`:: + (WARN) Found a NUL byte in the commit object body. + +`nulInHeader`:: + (FATAL) NUL byte exists in the object header. + +`nullSha1`:: + (WARN) Tree contains entries pointing to a null sha1. + +`treeNotSorted`:: + (ERROR) A tree is not properly sorted. + +`unknownType`:: + (ERROR) Found an unknown object type. + +`unterminatedHeader`:: + (FATAL) Missing end-of-line in the object header. + +`zeroPaddedDate`:: + (ERROR) Found a zero padded date in an author/commiter line. + +`zeroPaddedFilemode`:: + (WARN) Found a zero padded filemode in a tree. diff --git a/Documentation/git-fsck.txt b/Documentation/git-fsck.txt index 29318ea957..b6a0f8a085 100644 --- a/Documentation/git-fsck.txt +++ b/Documentation/git-fsck.txt @@ -152,6 +152,18 @@ hash mismatch <object>:: object database value. This indicates a serious data integrity problem. + +FSCK MESSAGES +------------- + +The following lists the types of errors `git fsck` detects and what +each error means, with their default severity. The severity of the +error, other than those that are marked as "(FATAL)", can be tweaked +by setting the corresponding `fsck.<msg-id>` configuration variable. + +include::fsck-msgids.txt[] + + Environment Variables --------------------- diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt index d7986419c2..440043cdb8 100644 --- a/Documentation/git-ls-files.txt +++ b/Documentation/git-ls-files.txt @@ -10,8 +10,8 @@ SYNOPSIS -------- [verse] 'git ls-files' [-z] [-t] [-v] [-f] - [-c|--cached] [-d|--deleted] [-o|--others] [-i|--|ignored] - [-s|--stage] [-u|--unmerged] [-k|--|killed] [-m|--modified] + [-c|--cached] [-d|--deleted] [-o|--others] [-i|--ignored] + [-s|--stage] [-u|--unmerged] [-k|--killed] [-m|--modified] [--directory [--no-empty-directory]] [--eol] [--deduplicate] [-x <pattern>|--exclude=<pattern>] diff --git a/Documentation/git-merge-tree.txt b/Documentation/git-merge-tree.txt index d6c356740e..04bcc416e6 100644 --- a/Documentation/git-merge-tree.txt +++ b/Documentation/git-merge-tree.txt @@ -81,6 +81,31 @@ Whereas for a conflicted merge, the output is by default of the form: These are discussed individually below. +However, there is an exception. If `--stdin` is passed, then there is +an extra section at the beginning, a NUL character at the end, and then +all the sections repeat for each line of input. Thus, if the first merge +is conflicted and the second is clean, the output would be of the form: + + <Merge status> + <OID of toplevel tree> + <Conflicted file info> + <Informational messages> + NUL + <Merge status> + <OID of toplevel tree> + NUL + +[[MS]] +Merge status +~~~~~~~~~~~~ + +This is an integer status followed by a NUL character. The integer status is: + + 0: merge had conflicts + 1: merge was clean + <0: something prevented the merge from running (e.g. access to repository + objects denied by filesystem) + [[OIDTLT]] OID of toplevel tree ~~~~~~~~~~~~~~~~~~~~ @@ -108,18 +133,50 @@ character instead of a newline character. Informational messages ~~~~~~~~~~~~~~~~~~~~~~ -This always starts with a blank line (or NUL if `-z` is passed) to -separate it from the previous sections, and then has free-form -messages about the merge, such as: +This section provides informational messages, typically about +conflicts. The format of the section varies significantly depending +on whether `-z` is passed. + +If `-z` is passed: + +The output format is zero or more conflict informational records, each +of the form: + + <list-of-paths><conflict-type>NUL<conflict-message>NUL + +where <list-of-paths> is of the form + + <number-of-paths>NUL<path1>NUL<path2>NUL...<pathN>NUL + +and includes paths (or branch names) affected by the conflict or +informational message in <conflict-message>. Also, <conflict-type> is a +stable string explaining the type of conflict, such as + + * "Auto-merging" + * "CONFLICT (rename/delete)" + * "CONFLICT (submodule lacks merge base)" + * "CONFLICT (binary)" + +and <conflict-message> is a more detailed message about the conflict which often +(but not always) embeds the <stable-short-type-description> within it. These +strings may change in future Git versions. Some examples: * "Auto-merging <file>" * "CONFLICT (rename/delete): <oldfile> renamed...but deleted in..." - * "Failed to merge submodule <submodule> (<reason>)" + * "Failed to merge submodule <submodule> (no merge base)" * "Warning: cannot merge binary files: <filename>" -Note that these free-form messages will never have a NUL character -in or between them, even if -z is passed. It is simply a large block -of text taking up the remainder of the output. +If `-z` is NOT passed: + +This section starts with a blank line to separate it from the previous +sections, and then only contains the <conflict-message> information +from the previous section (separated by newlines). These are +non-stable strings that should not be parsed by scripts, and are just +meant for human consumption. Also, note that while <conflict-message> +strings usually do not contain embedded newlines, they sometimes do. +(However, the free-form messages will never have an embedded NUL +character). So, the entire block of information is meant for human +readers as an agglomeration of all conflict messages. EXIT STATUS ----------- @@ -127,7 +184,10 @@ EXIT STATUS For a successful, non-conflicted merge, the exit status is 0. When the merge has conflicts, the exit status is 1. If the merge is not able to complete (or start) due to some kind of error, the exit status is -something other than 0 or 1 (and the output is unspecified). +something other than 0 or 1 (and the output is unspecified). When +--stdin is passed, the return status is 0 for both successful and +conflicted merges, and something other than 0 or 1 if it cannot complete +all the requested merges. USAGE NOTES ----------- diff --git a/Documentation/git-pack-redundant.txt b/Documentation/git-pack-redundant.txt index dda80a740c..99ef13839d 100644 --- a/Documentation/git-pack-redundant.txt +++ b/Documentation/git-pack-redundant.txt @@ -34,7 +34,7 @@ OPTIONS --alt-odb:: Don't require objects present in packs from alternate object - directories to be present in local packs. + database (odb) directories to be present in local packs. --verbose:: Outputs some statistics to stderr. Has a small performance penalty. diff --git a/Documentation/git-patch-id.txt b/Documentation/git-patch-id.txt index 442caff8a9..1d15fa45d5 100644 --- a/Documentation/git-patch-id.txt +++ b/Documentation/git-patch-id.txt @@ -8,18 +8,18 @@ git-patch-id - Compute unique ID for a patch SYNOPSIS -------- [verse] -'git patch-id' [--stable | --unstable] +'git patch-id' [--stable | --unstable | --verbatim] DESCRIPTION ----------- Read a patch from the standard input and compute the patch ID for it. A "patch ID" is nothing but a sum of SHA-1 of the file diffs associated with a -patch, with whitespace and line numbers ignored. As such, it's "reasonably -stable", but at the same time also reasonably unique, i.e., two patches that -have the same "patch ID" are almost guaranteed to be the same thing. +patch, with line numbers ignored. As such, it's "reasonably stable", but at +the same time also reasonably unique, i.e., two patches that have the same +"patch ID" are almost guaranteed to be the same thing. -IOW, you can use this thing to look for likely duplicate commits. +The main usecase for this command is to look for likely duplicate commits. When dealing with 'git diff-tree' output, it takes advantage of the fact that the patch is prefixed with the object name of the @@ -30,6 +30,12 @@ This can be used to make a mapping from patch ID to commit ID. OPTIONS ------- +--verbatim:: + Calculate the patch-id of the input as it is given, do not strip + any whitespace. + + This is the default if patchid.verbatim is true. + --stable:: Use a "stable" sum of hashes as the patch ID. With this option: - Reordering file diffs that make up a patch does not affect the ID. @@ -45,14 +51,16 @@ OPTIONS of "-O<orderfile>", thereby making existing databases storing such "unstable" or historical patch-ids unusable. + - All whitespace within the patch is ignored and does not affect the id. + This is the default if patchid.stable is set to true. --unstable:: Use an "unstable" hash as the patch ID. With this option, the result produced is compatible with the patch-id value produced - by git 1.9 and older. Users with pre-existing databases storing - patch-ids produced by git 1.9 and older (who do not deal with reordered - patches) may want to use this option. + by git 1.9 and older and whitespace is ignored. Users with pre-existing + databases storing patch-ids produced by git 1.9 and older (who do not deal + with reordered patches) may want to use this option. This is the default. diff --git a/Documentation/git-rebase.txt b/Documentation/git-rebase.txt index 9cb8931c7a..f9675bd24e 100644 --- a/Documentation/git-rebase.txt +++ b/Documentation/git-rebase.txt @@ -218,12 +218,14 @@ leave out at most one of A and B, in which case it defaults to HEAD. merge base of `<upstream>` and `<branch>`. Running `git rebase --keep-base <upstream> <branch>` is equivalent to running - `git rebase --onto <upstream>...<branch> <upstream> <branch>`. + `git rebase --reapply-cherry-picks --no-fork-point --onto <upstream>...<branch> <upstream> <branch>`. + This option is useful in the case where one is developing a feature on top of an upstream branch. While the feature is being worked on, the upstream branch may advance and it may not be the best idea to keep -rebasing on top of the upstream but to keep the base commit as-is. +rebasing on top of the upstream but to keep the base commit as-is. As +the base commit is unchanged this option implies `--reapply-cherry-picks` +to avoid losing commits. + Although both this option and `--fork-point` find the merge base between `<upstream>` and `<branch>`, this option uses the merge base as the _starting @@ -278,7 +280,8 @@ See also INCOMPATIBLE OPTIONS below. Note that commits which start empty are kept (unless `--no-keep-empty` is specified), and commits which are clean cherry-picks (as determined by `git log --cherry-mark ...`) are detected and dropped as a -preliminary step (unless `--reapply-cherry-picks` is passed). +preliminary step (unless `--reapply-cherry-picks` or `--keep-base` is +passed). + See also INCOMPATIBLE OPTIONS below. @@ -311,13 +314,16 @@ See also INCOMPATIBLE OPTIONS below. upstream changes, the behavior towards them is controlled by the `--empty` flag.) + -By default (or if `--no-reapply-cherry-picks` is given), these commits -will be automatically dropped. Because this necessitates reading all -upstream commits, this can be expensive in repos with a large number -of upstream commits that need to be read. When using the 'merge' -backend, warnings will be issued for each dropped commit (unless -`--quiet` is given). Advice will also be issued unless -`advice.skippedCherryPicks` is set to false (see linkgit:git-config[1]). + +In the absence of `--keep-base` (or if `--no-reapply-cherry-picks` is +given), these commits will be automatically dropped. Because this +necessitates reading all upstream commits, this can be expensive in +repositories with a large number of upstream commits that need to be +read. When using the 'merge' backend, warnings will be issued for each +dropped commit (unless `--quiet` is given). Advice will also be issued +unless `advice.skippedCherryPicks` is set to false (see +linkgit:git-config[1]). + + `--reapply-cherry-picks` allows rebase to forgo reading all upstream commits, potentially improving performance. @@ -443,9 +449,9 @@ When `--fork-point` is active, 'fork_point' will be used instead of <branch>` command (see linkgit:git-merge-base[1]). If 'fork_point' ends up being empty, the `<upstream>` will be used as a fallback. + -If `<upstream>` is given on the command line, then the default is -`--no-fork-point`, otherwise the default is `--fork-point`. See also -`rebase.forkpoint` in linkgit:git-config[1]. +If `<upstream>` or `--keep-base` is given on the command line, then +the default is `--no-fork-point`, otherwise the default is +`--fork-point`. See also `rebase.forkpoint` in linkgit:git-config[1]. + If your branch was based on `<upstream>` but `<upstream>` was rewound and your branch contains commits which were dropped, this option can be used diff --git a/Documentation/git-send-email.txt b/Documentation/git-send-email.txt index 3290043053..765b2df853 100644 --- a/Documentation/git-send-email.txt +++ b/Documentation/git-send-email.txt @@ -178,9 +178,18 @@ Sending for `sendmail` in `/usr/sbin`, `/usr/lib` and $PATH. --smtp-encryption=<encryption>:: - Specify the encryption to use, either 'ssl' or 'tls'. Any other - value reverts to plain SMTP. Default is the value of - `sendemail.smtpEncryption`. + Specify in what way encrypting begins for the SMTP connection. + Valid values are 'ssl' and 'tls'. Any other value reverts to plain + (unencrypted) SMTP, which defaults to port 25. + Despite the names, both values will use the same newer version of TLS, + but for historic reasons have these names. 'ssl' refers to "implicit" + encryption (sometimes called SMTPS), that uses port 465 by default. + 'tls' refers to "explicit" encryption (often known as STARTTLS), + that uses port 25 by default. Other ports might be used by the SMTP + server, which are not the default. Commonly found alternative port for + 'tls' and unencrypted is 587. You need to check your provider's + documentation or your server configuration to make sure + for your own case. Default is the value of `sendemail.smtpEncryption`. --smtp-domain=<FQDN>:: Specifies the Fully Qualified Domain Name (FQDN) used in the diff --git a/Documentation/git-shortlog.txt b/Documentation/git-shortlog.txt index f64e77047b..7d0277d033 100644 --- a/Documentation/git-shortlog.txt +++ b/Documentation/git-shortlog.txt @@ -47,6 +47,11 @@ OPTIONS Each pretty-printed commit will be rewrapped before it is shown. +--date=<format>:: + Show dates formatted according to the given date string. (See + the `--date` option in the "Commit Formatting" section of + linkgit:git-log[1]). Useful with `--group=format:<format>`. + --group=<type>:: Group commits based on `<type>`. If no `--group` option is specified, the default is `author`. `<type>` is one of: @@ -59,6 +64,9 @@ OPTIONS example, if your project uses `Reviewed-by` trailers, you might want to see who has been reviewing with `git shortlog -ns --group=trailer:reviewed-by`. + - `format:<format>`, any string accepted by the `--format` option of + 'git log'. (See the "PRETTY FORMATS" section of + linkgit:git-log[1].) + Note that commits that do not include the trailer will not be counted. Likewise, commits with multiple trailers (e.g., multiple signoffs) may diff --git a/Documentation/gitformat-commit-graph.txt b/Documentation/gitformat-commit-graph.txt index 7324665716..31cad585e2 100644 --- a/Documentation/gitformat-commit-graph.txt +++ b/Documentation/gitformat-commit-graph.txt @@ -3,7 +3,7 @@ gitformat-commit-graph(5) NAME ---- -gitformat-commit-graph - Git commit graph format +gitformat-commit-graph - Git commit-graph format SYNOPSIS -------- @@ -14,7 +14,7 @@ $GIT_DIR/objects/info/commit-graphs/* DESCRIPTION ----------- -The Git commit graph stores a list of commit OIDs and some associated +The Git commit-graph stores a list of commit OIDs and some associated metadata, including: - The generation number of the commit. @@ -34,7 +34,7 @@ corresponding to the array position within the list of commit OIDs. Due to some special constants we use to track parents, we can store at most (1 << 30) + (1 << 29) + (1 << 28) - 1 (around 1.8 billion) commits. -== Commit graph files have the following format: +== Commit-graph files have the following format: In order to allow extensions that add extra data to the graph, we organize the body into "chunks" and provide a binary lookup table at the beginning diff --git a/Documentation/glossary-content.txt b/Documentation/glossary-content.txt index aa2f41f5e7..5a537268e2 100644 --- a/Documentation/glossary-content.txt +++ b/Documentation/glossary-content.txt @@ -20,7 +20,7 @@ [[def_branch]]branch:: A "branch" is a line of development. The most recent <<def_commit,commit>> on a branch is referred to as the tip of - that branch. The tip of the branch is referenced by a branch + that branch. The tip of the branch is <<def_ref,referenced>> by a branch <<def_head,head>>, which moves forward as additional development is done on the branch. A single Git <<def_repository,repository>> can track an arbitrary number of @@ -75,6 +75,21 @@ state in the Git history, by creating a new commit representing the current state of the <<def_index,index>> and advancing <<def_HEAD,HEAD>> to point at the new commit. +[[def_commit_graph_general]]commit graph concept, representations and usage:: + A synonym for the <<def_DAG,DAG>> structure formed by the commits + in the object database, <<def_ref,referenced>> by branch tips, + using their <<def_chain,chain>> of linked commits. + This structure is the definitive commit graph. The + graph can be represented in other ways, e.g. the + <<def_commit_graph_file,"commit-graph" file>>. + +[[def_commit_graph_file]]commit-graph file:: + The "commit-graph" (normally hyphenated) file is a supplemental + representation of the <<def_commit_graph_general,commit graph>> + which accelerates commit graph walks. The "commit-graph" file is + stored either in the .git/objects/info directory or in the info + directory of an alternate object database. + [[def_commit_object]]commit object:: An <<def_object,object>> which contains the information about a particular <<def_revision,revision>>, such as <<def_parent,parents>>, committer, @@ -262,7 +277,7 @@ This commit is referred to as a "merge commit", or sometimes just a identified by its <<def_object_name,object name>>. The objects usually live in `$GIT_DIR/objects/`. -[[def_object_identifier]]object identifier:: +[[def_object_identifier]]object identifier (oid):: Synonym for <<def_object_name,object name>>. [[def_object_name]]object name:: @@ -493,6 +508,14 @@ exclude;; <<def_tree_object,trees>> to the trees or <<def_blob_object,blobs>> that they contain. +[[def_reachability_bitmap]]reachability bitmaps:: + Reachability bitmaps store information about the + <<def_reachable,reachability>> of a selected set of commits in + a packfile, or a multi-pack index (MIDX), to speed up object search. + The bitmaps are stored in a ".bitmap" file. A repository may have at + most one bitmap file in use. The bitmap file may belong to either one + pack, or the repository's multi-pack index (if it exists). + [[def_rebase]]rebase:: To reapply a series of changes from a <<def_branch,branch>> to a different base, and reset the <<def_head,head>> of that branch diff --git a/Documentation/howto/coordinate-embargoed-releases.txt b/Documentation/howto/coordinate-embargoed-releases.txt index 601aae88e9..e653775bab 100644 --- a/Documentation/howto/coordinate-embargoed-releases.txt +++ b/Documentation/howto/coordinate-embargoed-releases.txt @@ -1,9 +1,10 @@ Content-type: text/asciidoc -Abstract: When a critical vulnerability is discovered and fixed, we follow this - script to coordinate a public release. +Abstract: When a vulnerability is reported, we follow these guidelines to + assess the vulnerability, create and review a fix, and coordinate embargoed + security releases. How we coordinate embargoed releases -==================================== +------------------------------------ To protect Git users from critical vulnerabilities, we do not just release fixed versions like regular maintenance releases. Instead, we coordinate @@ -11,33 +12,147 @@ releases with packagers, keeping the fixes under an embargo until the release date. That way, users will have a chance to upgrade on that date, no matter what Operating System or distribution they run. -Open a Security Advisory draft ------------------------------- +The `git-security` mailing list +------------------------------- + +Responsible disclosures of vulnerabilities, analysis, proposed fixes as +well as the orchestration of coordinated embargoed releases all happen on the +`git-security` mailing list at <git-security@googlegroups.com>. + +In this context, the term "embargo" refers to the time period that information +about a vulnerability is kept under wraps and only shared on a need-to-know +basis. This is necessary to protect Git's users from bad actors who would +otherwise be made aware of attack vectors that could be exploited. "Lifting the +embargo" refers to publishing the version that fixes the vulnerabilities. + +Audience of the `git-security` mailing list +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Anybody may contact the `git-security` mailing list by sending an email +to <git-security@googlegroups.com>, though the archive is closed to the +public and only accessible to subscribed members. + +There are a few dozen subscribed members: core Git developers who are trusted +with addressing vulnerabilities, and stakeholders (i.e. owners of products +affected by security vulnerabilities in Git). + +Most of the discussions revolve around assessing the severity of the reported +issue (including the decision whether the report is security-relevant or can be +redirected to the public mailing list), how to remediate the issue, determining +the timeline of the disclosure as well as aligning priorities and +requirements. -The first step is to https://github.com/git/git/security/advisories/new[open an -advisory]. Technically, it is not necessary, but it is convenient and saves a -bit of hassle. This advisory can also be used to obtain the CVE number and it -will give us a private fork associated with it that can be used to collaborate -on a fix. +Communications +~~~~~~~~~~~~~~ -Release date of the embargoed version -------------------------------------- +If you are a stakeholder, it is a good idea to pay close attention to the +discussions, as pertinent information may be buried in the middle of a lively +conversation that might not look relevant to your interests. For example, the +tentative timeline might be agreed upon in the middle of discussing code +comment formatting in one of the patches and whether or not to combine fixes +for multiple, separate vulnerabilities into the same embargoed release. Most +mail threads are not usually structured specifically to communicate +agreements, assessments or timelines. -If the vulnerability affects Windows users, we want to have our friends over at -Visual Studio on board. This means we need to target a "Patch Tuesday" (i.e. a -second Tuesday of the month), at the minimum three weeks from heads-up to -coordinated release. +Typical timeline +---------------- -If the vulnerability affects the server side, or can benefit from scans on the -server side (i.e. if `git fsck` can detect an attack), it is important to give -all involved Git repository hosting sites enough time to scan all of those -repositories. +- A potential vulnerability is reported to the `git-security` mailing list. + +- The members of the git-security list start a discussion to give an initial + assessment of the severity of the reported potential vulnerability. + We aspire to do so within a few days. + +- After discussion, if consensus is reached that it is not critical enough + to warrant any embargo, the reporter is redirected to the public Git mailing + list. This ends the reporter's interaction with the `git-security` list. + +- If it is deemed critical enough for an embargo, ideas are presented on how to + address the vulnerability. + +- Usually around that time, the Git maintainer or their delegate(s) open a draft + security advisory in the `git/git` repository on GitHub (see below for more + details). + +- Code review can take place in a variety of different locations, + depending on context. These are: patches sent inline on the git-security list, + a private fork on GitHub associated with the draft security advisory, or the + git/cabal repository. + +- Contributors working on a fix should consider beginning by sending + patches to the git-security list (inline with the original thread), since they + are accessible to all subscribers, along with the original reporter. + +- Once the review has settled and everyone involved in the review agrees that + the patches are nearing the finish line, the Git maintainer, and others + determine a release date as well as the release trains that are serviced. The + decision regarding which versions need a backported fix is based on input from + the reporter, the contributor who worked on the patches, and from + stakeholders. Operators of hosting sites who may want to analyze whether the + given issue is exploited via any of the repositories they host, and binary + packagers who want to make sure their product gets patched adequately against + the vulnerability, for example, may want to give their input at this stage. + +- While the Git community does its best to accommodate the specific timeline + requests of the various binary packagers, the nature of the issue may preclude + a prolonged release schedule. For fixes deemed urgent, it may be in the best + interest of the Git users community to shorten the disclosure and release + timeline, and packagers may need to adapt accordingly. + +- Subsequently, branches with the fixes are pushed to the git/cabal repository. + +- The tags are created by the Git maintainer and pushed to the same repository. + +- The Git for Windows, Git for macOS, BSD, Debian, etc. maintainers prepare the + corresponding release artifacts, based on the tags created that have been + prepared by the Git maintainer. + +- The release artifacts prepared by various binary packagers can be + made available to stakeholders under embargo via a mail to the + `git-security` list. + +- Less than a week before the release, a mail with the relevant information is + sent to <distros@vs.openwall.org> (see below), a list used to pre-announce + embargoed releases of open source projects to the stakeholders of all major + distributions of Linux as well as other OSes. + +- Public communication is then prepared in advance of the release date. This + includes blog posts and mails to the Git and Git for Windows mailing lists. + +- On the day of the release, at around 10am Pacific Time, the Git maintainer + pushes the tag and the `master` branch to the public repository, then sends + out an announcement mail. + +- Once the tag is pushed, the Git for Windows maintainer publishes the + corresponding tag and creates a GitHub Release with the associated release + artifacts (Git for Windows installer, Portable Git, MinGit, etc). + +- Git for Windows release is then announced via a mail to the public Git and + Git for Windows mailing lists as well as via a tweet. + +- Ditto for distribution packagers for Linux and other platforms: + their releases are announced via their preferred channels. + +- A mail to <oss-security@lists.openwall.org> (see below for details) is sent + as a follow-up to the <distros@vs.openwall.org> one, describing the + vulnerability in detail, often including a proof of concept of an exploit. + +Note: The Git project makes no guarantees about timelines, but aims to keep +embargoes reasonably short in the interest of keeping Git's users safe. + +Opening a Security Advisory draft +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The first step is to https://github.com/git/git/security/advisories/new[open +an advisory]. Technically, this is not necessary. However, it is the most +convenient way to obtain the CVE number and it give us a private repository +associated with it that can be used to collaborate on a fix. Notifying the Linux distributions ---------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ At most two weeks before release date, we need to send a notification to -distros@vs.openwall.org, preferably less than 7 days before the release date. +<distros@vs.openwall.org>, preferably less than 7 days before the release date. This will reach most (all?) Linux distributions. See an example below, and the guidelines for this mailing list at https://oss-security.openwall.org/wiki/mailing-lists/distros#how-to-use-the-lists[here]. @@ -65,7 +180,7 @@ created using a command like this: tar cJvf cve-xxx.bundle.tar.xz cve-xxx.bundle Example mail to distros@vs.openwall.org ---------------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .... To: distros@vs.openwall.org @@ -101,7 +216,7 @@ Thanks, .... Example mail to oss-security@lists.openwall.com ------------------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .... To: oss-security@lists.openwall.com @@ -128,4 +243,4 @@ it goes to <developer>. Thanks, <name> -.... +....
\ No newline at end of file diff --git a/Documentation/howto/maintain-git.txt b/Documentation/howto/maintain-git.txt index a67130debb..215e2edb0f 100644 --- a/Documentation/howto/maintain-git.txt +++ b/Documentation/howto/maintain-git.txt @@ -256,7 +256,7 @@ by doing the following: merged to 'next', add it at the end of the list. Then: $ git checkout -B jch master - $ Meta/redo-jch.sh -c1 + $ sh Meta/redo-jch.sh -c1 to rebuild the 'jch' branch from scratch. "-c1" tells the script to stop merging at the first line that begins with '###' diff --git a/Documentation/lint-fsck-msgids.perl b/Documentation/lint-fsck-msgids.perl new file mode 100755 index 0000000000..1233ffe815 --- /dev/null +++ b/Documentation/lint-fsck-msgids.perl @@ -0,0 +1,70 @@ +#!/usr/bin/perl + +my ($fsck_h, $fsck_msgids_txt, $okfile) = @ARGV; + +my (%in_fsck_h, $fh, $bad); + +open($fh, "<", "$fsck_h") or die; +while (<$fh>) { + if (/^\s+FUNC\(([0-9A-Z_]+), ([A-Z]+)\)/) { + my ($name, $severity) = ($1, $2); + my ($first) = 1; + $name = join('', + map { + y/A-Z/a-z/; + if (!$first) { + s/^(.)/uc($1)/e; + } else { + $first = 0; + } + $_; + } + split(/_/, $name)); + $in_fsck_h{$name} = $severity; + } +} +close($fh); + +open($fh, "<", "$fsck_msgids_txt") or die; +my ($previous, $current); +while (<$fh>) { + if (!defined $current) { + if (/^\`([a-zA-Z0-9]*)\`::/) { + $current = $1; + if ((defined $previous) && + ($current le $previous)) { + print STDERR "$previous >= $current in doc\n"; + $bad = 1; + } + } + } elsif (/^\s+\(([A-Z]+)\) /) { + my ($level) = $1; + if (!exists $in_fsck_h{$current}) { + print STDERR "$current does not exist in fsck.h\n"; + $bad = 1; + } elsif ($in_fsck_h{$current} eq "") { + print STDERR "$current defined twice\n"; + $bad = 1; + } elsif ($in_fsck_h{$current} ne $level) { + print STDERR "$current severity $level != $in_fsck_h{$current}\n"; + $bad = 1; + } + $previous = $current; + $in_fsck_h{$current} = ""; # mark as seen. + undef $current; + } +} +close($fh); + +for my $key (keys %in_fsck_h) { + if ($in_fsck_h{$key} ne "") { + print STDERR "$key not explained in doc.\n"; + $bad = 1; + } +} + +die if ($bad); + +open($fh, ">", "$okfile"); +print $fh "good\n"; +close($fh); diff --git a/Documentation/technical/api-trace2.txt b/Documentation/technical/api-trace2.txt index 2afa28bb5a..de5fc25059 100644 --- a/Documentation/technical/api-trace2.txt +++ b/Documentation/technical/api-trace2.txt @@ -148,20 +148,18 @@ filename collisions). == Trace2 API -All public Trace2 functions and macros are defined in `trace2.h` and -`trace2.c`. All public symbols are prefixed with `trace2_`. +The Trace2 public API is defined and documented in `trace2.h`; refer to it for +more information. All public functions and macros are prefixed +with `trace2_` and are implemented in `trace2.c`. There are no public Trace2 data structures. The Trace2 code also defines a set of private functions and data types in the `trace2/` directory. These symbols are prefixed with `tr2_` -and should only be used by functions in `trace2.c`. +and should only be used by functions in `trace2.c` (or other private +source files in `trace2/`). -== Conventions for Public Functions and Macros - -The functions defined by the Trace2 API are declared and documented -in `trace2.h`. It defines the API functions and wrapper macros for -Trace2. +=== Conventions for Public Functions and Macros Some functions have a `_fl()` suffix to indicate that they take `file` and `line-number` arguments. @@ -172,52 +170,7 @@ take a `va_list` argument. Some functions have a `_printf_fl()` suffix to indicate that they also take a `printf()` style format with a variable number of arguments. -There are CPP wrapper macros and `#ifdef`s to hide most of these details. -See `trace2.h` for more details. The following discussion will only -describe the simplified forms. - -== Public API - -All Trace2 API functions send a message to all of the active -Trace2 Targets. This section describes the set of available -messages. - -It helps to divide these functions into groups for discussion -purposes. - -=== Basic Command Messages - -These are concerned with the lifetime of the overall git process. -e.g: `void trace2_initialize_clock()`, `void trace2_initialize()`, -`int trace2_is_enabled()`, `void trace2_cmd_start(int argc, const char **argv)`. - -=== Command Detail Messages - -These are concerned with describing the specific Git command -after the command line, config, and environment are inspected. -e.g: `void trace2_cmd_name(const char *name)`, -`void trace2_cmd_mode(const char *mode)`. - -=== Child Process Messages - -These are concerned with the various spawned child processes, -including shell scripts, git commands, editors, pagers, and hooks. - -e.g: `void trace2_child_start(struct child_process *cmd)`. - -=== Git Thread Messages - -These messages are concerned with Git thread usage. - -e.g: `void trace2_thread_start(const char *thread_name)`. - -=== Region and Data Messages - -These are concerned with recording performance data -over regions or spans of code. e.g: -`void trace2_region_enter(const char *category, const char *label, const struct repository *repo)`. - -Refer to trace2.h for details about all trace2 functions. +CPP wrapper macros are defined to hide most of these details. == Trace2 Target Formats @@ -685,8 +638,8 @@ The "exec_id" field is a command-unique id and is only useful if the `"thread_start"`:: This event is generated when a thread is started. It is - generated from *within* the new thread's thread-proc (for TLS - reasons). + generated from *within* the new thread's thread-proc (because + it needs to access data in the thread's thread-local storage). + ------------ { @@ -698,7 +651,7 @@ The "exec_id" field is a command-unique id and is only useful if the `"thread_exit"`:: This event is generated when a thread exits. It is generated - from *within* the thread's thread-proc (for TLS reasons). + from *within* the thread's thread-proc. + ------------ { @@ -816,6 +769,73 @@ The "value" field may be an integer or a string. } ------------ +`"th_timer"`:: + This event logs the amount of time that a stopwatch timer was + running in the thread. This event is generated when a thread + exits for timers that requested per-thread events. ++ +------------ +{ + "event":"th_timer", + ... + "category":"my_category", + "name":"my_timer", + "intervals":5, # number of time it was started/stopped + "t_total":0.052741, # total time in seconds it was running + "t_min":0.010061, # shortest interval + "t_max":0.011648 # longest interval +} +------------ + +`"timer"`:: + This event logs the amount of time that a stopwatch timer was + running aggregated across all threads. This event is generated + when the process exits. ++ +------------ +{ + "event":"timer", + ... + "category":"my_category", + "name":"my_timer", + "intervals":5, # number of time it was started/stopped + "t_total":0.052741, # total time in seconds it was running + "t_min":0.010061, # shortest interval + "t_max":0.011648 # longest interval +} +------------ + +`"th_counter"`:: + This event logs the value of a counter variable in a thread. + This event is generated when a thread exits for counters that + requested per-thread events. ++ +------------ +{ + "event":"th_counter", + ... + "category":"my_category", + "name":"my_counter", + "count":23 +} +------------ + +`"counter"`:: + This event logs the value of a counter variable across all threads. + This event is generated when the process exits. The total value + reported here is the sum across all threads. ++ +------------ +{ + "event":"counter", + ... + "category":"my_category", + "name":"my_counter", + "count":23 +} +------------ + + == Example Trace2 API Usage Here is a hypothetical usage of the Trace2 API showing the intended @@ -1206,7 +1226,7 @@ worked on 508 items at offset 2032. Thread "th04" worked on 508 items at offset 508. + This example also shows that thread names are assigned in a racy manner -as each thread starts and allocates TLS storage. +as each thread starts. Config (def param) Events:: @@ -1247,6 +1267,60 @@ d0 | main | data | r0 | 0.002126 | 0.002126 | fsy d0 | main | exit | | 0.000470 | | | code:0 d0 | main | atexit | | 0.000477 | | | code:0 ---------------- + +Stopwatch Timer Events:: + + Measure the time spent in a function call or span of code + that might be called from many places within the code + throughout the life of the process. ++ +---------------- +static void expensive_function(void) +{ + trace2_timer_start(TRACE2_TIMER_ID_TEST1); + ... + sleep_millisec(1000); // Do something expensive + ... + trace2_timer_stop(TRACE2_TIMER_ID_TEST1); +} + +static int ut_100timer(int argc, const char **argv) +{ + ... + + expensive_function(); + + // Do something else 1... + + expensive_function(); + + // Do something else 2... + + expensive_function(); + + return 0; +} +---------------- ++ +In this example, we measure the total time spent in +`expensive_function()` regardless of when it is called +in the overall flow of the program. ++ +---------------- +$ export GIT_TRACE2_PERF_BRIEF=1 +$ export GIT_TRACE2_PERF=~/log.perf +$ t/helper/test-tool trace2 100timer 3 1000 +... +$ cat ~/log.perf +d0 | main | version | | | | | ... +d0 | main | start | | 0.001453 | | | t/helper/test-tool trace2 100timer 3 1000 +d0 | main | cmd_name | | | | | trace2 (trace2) +d0 | main | exit | | 3.003667 | | | code:0 +d0 | main | timer | | | | test | name:test1 intervals:3 total:3.001686 min:1.000254 max:1.000929 +d0 | main | atexit | | 3.003796 | | | code:0 +---------------- + + == Future Work === Relationship to the Existing Trace Api (api-trace.txt) diff --git a/Documentation/technical/commit-graph.txt b/Documentation/technical/commit-graph.txt index 90c9760c23..86fed0de0f 100644 --- a/Documentation/technical/commit-graph.txt +++ b/Documentation/technical/commit-graph.txt @@ -1,4 +1,4 @@ -Git Commit Graph Design Notes +Git Commit-Graph Design Notes ============================= Git walks the commit graph for many reasons, including: @@ -17,7 +17,7 @@ There are two main costs here: The commit-graph file is a supplemental data structure that accelerates commit graph walks. If a user downgrades or disables the 'core.commitGraph' -config setting, then the existing ODB is sufficient. The file is stored +config setting, then the existing object database is sufficient. The file is stored as "commit-graph" either in the .git/objects/info directory or in the info directory of an alternate. @@ -95,7 +95,7 @@ with default order), but is not used when the topological order is required (such as merge base calculations, "git log --graph"). In practice, we expect some commits to be created recently and not stored -in the commit graph. We can treat these commits as having "infinite" +in the commit-graph. We can treat these commits as having "infinite" generation number and walk until reaching commits with known generation number. @@ -149,7 +149,7 @@ Design Details helpful for these clones, anyway. The commit-graph will not be read or written when shallow commits are present. -Commit Graphs Chains +Commit-Graphs Chains -------------------- Typically, repos grow with near-constant velocity (commits per day). Over time, diff --git a/Documentation/technical/parallel-checkout.txt b/Documentation/technical/parallel-checkout.txt index e790258a1a..47c9b6183c 100644 --- a/Documentation/technical/parallel-checkout.txt +++ b/Documentation/technical/parallel-checkout.txt @@ -56,7 +56,7 @@ Rejected Multi-Threaded Solution The most "straightforward" implementation would be to spread the set of to-be-updated cache entries across multiple threads. But due to the -thread-unsafe functions in the ODB code, we would have to use locks to +thread-unsafe functions in the object database code, we would have to use locks to coordinate the parallel operation. An early prototype of this solution showed that the multi-threaded checkout would bring performance improvements over the sequential code, but there was still too much lock @@ -722,6 +722,7 @@ PROGRAMS += $(patsubst %.o,git-%$X,$(PROGRAM_OBJS)) TEST_BUILTINS_OBJS += test-advise.o TEST_BUILTINS_OBJS += test-bitmap.o TEST_BUILTINS_OBJS += test-bloom.o +TEST_BUILTINS_OBJS += test-bundle-uri.o TEST_BUILTINS_OBJS += test-chmtime.o TEST_BUILTINS_OBJS += test-config.o TEST_BUILTINS_OBJS += test-crontab.o @@ -1095,6 +1096,7 @@ LIB_OBJS += trace.o LIB_OBJS += trace2.o LIB_OBJS += trace2/tr2_cfg.o LIB_OBJS += trace2/tr2_cmd_name.o +LIB_OBJS += trace2/tr2_ctr.o LIB_OBJS += trace2/tr2_dst.o LIB_OBJS += trace2/tr2_sid.o LIB_OBJS += trace2/tr2_sysenv.o @@ -1103,6 +1105,7 @@ LIB_OBJS += trace2/tr2_tgt_event.o LIB_OBJS += trace2/tr2_tgt_normal.o LIB_OBJS += trace2/tr2_tgt_perf.o LIB_OBJS += trace2/tr2_tls.o +LIB_OBJS += trace2/tr2_tmr.o LIB_OBJS += trailer.o LIB_OBJS += transport-helper.o LIB_OBJS += transport.o @@ -386,9 +386,19 @@ static void say_patch_name(FILE *output, const char *fmt, struct patch *patch) #define SLOP (16) +/* + * apply.c isn't equipped to handle arbitrarily large patches, because + * it intermingles `unsigned long` with `int` for the type used to store + * buffer lengths. + * + * Only process patches that are just shy of 1 GiB large in order to + * avoid any truncation or overflow issues. + */ +#define MAX_APPLY_SIZE (1024UL * 1024 * 1023) + static int read_patch_file(struct strbuf *sb, int fd) { - if (strbuf_read(sb, fd, 0) < 0) + if (strbuf_read(sb, fd, 0) < 0 || sb->len >= MAX_APPLY_SIZE) return error_errno("git apply: failed to read"); /* diff --git a/builtin/branch.c b/builtin/branch.c index 407517ba68..15be0c03ef 100644 --- a/builtin/branch.c +++ b/builtin/branch.c @@ -520,13 +520,6 @@ static void copy_or_rename_branch(const char *oldname, const char *newname, int const char *interpreted_newname = NULL; int recovery = 0; - if (!oldname) { - if (copy) - die(_("cannot copy the current branch while not on any.")); - else - die(_("cannot rename the current branch while not on any.")); - } - if (strbuf_check_branch_ref(&oldref, oldname)) { /* * Bad name --- this could be an attempt to rename a @@ -816,7 +809,7 @@ int cmd_branch(int argc, const char **argv, const char *prefix) strbuf_addf(&branch_ref, "refs/heads/%s", branch_name); if (!ref_exists(branch_ref.buf)) - ret = error((!argc || !strcmp(head, branch_name)) + error((!argc || !strcmp(head, branch_name)) ? _("No commit on branch '%s' yet.") : _("No branch named '%s'."), branch_name); @@ -827,24 +820,19 @@ int cmd_branch(int argc, const char **argv, const char *prefix) strbuf_release(&buf); return ret; - } else if (copy) { - if (!argc) - die(_("branch name required")); - else if (argc == 1) - copy_or_rename_branch(head, argv[0], 1, copy > 1); - else if (argc == 2) - copy_or_rename_branch(argv[0], argv[1], 1, copy > 1); - else - die(_("too many branches for a copy operation")); - } else if (rename) { + } else if (copy || rename) { if (!argc) die(_("branch name required")); + else if ((argc == 1) && filter.detached) + die(copy? _("cannot copy the current branch while not on any.") + : _("cannot rename the current branch while not on any.")); else if (argc == 1) - copy_or_rename_branch(head, argv[0], 0, rename > 1); + copy_or_rename_branch(head, argv[0], copy, copy + rename > 1); else if (argc == 2) - copy_or_rename_branch(argv[0], argv[1], 0, rename > 1); + copy_or_rename_branch(argv[0], argv[1], copy, copy + rename > 1); else - die(_("too many arguments for a rename operation")); + die(copy? _("too many branches for a copy operation") + : _("too many arguments for a rename operation")); } else if (new_upstream) { struct branch *branch; struct strbuf buf = STRBUF_INIT; diff --git a/builtin/bundle.c b/builtin/bundle.c index 544c78a5f3..c12c09f854 100644 --- a/builtin/bundle.c +++ b/builtin/bundle.c @@ -129,7 +129,8 @@ static int cmd_bundle_verify(int argc, const char **argv, const char *prefix) { goto cleanup; } close(bundle_fd); - if (verify_bundle(the_repository, &header, !quiet)) { + if (verify_bundle(the_repository, &header, + quiet ? VERIFY_BUNDLE_QUIET : VERIFY_BUNDLE_VERBOSE)) { ret = 1; goto cleanup; } @@ -195,7 +196,7 @@ static int cmd_bundle_unbundle(int argc, const char **argv, const char *prefix) strvec_pushl(&extra_index_pack_args, "-v", "--progress-title", _("Unbundling objects"), NULL); ret = !!unbundle(the_repository, &header, bundle_fd, - &extra_index_pack_args) || + &extra_index_pack_args, 0) || list_bundle_refs(&header, argc, argv); bundle_header_release(&header); cleanup: diff --git a/builtin/gc.c b/builtin/gc.c index 24ea85c7af..59fc785d1f 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -42,7 +42,7 @@ static const char * const builtin_gc_usage[] = { static int pack_refs = 1; static int prune_reflogs = 1; -static int cruft_packs = 0; +static int cruft_packs = -1; static int aggressive_depth = 50; static int aggressive_window = 250; static int gc_auto_threshold = 6700; @@ -593,6 +593,10 @@ int cmd_gc(int argc, const char **argv, const char *prefix) if (prune_expire && parse_expiry_date(prune_expire, &dummy)) die(_("failed to parse prune expiry value %s"), prune_expire); + prepare_repo_settings(the_repository); + if (cruft_packs < 0) + cruft_packs = the_repository->settings.gc_cruft_packs; + if (aggressive) { strvec_push(&repack, "-f"); if (aggressive_depth > 0) @@ -704,7 +708,6 @@ int cmd_gc(int argc, const char **argv, const char *prefix) clean_pack_garbage(); } - prepare_repo_settings(the_repository); if (the_repository->settings.gc_write_commit_graph == 1) write_commit_graph_reachable(the_repository->objects->odb, !quiet && !daemonized ? COMMIT_GRAPH_WRITE_PROGRESS : 0, diff --git a/builtin/log.c b/builtin/log.c index ee19dc5d45..5eafcf26b4 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -1334,6 +1334,7 @@ static void make_cover_letter(struct rev_info *rev, int use_separate_file, log.in2 = 4; log.file = rev->diffopt.file; log.groups = SHORTLOG_GROUP_AUTHOR; + shortlog_finish_setup(&log); for (i = 0; i < nr; i++) shortlog_add_commit(&log, list[i]); @@ -1763,7 +1764,7 @@ static void prepare_bases(struct base_tree_info *bases, struct object_id *patch_id; if (*commit_base_at(&commit_base, commit)) continue; - if (commit_patch_id(commit, &diffopt, &oid, 0, 1)) + if (commit_patch_id(commit, &diffopt, &oid, 0)) die(_("cannot get patch id")); ALLOC_GROW(bases->patch_id, bases->nr_patch_id + 1, bases->alloc_patch_id); patch_id = bases->patch_id + bases->nr_patch_id; diff --git a/builtin/merge-tree.c b/builtin/merge-tree.c index ae5782917b..fe853aa8f9 100644 --- a/builtin/merge-tree.c +++ b/builtin/merge-tree.c @@ -402,6 +402,7 @@ struct merge_tree_options { int allow_unrelated_histories; int show_messages; int name_only; + int use_stdin; }; static int real_merge(struct merge_tree_options *o, @@ -412,6 +413,7 @@ static int real_merge(struct merge_tree_options *o, struct commit_list *merge_bases = NULL; struct merge_options opt; struct merge_result result = { 0 }; + int show_messages = o->show_messages; parent1 = get_merge_parent(branch1); if (!parent1) @@ -443,9 +445,11 @@ static int real_merge(struct merge_tree_options *o, if (result.clean < 0) die(_("failure to merge")); - if (o->show_messages == -1) - o->show_messages = !result.clean; + if (show_messages == -1) + show_messages = !result.clean; + if (o->use_stdin) + printf("%d%c", result.clean, line_termination); printf("%s%c", oid_to_hex(&result.tree->object.oid), line_termination); if (!result.clean) { struct string_list conflicted_files = STRING_LIST_INIT_NODUP; @@ -467,11 +471,13 @@ static int real_merge(struct merge_tree_options *o, } string_list_clear(&conflicted_files, 1); } - if (o->show_messages) { + if (show_messages) { putchar(line_termination); merge_display_update_messages(&opt, line_termination == '\0', &result); } + if (o->use_stdin) + putchar(line_termination); merge_finalize(&opt, &result); return !result.clean; /* result.clean < 0 handled above */ } @@ -505,6 +511,10 @@ int cmd_merge_tree(int argc, const char **argv, const char *prefix) &o.allow_unrelated_histories, N_("allow merging unrelated histories"), PARSE_OPT_NONEG), + OPT_BOOL_F(0, "stdin", + &o.use_stdin, + N_("perform multiple merges, one per line of input"), + PARSE_OPT_NONEG), OPT_END() }; @@ -512,6 +522,32 @@ int cmd_merge_tree(int argc, const char **argv, const char *prefix) original_argc = argc - 1; /* ignoring argv[0] */ argc = parse_options(argc, argv, prefix, mt_options, merge_tree_usage, PARSE_OPT_STOP_AT_NON_OPTION); + + /* Handle --stdin */ + if (o.use_stdin) { + struct strbuf buf = STRBUF_INIT; + + if (o.mode == MODE_TRIVIAL) + die(_("--trivial-merge is incompatible with all other options")); + line_termination = '\0'; + while (strbuf_getline_lf(&buf, stdin) != EOF) { + struct strbuf **split; + int result; + + split = strbuf_split(&buf, ' '); + if (!split[0] || !split[1] || split[2]) + die(_("malformed input line: '%s'."), buf.buf); + strbuf_rtrim(split[0]); + result = real_merge(&o, split[0]->buf, split[1]->buf, prefix); + if (result < 0) + die(_("merging cannot continue; got unclean result of %d"), result); + strbuf_list_free(split); + } + strbuf_release(&buf); + return 0; + } + + /* Figure out which mode to use */ switch (o.mode) { default: BUG("unexpected command mode %d", o.mode); diff --git a/builtin/patch-id.c b/builtin/patch-id.c index 881fcf3273..f840fbf1c7 100644 --- a/builtin/patch-id.c +++ b/builtin/patch-id.c @@ -2,6 +2,7 @@ #include "builtin.h" #include "config.h" #include "diff.h" +#include "parse-options.h" static void flush_current_id(int patchlen, struct object_id *id, struct object_id *result) { @@ -57,10 +58,12 @@ static int scan_hunk_header(const char *p, int *p_before, int *p_after) } static int get_one_patchid(struct object_id *next_oid, struct object_id *result, - struct strbuf *line_buf, int stable) + struct strbuf *line_buf, int stable, int verbatim) { int patchlen = 0, found_next = 0; int before = -1, after = -1; + int diff_is_binary = 0; + char pre_oid_str[GIT_MAX_HEXSZ + 1], post_oid_str[GIT_MAX_HEXSZ + 1]; git_hash_ctx ctx; the_hash_algo->init_fn(&ctx); @@ -71,11 +74,14 @@ static int get_one_patchid(struct object_id *next_oid, struct object_id *result, const char *p = line; int len; - if (!skip_prefix(line, "diff-tree ", &p) && - !skip_prefix(line, "commit ", &p) && + /* Possibly skip over the prefix added by "log" or "format-patch" */ + if (!skip_prefix(line, "commit ", &p) && !skip_prefix(line, "From ", &p) && - starts_with(line, "\\ ") && 12 < strlen(line)) + starts_with(line, "\\ ") && 12 < strlen(line)) { + if (verbatim) + the_hash_algo->update_fn(&ctx, line, strlen(line)); continue; + } if (!get_oid_hex(p, next_oid)) { found_next = 1; @@ -88,14 +94,44 @@ static int get_one_patchid(struct object_id *next_oid, struct object_id *result, /* Parsing diff header? */ if (before == -1) { - if (starts_with(line, "index ")) + if (starts_with(line, "GIT binary patch") || + starts_with(line, "Binary files")) { + diff_is_binary = 1; + before = 0; + the_hash_algo->update_fn(&ctx, pre_oid_str, + strlen(pre_oid_str)); + the_hash_algo->update_fn(&ctx, post_oid_str, + strlen(post_oid_str)); + if (stable) + flush_one_hunk(result, &ctx); + continue; + } else if (skip_prefix(line, "index ", &p)) { + char *oid1_end = strstr(line, ".."); + char *oid2_end = NULL; + if (oid1_end) + oid2_end = strstr(oid1_end, " "); + if (!oid2_end) + oid2_end = line + strlen(line) - 1; + if (oid1_end != NULL && oid2_end != NULL) { + *oid1_end = *oid2_end = '\0'; + strlcpy(pre_oid_str, p, GIT_MAX_HEXSZ + 1); + strlcpy(post_oid_str, oid1_end + 2, GIT_MAX_HEXSZ + 1); + } continue; - else if (starts_with(line, "--- ")) + } else if (starts_with(line, "--- ")) before = after = 1; else if (!isalpha(line[0])) break; } + if (diff_is_binary) { + if (starts_with(line, "diff ")) { + diff_is_binary = 0; + before = -1; + } + continue; + } + /* Looking for a valid hunk header? */ if (before == 0 && after == 0) { if (starts_with(line, "@@ -")) { @@ -120,8 +156,8 @@ static int get_one_patchid(struct object_id *next_oid, struct object_id *result, if (line[0] == '+' || line[0] == ' ') after--; - /* Compute the sha without whitespace */ - len = remove_space(line); + /* Add line to hash algo (possibly removing whitespace) */ + len = verbatim ? strlen(line) : remove_space(line); patchlen += len; the_hash_algo->update_fn(&ctx, line, len); } @@ -134,7 +170,7 @@ static int get_one_patchid(struct object_id *next_oid, struct object_id *result, return patchlen; } -static void generate_id_list(int stable) +static void generate_id_list(int stable, int verbatim) { struct object_id oid, n, result; int patchlen; @@ -142,21 +178,32 @@ static void generate_id_list(int stable) oidclr(&oid); while (!feof(stdin)) { - patchlen = get_one_patchid(&n, &result, &line_buf, stable); + patchlen = get_one_patchid(&n, &result, &line_buf, stable, verbatim); flush_current_id(patchlen, &oid, &result); oidcpy(&oid, &n); } strbuf_release(&line_buf); } -static const char patch_id_usage[] = "git patch-id [--stable | --unstable]"; +static const char *const patch_id_usage[] = { + N_("git patch-id [--stable | --unstable | --verbatim]"), NULL +}; + +struct patch_id_opts { + int stable; + int verbatim; +}; static int git_patch_id_config(const char *var, const char *value, void *cb) { - int *stable = cb; + struct patch_id_opts *opts = cb; if (!strcmp(var, "patchid.stable")) { - *stable = git_config_bool(var, value); + opts->stable = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "patchid.verbatim")) { + opts->verbatim = git_config_bool(var, value); return 0; } @@ -165,21 +212,29 @@ static int git_patch_id_config(const char *var, const char *value, void *cb) int cmd_patch_id(int argc, const char **argv, const char *prefix) { - int stable = -1; - - git_config(git_patch_id_config, &stable); - - /* If nothing is set, default to unstable. */ - if (stable < 0) - stable = 0; - - if (argc == 2 && !strcmp(argv[1], "--stable")) - stable = 1; - else if (argc == 2 && !strcmp(argv[1], "--unstable")) - stable = 0; - else if (argc != 1) - usage(patch_id_usage); - - generate_id_list(stable); + /* if nothing is set, default to unstable */ + struct patch_id_opts config = {0, 0}; + int opts = 0; + struct option builtin_patch_id_options[] = { + OPT_CMDMODE(0, "unstable", &opts, + N_("use the unstable patch-id algorithm"), 1), + OPT_CMDMODE(0, "stable", &opts, + N_("use the stable patch-id algorithm"), 2), + OPT_CMDMODE(0, "verbatim", &opts, + N_("don't strip whitespace from the patch"), 3), + OPT_END() + }; + + git_config(git_patch_id_config, &config); + + /* verbatim implies stable */ + if (config.verbatim) + config.stable = 1; + + argc = parse_options(argc, argv, prefix, builtin_patch_id_options, + patch_id_usage, 0); + + generate_id_list(opts ? opts > 1 : config.stable, + opts ? opts == 3 : config.verbatim); return 0; } diff --git a/builtin/rebase.c b/builtin/rebase.c index 56e4214b44..5d855fd8f5 100644 --- a/builtin/rebase.c +++ b/builtin/rebase.c @@ -59,6 +59,26 @@ enum empty_type { EMPTY_ASK }; +enum action { + ACTION_NONE = 0, + ACTION_CONTINUE, + ACTION_SKIP, + ACTION_ABORT, + ACTION_QUIT, + ACTION_EDIT_TODO, + ACTION_SHOW_CURRENT_PATCH +}; + +static const char *action_names[] = { + "undefined", + "continue", + "skip", + "abort", + "quit", + "edit_todo", + "show_current_patch" +}; + struct rebase_options { enum rebase_type type; enum empty_type empty; @@ -68,7 +88,7 @@ struct rebase_options { const char *upstream_name; const char *upstream_arg; char *head_name; - struct object_id orig_head; + struct commit *orig_head; struct commit *onto; const char *onto_name; const char *revisions; @@ -85,7 +105,7 @@ struct rebase_options { REBASE_INTERACTIVE_EXPLICIT = 1<<4, } flags; struct strvec git_am_opts; - const char *action; + enum action action; int signoff; int allow_rerere_autoupdate; int keep_empty; @@ -157,24 +177,6 @@ static struct replay_opts get_replay_opts(const struct rebase_options *opts) return replay; } -enum action { - ACTION_NONE = 0, - ACTION_CONTINUE, - ACTION_SKIP, - ACTION_ABORT, - ACTION_QUIT, - ACTION_EDIT_TODO, - ACTION_SHOW_CURRENT_PATCH -}; - -static const char *action_names[] = { "undefined", - "continue", - "skip", - "abort", - "quit", - "edit_todo", - "show_current_patch" }; - static int edit_todo_file(unsigned flags) { const char *todo_file = rebase_path_todo(); @@ -261,13 +263,13 @@ static int do_interactive_rebase(struct rebase_options *opts, unsigned flags) struct replay_opts replay = get_replay_opts(opts); struct string_list commands = STRING_LIST_INIT_DUP; - if (get_revision_ranges(opts->upstream, opts->onto, &opts->orig_head, + if (get_revision_ranges(opts->upstream, opts->onto, &opts->orig_head->object.oid, &revisions, &shortrevisions)) return -1; if (init_basic_state(&replay, opts->head_name ? opts->head_name : "detached HEAD", - opts->onto, &opts->orig_head)) { + opts->onto, &opts->orig_head->object.oid)) { free(revisions); free(shortrevisions); @@ -298,9 +300,8 @@ static int do_interactive_rebase(struct rebase_options *opts, unsigned flags) split_exec_commands(opts->cmd, &commands); ret = complete_action(the_repository, &replay, flags, shortrevisions, opts->onto_name, opts->onto, - &opts->orig_head, &commands, opts->autosquash, - opts->update_refs, - &todo_list); + &opts->orig_head->object.oid, &commands, + opts->autosquash, opts->update_refs, &todo_list); } string_list_clear(&commands, 0); @@ -312,8 +313,7 @@ static int do_interactive_rebase(struct rebase_options *opts, unsigned flags) return ret; } -static int run_sequencer_rebase(struct rebase_options *opts, - enum action command) +static int run_sequencer_rebase(struct rebase_options *opts) { unsigned flags = 0; int abbreviate_commands = 0, ret = 0; @@ -328,7 +328,7 @@ static int run_sequencer_rebase(struct rebase_options *opts, flags |= opts->reapply_cherry_picks ? TODO_LIST_REAPPLY_CHERRY_PICKS : 0; flags |= opts->flags & REBASE_NO_QUIET ? TODO_LIST_WARN_SKIPPED_CHERRY_PICKS : 0; - switch (command) { + switch (opts->action) { case ACTION_NONE: { if (!opts->onto && !opts->upstream) die(_("a base commit must be provided with --upstream or --onto")); @@ -361,7 +361,7 @@ static int run_sequencer_rebase(struct rebase_options *opts, break; } default: - BUG("invalid command '%d'", command); + BUG("invalid command '%d'", opts->action); } return ret; @@ -431,9 +431,9 @@ static int read_basic_state(struct rebase_options *opts) opts->head_name = starts_with(head_name.buf, "refs/") ? xstrdup(head_name.buf) : NULL; strbuf_release(&head_name); - if (get_oid(buf.buf, &oid)) - return error(_("could not get 'onto': '%s'"), buf.buf); - opts->onto = lookup_commit_or_die(&oid, buf.buf); + if (get_oid_hex(buf.buf, &oid) || + !(opts->onto = lookup_commit_object(the_repository, &oid))) + return error(_("invalid onto: '%s'"), buf.buf); /* * We always write to orig-head, but interactive rebase used to write to @@ -448,7 +448,8 @@ static int read_basic_state(struct rebase_options *opts) } else if (!read_oneliner(&buf, state_dir_path("head", opts), READ_ONELINER_WARN_MISSING)) return -1; - if (get_oid(buf.buf, &opts->orig_head)) + if (get_oid_hex(buf.buf, &oid) || + !(opts->orig_head = lookup_commit_object(the_repository, &oid))) return error(_("invalid orig-head: '%s'"), buf.buf); if (file_exists(state_dir_path("quiet", opts))) @@ -517,7 +518,7 @@ static int rebase_write_basic_state(struct rebase_options *opts) write_file(state_dir_path("onto", opts), "%s", opts->onto ? oid_to_hex(&opts->onto->object.oid) : ""); write_file(state_dir_path("orig-head", opts), "%s", - oid_to_hex(&opts->orig_head)); + oid_to_hex(&opts->orig_head->object.oid)); if (!(opts->flags & REBASE_NO_QUIET)) write_file(state_dir_path("quiet", opts), "%s", ""); if (opts->flags & REBASE_VERBOSE) @@ -583,10 +584,11 @@ static int move_to_original_branch(struct rebase_options *opts) if (!opts->onto) BUG("move_to_original_branch without onto"); - strbuf_addf(&branch_reflog, "rebase finished: %s onto %s", + strbuf_addf(&branch_reflog, "%s (finish): %s onto %s", + getenv(GIT_REFLOG_ACTION_ENVIRONMENT), opts->head_name, oid_to_hex(&opts->onto->object.oid)); - strbuf_addf(&head_reflog, "rebase finished: returning to %s", - opts->head_name); + strbuf_addf(&head_reflog, "%s (finish): returning to %s", + getenv(GIT_REFLOG_ACTION_ENVIRONMENT), opts->head_name); ropts.branch = opts->head_name; ropts.flags = RESET_HEAD_REFS_ONLY; ropts.branch_msg = branch_reflog.buf; @@ -615,8 +617,9 @@ static int run_am(struct rebase_options *opts) am.git_cmd = 1; strvec_push(&am.args, "am"); - - if (opts->action && !strcmp("continue", opts->action)) { + strvec_pushf(&am.env, GIT_REFLOG_ACTION_ENVIRONMENT "=%s (pick)", + getenv(GIT_REFLOG_ACTION_ENVIRONMENT)); + if (opts->action == ACTION_CONTINUE) { strvec_push(&am.args, "--resolved"); strvec_pushf(&am.args, "--resolvemsg=%s", resolvemsg); if (opts->gpg_sign_opt) @@ -627,7 +630,7 @@ static int run_am(struct rebase_options *opts) return move_to_original_branch(opts); } - if (opts->action && !strcmp("skip", opts->action)) { + if (opts->action == ACTION_SKIP) { strvec_push(&am.args, "--skip"); strvec_pushf(&am.args, "--resolvemsg=%s", resolvemsg); status = run_command(&am); @@ -636,7 +639,7 @@ static int run_am(struct rebase_options *opts) return move_to_original_branch(opts); } - if (opts->action && !strcmp("show-current-patch", opts->action)) { + if (opts->action == ACTION_SHOW_CURRENT_PATCH) { strvec_push(&am.args, "--show-current-patch"); return run_command(&am); } @@ -646,7 +649,7 @@ static int run_am(struct rebase_options *opts) /* this is now equivalent to !opts->upstream */ &opts->onto->object.oid : &opts->upstream->object.oid), - oid_to_hex(&opts->orig_head)); + oid_to_hex(&opts->orig_head->object.oid)); rebased_patches = xstrdup(git_path("rebased-patches")); format_patch.out = open(rebased_patches, @@ -680,7 +683,7 @@ static int run_am(struct rebase_options *opts) free(rebased_patches); strvec_clear(&am.args); - ropts.oid = &opts->orig_head; + ropts.oid = &opts->orig_head->object.oid; ropts.branch = opts->head_name; ropts.default_reflog_action = DEFAULT_REFLOG_ACTION; reset_head(the_repository, &ropts); @@ -729,7 +732,7 @@ static int run_am(struct rebase_options *opts) return status; } -static int run_specific_rebase(struct rebase_options *opts, enum action action) +static int run_specific_rebase(struct rebase_options *opts) { int status; @@ -747,7 +750,7 @@ static int run_specific_rebase(struct rebase_options *opts, enum action action) opts->gpg_sign_opt = tmp; } - status = run_sequencer_rebase(opts, action); + status = run_sequencer_rebase(opts); } else if (opts->type == REBASE_APPLY) status = run_am(opts); else @@ -833,7 +836,7 @@ static int checkout_up_to_date(struct rebase_options *options) strbuf_addf(&buf, "%s: checkout %s", getenv(GIT_REFLOG_ACTION_ENVIRONMENT), options->switch_to); - ropts.oid = &options->orig_head; + ropts.oid = &options->orig_head->object.oid; ropts.branch = options->head_name; ropts.flags = RESET_HEAD_RUN_POST_CHECKOUT_HOOK; if (!ropts.branch) @@ -866,32 +869,23 @@ static int is_linear_history(struct commit *from, struct commit *to) static int can_fast_forward(struct commit *onto, struct commit *upstream, struct commit *restrict_revision, - struct object_id *head_oid, struct object_id *merge_base) + struct commit *head, struct object_id *branch_base) { - struct commit *head = lookup_commit(the_repository, head_oid); struct commit_list *merge_bases = NULL; int res = 0; - if (!head) - goto done; + if (is_null_oid(branch_base)) + goto done; /* fill_branch_base() found multiple merge bases */ - merge_bases = get_merge_bases(onto, head); - if (!merge_bases || merge_bases->next) { - oidcpy(merge_base, null_oid()); + if (!oideq(branch_base, &onto->object.oid)) goto done; - } - oidcpy(merge_base, &merge_bases->item->object.oid); - if (!oideq(merge_base, &onto->object.oid)) - goto done; - - if (restrict_revision && !oideq(&restrict_revision->object.oid, merge_base)) + if (restrict_revision && !oideq(&restrict_revision->object.oid, branch_base)) goto done; if (!upstream) goto done; - free_commit_list(merge_bases); merge_bases = get_merge_bases(upstream, head); if (!merge_bases || merge_bases->next) goto done; @@ -906,6 +900,20 @@ done: return res && is_linear_history(onto, head); } +static void fill_branch_base(struct rebase_options *options, + struct object_id *branch_base) +{ + struct commit_list *merge_bases = NULL; + + merge_bases = get_merge_bases(options->onto, options->orig_head); + if (!merge_bases || merge_bases->next) + oidcpy(branch_base, null_oid()); + else + oidcpy(branch_base, &merge_bases->item->object.oid); + + free_commit_list(merge_bases); +} + static int parse_opt_am(const struct option *opt, const char *arg, int unset) { struct rebase_options *opts = opt->value; @@ -1000,23 +1008,6 @@ static void NORETURN error_on_missing_default_upstream(void) exit(1); } -static void set_reflog_action(struct rebase_options *options) -{ - const char *env; - struct strbuf buf = STRBUF_INIT; - - if (!is_merge(options)) - return; - - env = getenv(GIT_REFLOG_ACTION_ENVIRONMENT); - if (env && strcmp("rebase", env)) - return; /* only override it if it is "rebase" */ - - strbuf_addf(&buf, "rebase (%s)", options->action); - setenv(GIT_REFLOG_ACTION_ENVIRONMENT, buf.buf, 1); - strbuf_release(&buf); -} - static int check_exec_cmd(const char *cmd) { if (strchr(cmd, '\n')) @@ -1039,9 +1030,8 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) struct strbuf msg = STRBUF_INIT; struct strbuf revisions = STRBUF_INIT; struct strbuf buf = STRBUF_INIT; - struct object_id merge_base; + struct object_id branch_base; int ignore_whitespace = 0; - enum action action = ACTION_NONE; const char *gpg_sign = NULL; struct string_list exec = STRING_LIST_INIT_NODUP; const char *rebase_merges = NULL; @@ -1090,18 +1080,18 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) OPT_BIT(0, "no-ff", &options.flags, N_("cherry-pick all commits, even if unchanged"), REBASE_FORCE), - OPT_CMDMODE(0, "continue", &action, N_("continue"), + OPT_CMDMODE(0, "continue", &options.action, N_("continue"), ACTION_CONTINUE), - OPT_CMDMODE(0, "skip", &action, + OPT_CMDMODE(0, "skip", &options.action, N_("skip current patch and continue"), ACTION_SKIP), - OPT_CMDMODE(0, "abort", &action, + OPT_CMDMODE(0, "abort", &options.action, N_("abort and check out the original branch"), ACTION_ABORT), - OPT_CMDMODE(0, "quit", &action, + OPT_CMDMODE(0, "quit", &options.action, N_("abort but keep HEAD where it is"), ACTION_QUIT), - OPT_CMDMODE(0, "edit-todo", &action, N_("edit the todo list " + OPT_CMDMODE(0, "edit-todo", &options.action, N_("edit the todo list " "during an interactive rebase"), ACTION_EDIT_TODO), - OPT_CMDMODE(0, "show-current-patch", &action, + OPT_CMDMODE(0, "show-current-patch", &options.action, N_("show the patch file being applied or merged"), ACTION_SHOW_CURRENT_PATCH), OPT_CALLBACK_F(0, "apply", &options, NULL, @@ -1175,6 +1165,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) prepare_repo_settings(the_repository); the_repository->settings.command_requires_full_index = 0; + options.reapply_cherry_picks = -1; options.allow_empty_message = 1; git_config(rebase_config, &options); /* options.gpg_sign_opt will be either "-S" or NULL */ @@ -1192,7 +1183,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) } else if (is_directory(merge_dir())) { strbuf_reset(&buf); strbuf_addf(&buf, "%s/rewritten", merge_dir()); - if (!(action == ACTION_ABORT) && is_directory(buf.buf)) { + if (!(options.action == ACTION_ABORT) && is_directory(buf.buf)) { die(_("`rebase --preserve-merges` (-p) is no longer supported.\n" "Use `git rebase --abort` to terminate current rebase.\n" "Or downgrade to v2.33, or earlier, to complete the rebase.")); @@ -1219,7 +1210,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) "Note: Your `pull.rebase` configuration may also be set to 'preserve',\n" "which is no longer supported; use 'merges' instead")); - if (action != ACTION_NONE && total_argc != 2) { + if (options.action != ACTION_NONE && total_argc != 2) { usage_with_options(builtin_rebase_usage, builtin_rebase_options); } @@ -1233,16 +1224,28 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) die(_("options '%s' and '%s' cannot be used together"), "--keep-base", "--onto"); if (options.root) die(_("options '%s' and '%s' cannot be used together"), "--keep-base", "--root"); + /* + * --keep-base defaults to --no-fork-point to keep the + * base the same. + */ + if (options.fork_point < 0) + options.fork_point = 0; } + /* + * --keep-base defaults to --reapply-cherry-picks to avoid losing + * commits when using this option. + */ + if (options.reapply_cherry_picks < 0) + options.reapply_cherry_picks = keep_base; if (options.root && options.fork_point > 0) die(_("options '%s' and '%s' cannot be used together"), "--root", "--fork-point"); - if (action != ACTION_NONE && !in_progress) + if (options.action != ACTION_NONE && !in_progress) die(_("No rebase in progress?")); setenv(GIT_REFLOG_ACTION_ENVIRONMENT, "rebase", 0); - if (action == ACTION_EDIT_TODO && !is_merge(&options)) + if (options.action == ACTION_EDIT_TODO && !is_merge(&options)) die(_("The --edit-todo action can only be used during " "interactive rebase.")); @@ -1252,18 +1255,15 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) else if (exec.nr) trace2_cmd_mode("interactive-exec"); else - trace2_cmd_mode(action_names[action]); + trace2_cmd_mode(action_names[options.action]); } - switch (action) { + switch (options.action) { case ACTION_CONTINUE: { struct object_id head; struct lock_file lock_file = LOCK_INIT; int fd; - options.action = "continue"; - set_reflog_action(&options); - /* Sanity check */ if (get_oid("HEAD", &head)) die(_("Cannot read HEAD")); @@ -1289,9 +1289,6 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) case ACTION_SKIP: { struct string_list merge_rr = STRING_LIST_INIT_DUP; - options.action = "skip"; - set_reflog_action(&options); - rerere_clear(the_repository, &merge_rr); string_list_clear(&merge_rr, 1); ropts.flags = RESET_HEAD_HARD; @@ -1304,21 +1301,25 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) } case ACTION_ABORT: { struct string_list merge_rr = STRING_LIST_INIT_DUP; - options.action = "abort"; - set_reflog_action(&options); + struct strbuf head_msg = STRBUF_INIT; rerere_clear(the_repository, &merge_rr); string_list_clear(&merge_rr, 1); if (read_basic_state(&options)) exit(1); - ropts.oid = &options.orig_head; + + strbuf_addf(&head_msg, "%s (abort): returning to %s", + getenv(GIT_REFLOG_ACTION_ENVIRONMENT), + options.head_name ? options.head_name + : oid_to_hex(&options.orig_head->object.oid)); + ropts.oid = &options.orig_head->object.oid; + ropts.head_msg = head_msg.buf; ropts.branch = options.head_name; ropts.flags = RESET_HEAD_HARD; - ropts.default_reflog_action = DEFAULT_REFLOG_ACTION; if (reset_head(the_repository, &ropts) < 0) die(_("could not move back to %s"), - oid_to_hex(&options.orig_head)); + oid_to_hex(&options.orig_head->object.oid)); remove_branch_state(the_repository, 0); ret = finish_rebase(&options); goto cleanup; @@ -1341,17 +1342,15 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) goto cleanup; } case ACTION_EDIT_TODO: - options.action = "edit-todo"; options.dont_finish_rebase = 1; goto run_rebase; case ACTION_SHOW_CURRENT_PATCH: - options.action = "show-current-patch"; options.dont_finish_rebase = 1; goto run_rebase; case ACTION_NONE: break; default: - BUG("action: %d", action); + BUG("action: %d", options.action); } /* Make sure no rebase is in progress */ @@ -1375,7 +1374,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) } if ((options.flags & REBASE_INTERACTIVE_EXPLICIT) || - (action != ACTION_NONE) || + (options.action != ACTION_NONE) || (exec.nr > 0) || options.autosquash) { allow_preemptive_ff = 0; @@ -1410,7 +1409,11 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) if (options.empty != EMPTY_UNSPECIFIED) imply_merge(&options, "--empty"); - if (options.reapply_cherry_picks) + /* + * --keep-base implements --reapply-cherry-picks by altering upstream so + * it works with both backends. + */ + if (options.reapply_cherry_picks && !keep_base) imply_merge(&options, "--reapply-cherry-picks"); if (gpg_sign) @@ -1604,25 +1607,27 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) */ if (argc == 1) { /* Is it "rebase other branchname" or "rebase other commit"? */ + struct object_id branch_oid; branch_name = argv[0]; options.switch_to = argv[0]; /* Is it a local branch? */ strbuf_reset(&buf); strbuf_addf(&buf, "refs/heads/%s", branch_name); - if (!read_ref(buf.buf, &options.orig_head)) { + if (!read_ref(buf.buf, &branch_oid)) { die_if_checked_out(buf.buf, 1); options.head_name = xstrdup(buf.buf); + options.orig_head = + lookup_commit_object(the_repository, + &branch_oid); /* If not is it a valid ref (branch or commit)? */ } else { - struct commit *commit = + options.orig_head = lookup_commit_reference_by_name(branch_name); - if (!commit) - die(_("no such branch/commit '%s'"), - branch_name); - oidcpy(&options.orig_head, &commit->object.oid); options.head_name = NULL; } + if (!options.orig_head) + die(_("no such branch/commit '%s'"), branch_name); } else if (argc == 0) { /* Do not need to switch branches, we are already on it. */ options.head_name = @@ -1639,8 +1644,9 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) FREE_AND_NULL(options.head_name); branch_name = "HEAD"; } - if (get_oid("HEAD", &options.orig_head)) - die(_("Could not resolve HEAD to a revision")); + options.orig_head = lookup_commit_reference_by_name("HEAD"); + if (!options.orig_head) + die(_("Could not resolve HEAD to a commit")); } else BUG("unexpected number of arguments left to parse"); @@ -1654,7 +1660,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) } else if (!options.onto_name) options.onto_name = options.upstream_name; if (strstr(options.onto_name, "...")) { - if (get_oid_mb(options.onto_name, &merge_base) < 0) { + if (get_oid_mb(options.onto_name, &branch_base) < 0) { if (keep_base) die(_("'%s': need exactly one merge base with branch"), options.upstream_name); @@ -1662,7 +1668,7 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) die(_("'%s': need exactly one merge base"), options.onto_name); } - options.onto = lookup_commit_or_die(&merge_base, + options.onto = lookup_commit_or_die(&branch_base, options.onto_name); } else { options.onto = @@ -1670,15 +1676,15 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) if (!options.onto) die(_("Does not point to a valid commit '%s'"), options.onto_name); + fill_branch_base(&options, &branch_base); } - if (options.fork_point > 0) { - struct commit *head = - lookup_commit_reference(the_repository, - &options.orig_head); + if (keep_base && options.reapply_cherry_picks) + options.upstream = options.onto; + + if (options.fork_point > 0) options.restrict_revision = - get_fork_point(options.upstream_name, head); - } + get_fork_point(options.upstream_name, options.orig_head); if (repo_read_index(the_repository) < 0) die(_("could not read index")); @@ -1703,13 +1709,10 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) * Check if we are already based on onto with linear history, * in which case we could fast-forward without replacing the commits * with new commits recreated by replaying their changes. - * - * Note that can_fast_forward() initializes merge_base, so we have to - * call it before checking allow_preemptive_ff. */ - if (can_fast_forward(options.onto, options.upstream, options.restrict_revision, - &options.orig_head, &merge_base) && - allow_preemptive_ff) { + if (allow_preemptive_ff && + can_fast_forward(options.onto, options.upstream, options.restrict_revision, + options.orig_head, &branch_base)) { int flag; if (!(options.flags & REBASE_FORCE)) { @@ -1750,12 +1753,12 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) struct diff_options opts; if (options.flags & REBASE_VERBOSE) { - if (is_null_oid(&merge_base)) + if (is_null_oid(&branch_base)) printf(_("Changes to %s:\n"), oid_to_hex(&options.onto->object.oid)); else printf(_("Changes from %s to %s:\n"), - oid_to_hex(&merge_base), + oid_to_hex(&branch_base), oid_to_hex(&options.onto->object.oid)); } @@ -1767,8 +1770,8 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) DIFF_FORMAT_SUMMARY | DIFF_FORMAT_DIFFSTAT; opts.detect_rename = DIFF_DETECT_RENAME; diff_setup_done(&opts); - diff_tree_oid(is_null_oid(&merge_base) ? - the_hash_algo->empty_tree : &merge_base, + diff_tree_oid(is_null_oid(&branch_base) ? + the_hash_algo->empty_tree : &branch_base, &options.onto->object.oid, "", &opts); diffcore_std(&opts); diff_flush(&opts); @@ -1782,10 +1785,10 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) printf(_("First, rewinding head to replay your work on top of " "it...\n")); - strbuf_addf(&msg, "%s: checkout %s", + strbuf_addf(&msg, "%s (start): checkout %s", getenv(GIT_REFLOG_ACTION_ENVIRONMENT), options.onto_name); ropts.oid = &options.onto->object.oid; - ropts.orig_head = &options.orig_head, + ropts.orig_head = &options.orig_head->object.oid, ropts.flags = RESET_HEAD_DETACH | RESET_ORIG_HEAD | RESET_HEAD_RUN_POST_CHECKOUT_HOOK; ropts.head_msg = msg.buf; @@ -1798,19 +1801,10 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) * If the onto is a proper descendant of the tip of the branch, then * we just fast-forwarded. */ - strbuf_reset(&msg); - if (oideq(&merge_base, &options.orig_head)) { + if (oideq(&branch_base, &options.orig_head->object.oid)) { printf(_("Fast-forwarded %s to %s.\n"), branch_name, options.onto_name); - strbuf_addf(&msg, "rebase finished: %s onto %s", - options.head_name ? options.head_name : "detached HEAD", - oid_to_hex(&options.onto->object.oid)); - memset(&ropts, 0, sizeof(ropts)); - ropts.branch = options.head_name; - ropts.flags = RESET_HEAD_REFS_ONLY; - ropts.head_msg = msg.buf; - reset_head(the_repository, &ropts); - strbuf_release(&msg); + move_to_original_branch(&options); ret = finish_rebase(&options); goto cleanup; } @@ -1820,12 +1814,12 @@ int cmd_rebase(int argc, const char **argv, const char *prefix) (options.restrict_revision ? oid_to_hex(&options.restrict_revision->object.oid) : oid_to_hex(&options.upstream->object.oid)), - oid_to_hex(&options.orig_head)); + oid_to_hex(&options.orig_head->object.oid)); options.revisions = revisions.buf; run_rebase: - ret = run_specific_rebase(&options, action); + ret = run_specific_rebase(&options); cleanup: strbuf_release(&buf); diff --git a/builtin/repack.c b/builtin/repack.c index 3f0cd55351..10e23f9ee1 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -92,44 +92,6 @@ static int repack_config(const char *var, const char *value, void *cb) } /* - * Remove temporary $GIT_OBJECT_DIRECTORY/pack/.tmp-$$-pack-* files. - */ -static void remove_temporary_files(void) -{ - struct strbuf buf = STRBUF_INIT; - size_t dirlen, prefixlen; - DIR *dir; - struct dirent *e; - - dir = opendir(packdir); - if (!dir) - return; - - /* Point at the slash at the end of ".../objects/pack/" */ - dirlen = strlen(packdir) + 1; - strbuf_addstr(&buf, packtmp); - /* Hold the length of ".tmp-%d-pack-" */ - prefixlen = buf.len - dirlen; - - while ((e = readdir(dir))) { - if (strncmp(e->d_name, buf.buf + dirlen, prefixlen)) - continue; - strbuf_setlen(&buf, dirlen); - strbuf_addstr(&buf, e->d_name); - unlink(buf.buf); - } - closedir(dir); - strbuf_release(&buf); -} - -static void remove_pack_on_signal(int signo) -{ - remove_temporary_files(); - sigchain_pop(signo); - raise(signo); -} - -/* * Adds all packs hex strings to either fname_nonkept_list or * fname_kept_list based on whether each pack has a corresponding * .keep file or not. Packs without a .keep file are not to be kept @@ -247,11 +209,15 @@ static struct { {".idx"}, }; -static unsigned populate_pack_exts(char *name) +struct generated_pack_data { + struct tempfile *tempfiles[ARRAY_SIZE(exts)]; +}; + +static struct generated_pack_data *populate_pack_exts(const char *name) { struct stat statbuf; struct strbuf path = STRBUF_INIT; - unsigned ret = 0; + struct generated_pack_data *data = xcalloc(1, sizeof(*data)); int i; for (i = 0; i < ARRAY_SIZE(exts); i++) { @@ -261,11 +227,11 @@ static unsigned populate_pack_exts(char *name) if (stat(path.buf, &statbuf)) continue; - ret |= (1 << i); + data->tempfiles[i] = register_tempfile(path.buf); } strbuf_release(&path); - return ret; + return data; } static void repack_promisor_objects(const struct pack_objects_args *args, @@ -320,7 +286,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args, line.buf); write_promisor_file(promisor_name, NULL, 0); - item->util = (void *)(uintptr_t)populate_pack_exts(item->string); + item->util = populate_pack_exts(item->string); free(promisor_name); } @@ -739,10 +705,14 @@ static int write_cruft_pack(const struct pack_objects_args *args, out = xfdopen(cmd.out, "r"); while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + if (line.len != the_hash_algo->hexsz) die(_("repack: Expecting full hex object ID lines only " "from pack-objects.")); - string_list_append(names, line.buf); + + item = string_list_append(names, line.buf); + item->util = populate_pack_exts(line.buf); } fclose(out); @@ -888,8 +858,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix) split_pack_geometry(geometry, geometric_factor); } - sigchain_push_common(remove_pack_on_signal); - prepare_pack_objects(&cmd, &po_args); show_progress = !po_args.quiet && isatty(2); @@ -981,9 +949,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix) out = xfdopen(cmd.out, "r"); while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + if (line.len != the_hash_algo->hexsz) die(_("repack: Expecting full hex object ID lines only from pack-objects.")); - string_list_append(&names, line.buf); + item = string_list_append(&names, line.buf); + item->util = populate_pack_exts(item->string); } fclose(out); ret = finish_command(&cmd); @@ -1022,40 +993,38 @@ int cmd_repack(int argc, const char **argv, const char *prefix) string_list_sort(&names); - for_each_string_list_item(item, &names) { - item->util = (void *)(uintptr_t)populate_pack_exts(item->string); - } - close_object_store(the_repository->objects); /* * Ok we have prepared all new packfiles. */ for_each_string_list_item(item, &names) { + struct generated_pack_data *data = item->util; + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { - char *fname, *fname_old; + char *fname; fname = mkpathdup("%s/pack-%s%s", packdir, item->string, exts[ext].name); - fname_old = mkpathdup("%s-%s%s", - packtmp, item->string, exts[ext].name); - if (((uintptr_t)item->util) & ((uintptr_t)1 << ext)) { + if (data->tempfiles[ext]) { + const char *fname_old = get_tempfile_path(data->tempfiles[ext]); struct stat statbuffer; + if (!stat(fname_old, &statbuffer)) { statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); chmod(fname_old, statbuffer.st_mode); } - if (rename(fname_old, fname)) - die_errno(_("renaming '%s' failed"), fname_old); + if (rename_tempfile(&data->tempfiles[ext], fname)) + die_errno(_("renaming pack to '%s' failed"), fname); } else if (!exts[ext].optional) - die(_("missing required file: %s"), fname_old); + die(_("pack-objects did not write a '%s' file for pack %s-%s"), + exts[ext].name, packtmp, item->string); else if (unlink(fname) < 0 && errno != ENOENT) die_errno(_("could not unlink: %s"), fname); free(fname); - free(fname_old); } } /* End of pack replacement. */ @@ -1143,7 +1112,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (run_update_server_info) update_server_info(0); - remove_temporary_files(); if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) { unsigned flags = 0; @@ -1152,7 +1120,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) write_midx_file(get_object_directory(), NULL, NULL, flags); } - string_list_clear(&names, 0); + string_list_clear(&names, 1); string_list_clear(&existing_nonkept_packs, 0); string_list_clear(&existing_kept_packs, 0); clear_pack_geometry(geometry); diff --git a/builtin/shortlog.c b/builtin/shortlog.c index 7a1e1fe7c0..27a87167e1 100644 --- a/builtin/shortlog.c +++ b/builtin/shortlog.c @@ -132,7 +132,9 @@ static void read_from_stdin(struct shortlog *log) match = committer_match; break; case SHORTLOG_GROUP_TRAILER: - die(_("using --group=trailer with stdin is not supported")); + die(_("using %s with stdin is not supported"), "--group=trailer"); + case SHORTLOG_GROUP_FORMAT: + die(_("using %s with stdin is not supported"), "--group=format"); default: BUG("unhandled shortlog group"); } @@ -170,6 +172,9 @@ static void insert_records_from_trailers(struct shortlog *log, const char *commit_buffer, *body; struct strbuf ident = STRBUF_INIT; + if (!log->trailers.nr) + return; + /* * Using format_commit_message("%B") would be simpler here, but * this saves us copying the message. @@ -200,9 +205,34 @@ static void insert_records_from_trailers(struct shortlog *log, unuse_commit_buffer(commit, commit_buffer); } +static int shortlog_needs_dedup(const struct shortlog *log) +{ + return HAS_MULTI_BITS(log->groups) || log->format.nr > 1 || log->trailers.nr; +} + +static void insert_records_from_format(struct shortlog *log, + struct strset *dups, + struct commit *commit, + struct pretty_print_context *ctx, + const char *oneline) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + + for_each_string_list_item(item, &log->format) { + strbuf_reset(&buf); + + format_commit_message(commit, item->string, &buf, ctx); + + if (!shortlog_needs_dedup(log) || strset_add(dups, buf.buf)) + insert_one_record(log, buf.buf, oneline); + } + + strbuf_release(&buf); +} + void shortlog_add_commit(struct shortlog *log, struct commit *commit) { - struct strbuf ident = STRBUF_INIT; struct strbuf oneline = STRBUF_INIT; struct strset dups = STRSET_INIT; struct pretty_print_context ctx = {0}; @@ -211,7 +241,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit) ctx.fmt = CMIT_FMT_USERFORMAT; ctx.abbrev = log->abbrev; ctx.print_email_subject = 1; - ctx.date_mode.type = DATE_NORMAL; + ctx.date_mode = log->date_mode; ctx.output_encoding = get_log_output_encoding(); if (!log->summary) { @@ -222,30 +252,10 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit) } oneline_str = oneline.len ? oneline.buf : "<none>"; - if (log->groups & SHORTLOG_GROUP_AUTHOR) { - strbuf_reset(&ident); - format_commit_message(commit, - log->email ? "%aN <%aE>" : "%aN", - &ident, &ctx); - if (!HAS_MULTI_BITS(log->groups) || - strset_add(&dups, ident.buf)) - insert_one_record(log, ident.buf, oneline_str); - } - if (log->groups & SHORTLOG_GROUP_COMMITTER) { - strbuf_reset(&ident); - format_commit_message(commit, - log->email ? "%cN <%cE>" : "%cN", - &ident, &ctx); - if (!HAS_MULTI_BITS(log->groups) || - strset_add(&dups, ident.buf)) - insert_one_record(log, ident.buf, oneline_str); - } - if (log->groups & SHORTLOG_GROUP_TRAILER) { - insert_records_from_trailers(log, &dups, commit, &ctx, oneline_str); - } + insert_records_from_trailers(log, &dups, commit, &ctx, oneline_str); + insert_records_from_format(log, &dups, commit, &ctx, oneline_str); strset_clear(&dups); - strbuf_release(&ident); strbuf_release(&oneline); } @@ -314,6 +324,7 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns if (unset) { log->groups = 0; string_list_clear(&log->trailers, 0); + string_list_clear(&log->format, 0); } else if (!strcasecmp(arg, "author")) log->groups |= SHORTLOG_GROUP_AUTHOR; else if (!strcasecmp(arg, "committer")) @@ -321,8 +332,15 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns else if (skip_prefix(arg, "trailer:", &field)) { log->groups |= SHORTLOG_GROUP_TRAILER; string_list_append(&log->trailers, field); - } else + } else if (skip_prefix(arg, "format:", &field)) { + log->groups |= SHORTLOG_GROUP_FORMAT; + string_list_append(&log->format, field); + } else if (strchr(arg, '%')) { + log->groups |= SHORTLOG_GROUP_FORMAT; + string_list_append(&log->format, arg); + } else { return error(_("unknown group type: %s"), arg); + } return 0; } @@ -340,6 +358,19 @@ void shortlog_init(struct shortlog *log) log->in2 = DEFAULT_INDENT2; log->trailers.strdup_strings = 1; log->trailers.cmp = strcasecmp; + log->format.strdup_strings = 1; +} + +void shortlog_finish_setup(struct shortlog *log) +{ + if (log->groups & SHORTLOG_GROUP_AUTHOR) + string_list_append(&log->format, + log->email ? "%aN <%aE>" : "%aN"); + if (log->groups & SHORTLOG_GROUP_COMMITTER) + string_list_append(&log->format, + log->email ? "%cN <%cE>" : "%cN"); + + string_list_sort(&log->trailers); } int cmd_shortlog(int argc, const char **argv, const char *prefix) @@ -407,10 +438,11 @@ parse_done: log.user_format = rev.commit_format == CMIT_FMT_USERFORMAT; log.abbrev = rev.abbrev; log.file = rev.diffopt.file; + log.date_mode = rev.date_mode; if (!log.groups) log.groups = SHORTLOG_GROUP_AUTHOR; - string_list_sort(&log.trailers); + shortlog_finish_setup(&log); /* assume HEAD if from a tty */ if (!nongit && !rev.pending.nr && isatty(0)) @@ -479,4 +511,5 @@ void shortlog_output(struct shortlog *log) log->list.strdup_strings = 1; string_list_clear(&log->list, 1); clear_mailmap(&log->mailmap); + string_list_clear(&log->format, 0); } diff --git a/bundle-uri.c b/bundle-uri.c index 4a8cc74ed0..79a914f961 100644 --- a/bundle-uri.c +++ b/bundle-uri.c @@ -4,23 +4,221 @@ #include "object-store.h" #include "refs.h" #include "run-command.h" +#include "hashmap.h" +#include "pkt-line.h" +#include "config.h" -static int find_temp_filename(struct strbuf *name) +static int compare_bundles(const void *hashmap_cmp_fn_data, + const struct hashmap_entry *he1, + const struct hashmap_entry *he2, + const void *id) +{ + const struct remote_bundle_info *e1 = + container_of(he1, const struct remote_bundle_info, ent); + const struct remote_bundle_info *e2 = + container_of(he2, const struct remote_bundle_info, ent); + + return strcmp(e1->id, id ? (const char *)id : e2->id); +} + +void init_bundle_list(struct bundle_list *list) +{ + memset(list, 0, sizeof(*list)); + + /* Implied defaults. */ + list->mode = BUNDLE_MODE_ALL; + list->version = 1; + + hashmap_init(&list->bundles, compare_bundles, NULL, 0); +} + +static int clear_remote_bundle_info(struct remote_bundle_info *bundle, + void *data) +{ + FREE_AND_NULL(bundle->id); + FREE_AND_NULL(bundle->uri); + FREE_AND_NULL(bundle->file); + bundle->unbundled = 0; + return 0; +} + +void clear_bundle_list(struct bundle_list *list) +{ + if (!list) + return; + + for_all_bundles_in_list(list, clear_remote_bundle_info, NULL); + hashmap_clear_and_free(&list->bundles, struct remote_bundle_info, ent); +} + +int for_all_bundles_in_list(struct bundle_list *list, + bundle_iterator iter, + void *data) +{ + struct remote_bundle_info *info; + struct hashmap_iter i; + + hashmap_for_each_entry(&list->bundles, &i, info, ent) { + int result = iter(info, data); + + if (result) + return result; + } + + return 0; +} + +static int summarize_bundle(struct remote_bundle_info *info, void *data) +{ + FILE *fp = data; + fprintf(fp, "[bundle \"%s\"]\n", info->id); + fprintf(fp, "\turi = %s\n", info->uri); + return 0; +} + +void print_bundle_list(FILE *fp, struct bundle_list *list) +{ + const char *mode; + + switch (list->mode) { + case BUNDLE_MODE_ALL: + mode = "all"; + break; + + case BUNDLE_MODE_ANY: + mode = "any"; + break; + + case BUNDLE_MODE_NONE: + default: + mode = "<unknown>"; + } + + fprintf(fp, "[bundle]\n"); + fprintf(fp, "\tversion = %d\n", list->version); + fprintf(fp, "\tmode = %s\n", mode); + + for_all_bundles_in_list(list, summarize_bundle, fp); +} + +/** + * Given a key-value pair, update the state of the given bundle list. + * Returns 0 if the key-value pair is understood. Returns -1 if the key + * is not understood or the value is malformed. + */ +static int bundle_list_update(const char *key, const char *value, + struct bundle_list *list) +{ + struct strbuf id = STRBUF_INIT; + struct remote_bundle_info lookup = REMOTE_BUNDLE_INFO_INIT; + struct remote_bundle_info *bundle; + const char *subsection, *subkey; + size_t subsection_len; + + if (parse_config_key(key, "bundle", &subsection, &subsection_len, &subkey)) + return -1; + + if (!subsection_len) { + if (!strcmp(subkey, "version")) { + int version; + if (!git_parse_int(value, &version)) + return -1; + if (version != 1) + return -1; + + list->version = version; + return 0; + } + + if (!strcmp(subkey, "mode")) { + if (!strcmp(value, "all")) + list->mode = BUNDLE_MODE_ALL; + else if (!strcmp(value, "any")) + list->mode = BUNDLE_MODE_ANY; + else + return -1; + return 0; + } + + /* Ignore other unknown global keys. */ + return 0; + } + + strbuf_add(&id, subsection, subsection_len); + + /* + * Check for an existing bundle with this <id>, or create one + * if necessary. + */ + lookup.id = id.buf; + hashmap_entry_init(&lookup.ent, strhash(lookup.id)); + if (!(bundle = hashmap_get_entry(&list->bundles, &lookup, ent, NULL))) { + CALLOC_ARRAY(bundle, 1); + bundle->id = strbuf_detach(&id, NULL); + hashmap_entry_init(&bundle->ent, strhash(bundle->id)); + hashmap_add(&list->bundles, &bundle->ent); + } + strbuf_release(&id); + + if (!strcmp(subkey, "uri")) { + if (bundle->uri) + return -1; + bundle->uri = xstrdup(value); + return 0; + } + + /* + * At this point, we ignore any information that we don't + * understand, assuming it to be hints for a heuristic the client + * does not currently understand. + */ + return 0; +} + +static int config_to_bundle_list(const char *key, const char *value, void *data) +{ + struct bundle_list *list = data; + return bundle_list_update(key, value, list); +} + +int bundle_uri_parse_config_format(const char *uri, + const char *filename, + struct bundle_list *list) +{ + int result; + struct config_options opts = { + .error_action = CONFIG_ERROR_ERROR, + }; + + result = git_config_from_file_with_options(config_to_bundle_list, + filename, list, + &opts); + + if (!result && list->mode == BUNDLE_MODE_NONE) { + warning(_("bundle list at '%s' has no mode"), uri); + result = 1; + } + + return result; +} + +static char *find_temp_filename(void) { int fd; + struct strbuf name = STRBUF_INIT; /* * Find a temporary filename that is available. This is briefly * racy, but unlikely to collide. */ - fd = odb_mkstemp(name, "bundles/tmp_uri_XXXXXX"); + fd = odb_mkstemp(&name, "bundles/tmp_uri_XXXXXX"); if (fd < 0) { warning(_("failed to create temporary file")); - return -1; + return NULL; } close(fd); - unlink(name->buf); - return 0; + unlink(name.buf); + return strbuf_detach(&name, NULL); } static int download_https_uri_to_file(const char *file, const char *uri) @@ -32,6 +230,7 @@ static int download_https_uri_to_file(const char *file, const char *uri) int found_get = 0; strvec_pushl(&cp.args, "git-remote-https", uri, NULL); + cp.err = -1; cp.in = -1; cp.out = -1; @@ -105,7 +304,13 @@ static int unbundle_from_file(struct repository *r, const char *file) if ((bundle_fd = read_bundle_header(file, &header)) < 0) return 1; - if ((result = unbundle(r, &header, bundle_fd, NULL))) + /* + * Skip the reachability walk here, since we will be adding + * a reachable ref pointing to the new tips, which will reach + * the prerequisite commits. + */ + if ((result = unbundle(r, &header, bundle_fd, NULL, + VERIFY_BUNDLE_QUIET))) return 1; /* @@ -138,31 +343,248 @@ static int unbundle_from_file(struct repository *r, const char *file) return result; } -int fetch_bundle_uri(struct repository *r, const char *uri) +struct bundle_list_context { + struct repository *r; + struct bundle_list *list; + enum bundle_list_mode mode; + int count; + int depth; +}; + +/* + * This early definition is necessary because we use indirect recursion: + * + * While iterating through a bundle list that was downloaded as part + * of fetch_bundle_uri_internal(), iterator methods eventually call it + * again, but with depth + 1. + */ +static int fetch_bundle_uri_internal(struct repository *r, + struct remote_bundle_info *bundle, + int depth, + struct bundle_list *list); + +static int download_bundle_to_file(struct remote_bundle_info *bundle, void *data) { - int result = 0; - struct strbuf filename = STRBUF_INIT; + int res; + struct bundle_list_context *ctx = data; + + if (ctx->mode == BUNDLE_MODE_ANY && ctx->count) + return 0; + + res = fetch_bundle_uri_internal(ctx->r, bundle, ctx->depth + 1, ctx->list); + + /* + * Only increment count if the download succeeded. If our mode is + * BUNDLE_MODE_ANY, then we will want to try other URIs in the + * list in case they work instead. + */ + if (!res) + ctx->count++; + + /* + * To be opportunistic as possible, we continue iterating and + * download as many bundles as we can, so we can apply the ones + * that work, even in BUNDLE_MODE_ALL mode. + */ + return 0; +} + +static int download_bundle_list(struct repository *r, + struct bundle_list *local_list, + struct bundle_list *global_list, + int depth) +{ + struct bundle_list_context ctx = { + .r = r, + .list = global_list, + .depth = depth + 1, + .mode = local_list->mode, + }; + + return for_all_bundles_in_list(local_list, download_bundle_to_file, &ctx); +} + +static int fetch_bundle_list_in_config_format(struct repository *r, + struct bundle_list *global_list, + struct remote_bundle_info *bundle, + int depth) +{ + int result; + struct bundle_list list_from_bundle; - if ((result = find_temp_filename(&filename))) + init_bundle_list(&list_from_bundle); + + if ((result = bundle_uri_parse_config_format(bundle->uri, + bundle->file, + &list_from_bundle))) goto cleanup; - if ((result = copy_uri_to_file(filename.buf, uri))) { - warning(_("failed to download bundle from URI '%s'"), uri); + if (list_from_bundle.mode == BUNDLE_MODE_NONE) { + warning(_("unrecognized bundle mode from URI '%s'"), + bundle->uri); + result = -1; goto cleanup; } - if ((result = !is_bundle(filename.buf, 0))) { - warning(_("file at URI '%s' is not a bundle"), uri); + if ((result = download_bundle_list(r, &list_from_bundle, + global_list, depth))) goto cleanup; + +cleanup: + clear_bundle_list(&list_from_bundle); + return result; +} + +/** + * This limits the recursion on fetch_bundle_uri_internal() when following + * bundle lists. + */ +static int max_bundle_uri_depth = 4; + +/** + * Recursively download all bundles advertised at the given URI + * to files. If the file is a bundle, then add it to the given + * 'list'. Otherwise, expect a bundle list and recurse on the + * URIs in that list according to the list mode (ANY or ALL). + */ +static int fetch_bundle_uri_internal(struct repository *r, + struct remote_bundle_info *bundle, + int depth, + struct bundle_list *list) +{ + int result = 0; + struct remote_bundle_info *bcopy; + + if (depth >= max_bundle_uri_depth) { + warning(_("exceeded bundle URI recursion limit (%d)"), + max_bundle_uri_depth); + return -1; } - if ((result = unbundle_from_file(r, filename.buf))) { - warning(_("failed to unbundle bundle from URI '%s'"), uri); + if (!bundle->file && + !(bundle->file = find_temp_filename())) { + result = -1; goto cleanup; } + if ((result = copy_uri_to_file(bundle->file, bundle->uri))) { + warning(_("failed to download bundle from URI '%s'"), bundle->uri); + goto cleanup; + } + + if ((result = !is_bundle(bundle->file, 1))) { + result = fetch_bundle_list_in_config_format( + r, list, bundle, depth); + if (result) + warning(_("file at URI '%s' is not a bundle or bundle list"), + bundle->uri); + goto cleanup; + } + + /* Copy the bundle and insert it into the global list. */ + CALLOC_ARRAY(bcopy, 1); + bcopy->id = xstrdup(bundle->id); + bcopy->file = xstrdup(bundle->file); + hashmap_entry_init(&bcopy->ent, strhash(bcopy->id)); + hashmap_add(&list->bundles, &bcopy->ent); + cleanup: - unlink(filename.buf); - strbuf_release(&filename); + if (result && bundle->file) + unlink(bundle->file); + return result; +} + +/** + * This loop iterator breaks the loop with nonzero return code on the + * first successful unbundling of a bundle. + */ +static int attempt_unbundle(struct remote_bundle_info *info, void *data) +{ + struct repository *r = data; + + if (!info->file || info->unbundled) + return 0; + + if (!unbundle_from_file(r, info->file)) { + info->unbundled = 1; + return 1; + } + + return 0; +} + +static int unbundle_all_bundles(struct repository *r, + struct bundle_list *list) +{ + /* + * Iterate through all bundles looking for ones that can + * successfully unbundle. If any succeed, then perhaps another + * will succeed in the next attempt. + * + * Keep in mind that a non-zero result for the loop here means + * the loop terminated early on a successful unbundling, which + * signals that we can try again. + */ + while (for_all_bundles_in_list(list, attempt_unbundle, r)) ; + + return 0; +} + +static int unlink_bundle(struct remote_bundle_info *info, void *data) +{ + if (info->file) + unlink_or_warn(info->file); + return 0; +} + +int fetch_bundle_uri(struct repository *r, const char *uri) +{ + int result; + struct bundle_list list; + struct remote_bundle_info bundle = { + .uri = xstrdup(uri), + .id = xstrdup(""), + }; + + init_bundle_list(&list); + + /* If a bundle is added to this global list, then it is required. */ + list.mode = BUNDLE_MODE_ALL; + + if ((result = fetch_bundle_uri_internal(r, &bundle, 0, &list))) + goto cleanup; + + result = unbundle_all_bundles(r, &list); + +cleanup: + for_all_bundles_in_list(&list, unlink_bundle, NULL); + clear_bundle_list(&list); + clear_remote_bundle_info(&bundle, NULL); + return result; +} + +/** + * General API for {transport,connect}.c etc. + */ +int bundle_uri_parse_line(struct bundle_list *list, const char *line) +{ + int result; + const char *equals; + struct strbuf key = STRBUF_INIT; + + if (!strlen(line)) + return error(_("bundle-uri: got an empty line")); + + equals = strchr(line, '='); + + if (!equals) + return error(_("bundle-uri: line is not of the form 'key=value'")); + if (line == equals || !*(equals + 1)) + return error(_("bundle-uri: line has empty key or value")); + + strbuf_add(&key, line, equals - line); + result = bundle_list_update(key.buf, equals + 1, list); + strbuf_release(&key); + return result; } diff --git a/bundle-uri.h b/bundle-uri.h index 8a152f1ef1..4dbc269823 100644 --- a/bundle-uri.h +++ b/bundle-uri.h @@ -1,7 +1,88 @@ #ifndef BUNDLE_URI_H #define BUNDLE_URI_H +#include "hashmap.h" +#include "strbuf.h" + struct repository; +struct string_list; + +/** + * The remote_bundle_info struct contains information for a single bundle + * URI. This may be initialized simply by a given URI or might have + * additional metadata associated with it if the bundle was advertised by + * a bundle list. + */ +struct remote_bundle_info { + struct hashmap_entry ent; + + /** + * The 'id' is a name given to the bundle for reference + * by other bundle infos. + */ + char *id; + + /** + * The 'uri' is the location of the remote bundle so + * it can be downloaded on-demand. This will be NULL + * if there was no table of contents. + */ + char *uri; + + /** + * If the bundle has been downloaded, then 'file' is a + * filename storing its contents. Otherwise, 'file' is + * NULL. + */ + char *file; + + /** + * If the bundle has been unbundled successfully, then + * this boolean is true. + */ + unsigned unbundled:1; +}; + +#define REMOTE_BUNDLE_INFO_INIT { 0 } + +enum bundle_list_mode { + BUNDLE_MODE_NONE = 0, + BUNDLE_MODE_ALL, + BUNDLE_MODE_ANY +}; + +/** + * A bundle_list contains an unordered set of remote_bundle_info structs, + * as well as information about the bundle listing, such as version and + * mode. + */ +struct bundle_list { + int version; + enum bundle_list_mode mode; + struct hashmap bundles; +}; + +void init_bundle_list(struct bundle_list *list); +void clear_bundle_list(struct bundle_list *list); + +typedef int (*bundle_iterator)(struct remote_bundle_info *bundle, + void *data); + +int for_all_bundles_in_list(struct bundle_list *list, + bundle_iterator iter, + void *data); + +struct FILE; +void print_bundle_list(FILE *fp, struct bundle_list *list); + +/** + * A bundle URI may point to a bundle list where the key=value + * pairs are provided in config file format. This method is + * exposed publicly for testing purposes. + */ +int bundle_uri_parse_config_format(const char *uri, + const char *filename, + struct bundle_list *list); /** * Fetch data from the given 'uri' and unbundle the bundle data found @@ -11,4 +92,16 @@ struct repository; */ int fetch_bundle_uri(struct repository *r, const char *uri); +/** + * General API for {transport,connect}.c etc. + */ + +/** + * Parse a "key=value" packet line from the bundle-uri verb. + * + * Returns 0 on success and non-zero on error. + */ +int bundle_uri_parse_line(struct bundle_list *list, + const char *line); + #endif @@ -189,7 +189,7 @@ static int list_refs(struct string_list *r, int argc, const char **argv) int verify_bundle(struct repository *r, struct bundle_header *header, - int verbose) + enum verify_bundle_flags flags) { /* * Do fast check, then if any prereqs are missing then go line by line @@ -202,10 +202,8 @@ int verify_bundle(struct repository *r, int i, ret = 0, req_nr; const char *message = _("Repository lacks these prerequisite commits:"); - if (!r || !r->objects || !r->objects->odb) { - ret = error(_("need a repository to verify a bundle")); - goto cleanup; - } + if (!r || !r->objects || !r->objects->odb) + return error(_("need a repository to verify a bundle")); repo_init_revisions(r, &revs, NULL); for (i = 0; i < p->nr; i++) { @@ -218,7 +216,10 @@ int verify_bundle(struct repository *r, add_pending_object(&revs, o, name); continue; } - if (++ret == 1) + ret++; + if (flags & VERIFY_BUNDLE_QUIET) + continue; + if (ret == 1) error("%s", message); error("%s %s", oid_to_hex(oid), name); } @@ -245,21 +246,15 @@ int verify_bundle(struct repository *r, assert(o); /* otherwise we'd have returned early */ if (o->flags & SHOWN) continue; - if (++ret == 1) + ret++; + if (flags & VERIFY_BUNDLE_QUIET) + continue; + if (ret == 1) error("%s", message); error("%s %s", oid_to_hex(oid), name); } - /* Clean up objects used, as they will be reused. */ - for (i = 0; i < p->nr; i++) { - struct string_list_item *e = p->items + i; - struct object_id *oid = e->util; - commit = lookup_commit_reference_gently(r, oid, 1); - if (commit) - clear_commit_marks(commit, ALL_REV_FLAGS); - } - - if (verbose) { + if (flags & VERIFY_BUNDLE_VERBOSE) { struct string_list *r; r = &header->references; @@ -287,6 +282,14 @@ int verify_bundle(struct repository *r, list_objects_filter_spec(&header->filter)); } cleanup: + /* Clean up objects used, as they will be reused. */ + for (i = 0; i < p->nr; i++) { + struct string_list_item *e = p->items + i; + struct object_id *oid = e->util; + commit = lookup_commit_reference_gently(r, oid, 1); + if (commit) + clear_commit_marks(commit, ALL_REV_FLAGS | PREREQ_MARK); + } release_revisions(&revs); return ret; } @@ -620,7 +623,8 @@ err: } int unbundle(struct repository *r, struct bundle_header *header, - int bundle_fd, struct strvec *extra_index_pack_args) + int bundle_fd, struct strvec *extra_index_pack_args, + enum verify_bundle_flags flags) { struct child_process ip = CHILD_PROCESS_INIT; strvec_pushl(&ip.args, "index-pack", "--fix-thin", "--stdin", NULL); @@ -634,7 +638,7 @@ int unbundle(struct repository *r, struct bundle_header *header, strvec_clear(extra_index_pack_args); } - if (verify_bundle(r, header, 0)) + if (verify_bundle(r, header, flags)) return -1; ip.in = bundle_fd; ip.no_stdout = 1; @@ -30,7 +30,14 @@ int read_bundle_header_fd(int fd, struct bundle_header *header, int create_bundle(struct repository *r, const char *path, int argc, const char **argv, struct strvec *pack_options, int version); -int verify_bundle(struct repository *r, struct bundle_header *header, int verbose); + +enum verify_bundle_flags { + VERIFY_BUNDLE_VERBOSE = (1 << 0), + VERIFY_BUNDLE_QUIET = (1 << 1), +}; + +int verify_bundle(struct repository *r, struct bundle_header *header, + enum verify_bundle_flags flags); /** * Unbundle after reading the header with read_bundle_header(). @@ -41,9 +48,13 @@ int verify_bundle(struct repository *r, struct bundle_header *header, int verbos * Provide "extra_index_pack_args" to pass any extra arguments * (e.g. "-v" for verbose/progress), NULL otherwise. The provided * "extra_index_pack_args" (if any) will be strvec_clear()'d for you. + * + * Before unbundling, this method will call verify_bundle() with the + * given 'flags'. */ int unbundle(struct repository *r, struct bundle_header *header, - int bundle_fd, struct strvec *extra_index_pack_args); + int bundle_fd, struct strvec *extra_index_pack_args, + enum verify_bundle_flags flags); int list_bundle_refs(struct bundle_header *header, int argc, const char **argv); @@ -59,6 +59,14 @@ struct commit *lookup_commit_or_die(const struct object_id *oid, const char *ref return c; } +struct commit *lookup_commit_object(struct repository *r, + const struct object_id *oid) +{ + struct object *obj = parse_object(r, oid); + return obj ? object_as_type(obj, OBJ_COMMIT, 0) : NULL; + +} + struct commit *lookup_commit(struct repository *r, const struct object_id *oid) { struct object *obj = lookup_object(r, oid); @@ -64,6 +64,19 @@ enum decoration_type { void add_name_decoration(enum decoration_type type, const char *name, struct object *obj); const struct name_decoration *get_name_decoration(const struct object *obj); +/* + * Look up commit named by "oid" respecting replacement objects. + * Returns NULL if "oid" is not a commit or does not exist. + */ +struct commit *lookup_commit_object(struct repository *r, const struct object_id *oid); + +/* + * Look up commit named by "oid" without replacement objects or + * checking for object existence. Returns the requested commit if it + * is found in the object cache, NULL if "oid" is in the object cache + * but is not a commit and a newly allocated unparsed commit object if + * "oid" is not in the object cache. + */ struct commit *lookup_commit(struct repository *r, const struct object_id *oid); struct commit *lookup_commit_reference(struct repository *r, const struct object_id *oid); @@ -1215,7 +1215,7 @@ static int git_parse_unsigned(const char *value, uintmax_t *ret, uintmax_t max) return 0; } -static int git_parse_int(const char *value, int *ret) +int git_parse_int(const char *value, int *ret) { intmax_t tmp; if (!git_parse_signed(value, &tmp, maximum_signed_value_of_type(int))) @@ -206,6 +206,7 @@ int config_with_options(config_fn_t fn, void *, int git_parse_ssize_t(const char *, ssize_t *); int git_parse_ulong(const char *, unsigned long *); +int git_parse_int(const char *value, int *ret); /** * Same as `git_config_bool`, except that it returns -1 on error rather diff --git a/contrib/subtree/git-subtree.sh b/contrib/subtree/git-subtree.sh index 7562a395c2..10c9c87839 100755 --- a/contrib/subtree/git-subtree.sh +++ b/contrib/subtree/git-subtree.sh @@ -98,10 +98,18 @@ progress () { assert () { if ! "$@" then - die "assertion failed: $*" + die "fatal: assertion failed: $*" fi } +# Usage: die_incompatible_opt OPTION COMMAND +die_incompatible_opt () { + assert test "$#" = 2 + opt="$1" + arg_command="$2" + die "fatal: the '$opt' flag does not make sense with 'git subtree $arg_command'." +} + main () { if test $# -eq 0 then @@ -147,7 +155,7 @@ main () { allow_addmerge=$arg_split_rejoin ;; *) - die "Unknown command '$arg_command'" + die "fatal: unknown command '$arg_command'" ;; esac # Reset the arguments array for "real" flag parsing. @@ -176,16 +184,16 @@ main () { arg_debug=1 ;; --annotate) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_annotate="$1" shift ;; --no-annotate) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_annotate= ;; -b) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_branch="$1" shift ;; @@ -194,7 +202,7 @@ main () { shift ;; -m) - test -n "$allow_addmerge" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_addmerge" || die_incompatible_opt "$opt" "$arg_command" arg_addmerge_message="$1" shift ;; @@ -202,41 +210,41 @@ main () { arg_prefix= ;; --onto) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_onto="$1" shift ;; --no-onto) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_onto= ;; --rejoin) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" ;; --no-rejoin) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" ;; --ignore-joins) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_ignore_joins=1 ;; --no-ignore-joins) - test -n "$allow_split" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_split" || die_incompatible_opt "$opt" "$arg_command" arg_split_ignore_joins= ;; --squash) - test -n "$allow_addmerge" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_addmerge" || die_incompatible_opt "$opt" "$arg_command" arg_addmerge_squash=1 ;; --no-squash) - test -n "$allow_addmerge" || die "The '$opt' flag does not make sense with 'git subtree $arg_command'." + test -n "$allow_addmerge" || die_incompatible_opt "$opt" "$arg_command" arg_addmerge_squash= ;; --) break ;; *) - die "Unexpected option: $opt" + die "fatal: unexpected option: $opt" ;; esac done @@ -244,17 +252,17 @@ main () { if test -z "$arg_prefix" then - die "You must provide the --prefix option." + die "fatal: you must provide the --prefix option." fi case "$arg_command" in add) test -e "$arg_prefix" && - die "prefix '$arg_prefix' already exists." + die "fatal: prefix '$arg_prefix' already exists." ;; *) test -e "$arg_prefix" || - die "'$arg_prefix' does not exist; use 'git subtree add'" + die "fatal: '$arg_prefix' does not exist; use 'git subtree add'" ;; esac @@ -274,11 +282,11 @@ cache_setup () { assert test $# = 0 cachedir="$GIT_DIR/subtree-cache/$$" rm -rf "$cachedir" || - die "Can't delete old cachedir: $cachedir" + die "fatal: can't delete old cachedir: $cachedir" mkdir -p "$cachedir" || - die "Can't create new cachedir: $cachedir" + die "fatal: can't create new cachedir: $cachedir" mkdir -p "$cachedir/notree" || - die "Can't create new cachedir: $cachedir/notree" + die "fatal: can't create new cachedir: $cachedir/notree" debug "Using cachedir: $cachedir" >&2 } @@ -334,7 +342,7 @@ cache_set () { test "$oldrev" != "latest_new" && test -e "$cachedir/$oldrev" then - die "cache for $oldrev already exists!" + die "fatal: cache for $oldrev already exists!" fi echo "$newrev" >"$cachedir/$oldrev" } @@ -363,13 +371,47 @@ try_remove_previous () { fi } -# Usage: find_latest_squash DIR +# Usage: process_subtree_split_trailer SPLIT_HASH MAIN_HASH [REPOSITORY] +process_subtree_split_trailer () { + assert test $# = 2 -o $# = 3 + b="$1" + sq="$2" + repository="" + if test "$#" = 3 + then + repository="$3" + fi + fail_msg="fatal: could not rev-parse split hash $b from commit $sq" + if ! sub="$(git rev-parse --verify --quiet "$b^{commit}")" + then + # if 'repository' was given, try to fetch the 'git-subtree-split' hash + # before 'rev-parse'-ing it again, as it might be a tag that we do not have locally + if test -n "${repository}" + then + git fetch "$repository" "$b" + sub="$(git rev-parse --verify --quiet "$b^{commit}")" || + die "$fail_msg" + else + hint1=$(printf "hint: hash might be a tag, try fetching it from the subtree repository:") + hint2=$(printf "hint: git fetch <subtree-repository> $b") + fail_msg=$(printf "$fail_msg\n$hint1\n$hint2") + die "$fail_msg" + fi + fi +} + +# Usage: find_latest_squash DIR [REPOSITORY] find_latest_squash () { - assert test $# = 1 - debug "Looking for latest squash ($dir)..." + assert test $# = 1 -o $# = 2 + dir="$1" + repository="" + if test "$#" = 2 + then + repository="$2" + fi + debug "Looking for latest squash (dir=$dir, repository=$repository)..." local indent=$(($indent + 1)) - dir="$1" sq= main= sub= @@ -387,8 +429,7 @@ find_latest_squash () { main="$b" ;; git-subtree-split:) - sub="$(git rev-parse "$b^{commit}")" || - die "could not rev-parse split hash $b from commit $sq" + process_subtree_split_trailer "$b" "$sq" "$repository" ;; END) if test -n "$sub" @@ -412,14 +453,19 @@ find_latest_squash () { done || exit $? } -# Usage: find_existing_splits DIR REV +# Usage: find_existing_splits DIR REV [REPOSITORY] find_existing_splits () { - assert test $# = 2 + assert test $# = 2 -o $# = 3 debug "Looking for prior splits..." local indent=$(($indent + 1)) dir="$1" rev="$2" + repository="" + if test "$#" = 3 + then + repository="$3" + fi main= sub= local grep_format="^git-subtree-dir: $dir/*\$" @@ -439,8 +485,7 @@ find_existing_splits () { main="$b" ;; git-subtree-split:) - sub="$(git rev-parse "$b^{commit}")" || - die "could not rev-parse split hash $b from commit $sq" + process_subtree_split_trailer "$b" "$sq" "$repository" ;; END) debug "Main is: '$main'" @@ -490,7 +535,7 @@ copy_commit () { cat ) | git commit-tree "$2" $3 # reads the rest of stdin - ) || die "Can't copy commit $1" + ) || die "fatal: can't copy commit $1" } # Usage: add_msg DIR LATEST_OLD LATEST_NEW @@ -718,11 +763,11 @@ ensure_clean () { assert test $# = 0 if ! git diff-index HEAD --exit-code --quiet 2>&1 then - die "Working tree has modifications. Cannot add." + die "fatal: working tree has modifications. Cannot add." fi if ! git diff-index --cached HEAD --exit-code --quiet 2>&1 then - die "Index has modifications. Cannot add." + die "fatal: index has modifications. Cannot add." fi } @@ -730,7 +775,7 @@ ensure_clean () { ensure_valid_ref_format () { assert test $# = 1 git check-ref-format "refs/heads/$1" || - die "'$1' does not look like a ref" + die "fatal: '$1' does not look like a ref" } # Usage: process_split_commit REV PARENTS @@ -796,7 +841,7 @@ cmd_add () { if test $# -eq 1 then git rev-parse -q --verify "$1^{commit}" >/dev/null || - die "'$1' does not refer to a commit" + die "fatal: '$1' does not refer to a commit" cmd_add_commit "$@" @@ -811,7 +856,7 @@ cmd_add () { cmd_add_repository "$@" else - say >&2 "error: parameters were '$*'" + say >&2 "fatal: parameters were '$*'" die "Provide either a commit or a repository and commit." fi } @@ -843,7 +888,7 @@ cmd_add_commit () { git checkout -- "$dir" || exit $? tree=$(git write-tree) || exit $? - headrev=$(git rev-parse HEAD) || exit $? + headrev=$(git rev-parse --verify HEAD) || exit $? if test -n "$headrev" && test "$headrev" != "$rev" then headp="-p $headrev" @@ -866,17 +911,22 @@ cmd_add_commit () { say >&2 "Added dir '$dir'" } -# Usage: cmd_split [REV] +# Usage: cmd_split [REV] [REPOSITORY] cmd_split () { if test $# -eq 0 then rev=$(git rev-parse HEAD) - elif test $# -eq 1 + elif test $# -eq 1 -o $# -eq 2 then rev=$(git rev-parse -q --verify "$1^{commit}") || - die "'$1' does not refer to a commit" + die "fatal: '$1' does not refer to a commit" else - die "You must provide exactly one revision. Got: '$*'" + die "fatal: you must provide exactly one revision, and optionnally a repository. Got: '$*'" + fi + repository="" + if test "$#" = 2 + then + repository="$2" fi if test -n "$arg_split_rejoin" @@ -900,7 +950,7 @@ cmd_split () { done || exit $? fi - unrevs="$(find_existing_splits "$dir" "$rev")" || exit $? + unrevs="$(find_existing_splits "$dir" "$rev" "$repository")" || exit $? # We can't restrict rev-list to only $dir here, because some of our # parents have the $dir contents the root, and those won't match. @@ -919,7 +969,7 @@ cmd_split () { latest_new=$(cache_get latest_new) || exit $? if test -z "$latest_new" then - die "No new revisions were found" + die "fatal: no new revisions were found" fi if test -n "$arg_split_rejoin" @@ -940,7 +990,7 @@ cmd_split () { then if ! git merge-base --is-ancestor "$arg_split_branch" "$latest_new" then - die "Branch '$arg_split_branch' is not an ancestor of commit '$latest_new'." + die "fatal: branch '$arg_split_branch' is not an ancestor of commit '$latest_new'." fi action='Updated' else @@ -954,20 +1004,25 @@ cmd_split () { exit 0 } -# Usage: cmd_merge REV +# Usage: cmd_merge REV [REPOSITORY] cmd_merge () { - test $# -eq 1 || - die "You must provide exactly one revision. Got: '$*'" + test $# -eq 1 -o $# -eq 2 || + die "fatal: you must provide exactly one revision, and optionally a repository. Got: '$*'" rev=$(git rev-parse -q --verify "$1^{commit}") || - die "'$1' does not refer to a commit" + die "fatal: '$1' does not refer to a commit" + repository="" + if test "$#" = 2 + then + repository="$2" + fi ensure_clean if test -n "$arg_addmerge_squash" then - first_split="$(find_latest_squash "$dir")" || exit $? + first_split="$(find_latest_squash "$dir" "$repository")" || exit $? if test -z "$first_split" then - die "Can't squash-merge: '$dir' was never added." + die "fatal: can't squash-merge: '$dir' was never added." fi set $first_split old=$1 @@ -995,19 +1050,21 @@ cmd_merge () { cmd_pull () { if test $# -ne 2 then - die "You must provide <repository> <ref>" + die "fatal: you must provide <repository> <ref>" fi + repository="$1" + ref="$2" ensure_clean - ensure_valid_ref_format "$2" - git fetch "$@" || exit $? - cmd_merge FETCH_HEAD + ensure_valid_ref_format "$ref" + git fetch "$repository" "$ref" || exit $? + cmd_merge FETCH_HEAD "$repository" } # Usage: cmd_push REPOSITORY [+][LOCALREV:]REMOTEREF cmd_push () { if test $# -ne 2 then - die "You must provide <repository> <refspec>" + die "fatal: you must provide <repository> <refspec>" fi if test -e "$dir" then @@ -1022,13 +1079,13 @@ cmd_push () { fi ensure_valid_ref_format "$remoteref" localrev_presplit=$(git rev-parse -q --verify "$localrevname_presplit^{commit}") || - die "'$localrevname_presplit' does not refer to a commit" + die "fatal: '$localrevname_presplit' does not refer to a commit" echo "git push using: " "$repository" "$refspec" - localrev=$(cmd_split "$localrev_presplit") || die + localrev=$(cmd_split "$localrev_presplit" "$repository") || die git push "$repository" "$localrev":"refs/heads/$remoteref" else - die "'$dir' must already exist. Try 'git subtree add'." + die "fatal: '$dir' must already exist. Try 'git subtree add'." fi } diff --git a/contrib/subtree/git-subtree.txt b/contrib/subtree/git-subtree.txt index 9cddfa2654..004abf415b 100644 --- a/contrib/subtree/git-subtree.txt +++ b/contrib/subtree/git-subtree.txt @@ -11,7 +11,7 @@ SYNOPSIS [verse] 'git subtree' [<options>] -P <prefix> add <local-commit> 'git subtree' [<options>] -P <prefix> add <repository> <remote-ref> -'git subtree' [<options>] -P <prefix> merge <local-commit> +'git subtree' [<options>] -P <prefix> merge <local-commit> [<repository>] 'git subtree' [<options>] -P <prefix> split [<local-commit>] [verse] @@ -76,7 +76,7 @@ add <repository> <remote-ref>:: only a single commit from the subproject, rather than its entire history. -merge <local-commit>:: +merge <local-commit> [<repository>]:: Merge recent changes up to <local-commit> into the <prefix> subtree. As with normal 'git merge', this doesn't remove your own local changes; it just merges those @@ -88,8 +88,13 @@ If you use '--squash', the merge direction doesn't always have to be forward; you can use this command to go back in time from v2.5 to v2.4, for example. If your merge introduces a conflict, you can resolve it in the usual ways. ++ +When using '--squash', and the previous merge with '--squash' merged an +annotated tag of the subtree repository, that tag needs to be available locally. +If <repository> is given, a missing tag will automatically be fetched from that +repository. -split [<local-commit>]:: +split [<local-commit>] [<repository>]:: Extract a new, synthetic project history from the history of the <prefix> subtree of <local-commit>, or of HEAD if no <local-commit> is given. The new history @@ -109,6 +114,11 @@ settings passed to 'split' (such as '--annotate') are the same. Because of this, if you add new commits and then re-split, the new commits will be attached as commits on top of the history you generated last time, so 'git merge' and friends will work as expected. ++ +When a previous merge with '--squash' merged an annotated tag of the +subtree repository, that tag needs to be available locally. +If <repository> is given, a missing tag will automatically be fetched from that +repository. pull <repository> <remote-ref>:: Exactly like 'merge', but parallels 'git pull' in that diff --git a/contrib/subtree/t/t7900-subtree.sh b/contrib/subtree/t/t7900-subtree.sh index 1c1f76f04a..341c169eca 100755 --- a/contrib/subtree/t/t7900-subtree.sh +++ b/contrib/subtree/t/t7900-subtree.sh @@ -43,6 +43,30 @@ last_commit_subject () { git log --pretty=format:%s -1 } +# Upon 'git subtree add|merge --squash' of an annotated tag, +# pre-2.32.0 versions of 'git subtree' would write the hash of the tag +# (sub1 below), instead of the commit (sub1^{commit}) in the +# "git-subtree-split" trailer. +# We immitate this behaviour below using a replace ref. +# This function creates 3 repositories: +# - $1 +# - $1-sub (added as subtree "sub" in $1) +# - $1-clone (clone of $1) +test_create_pre2_32_repo () { + subtree_test_create_repo "$1" && + subtree_test_create_repo "$1-sub" && + test_commit -C "$1" main1 && + test_commit -C "$1-sub" --annotate sub1 && + git -C "$1" subtree add --prefix="sub" --squash "../$1-sub" sub1 && + tag=$(git -C "$1" rev-parse FETCH_HEAD) && + commit=$(git -C "$1" rev-parse FETCH_HEAD^{commit}) && + git -C "$1" log -1 --format=%B HEAD^2 >msg && + test_commit -C "$1-sub" --annotate sub2 && + git clone --no-local "$1" "$1-clone" && + new_commit=$(cat msg | sed -e "s/$commit/$tag/" | git -C "$1-clone" commit-tree HEAD^2^{tree}) && + git -C "$1-clone" replace HEAD^2 $new_commit +} + test_expect_success 'shows short help text for -h' ' test_expect_code 129 git subtree -h >out 2>err && test_must_be_empty err && @@ -264,6 +288,13 @@ test_expect_success 'merge new subproj history into subdir/ with a slash appende ) ' +test_expect_success 'merge with --squash after annotated tag was added/merged with --squash pre-v2.32.0 ' ' + test_create_pre2_32_repo "$test_count" && + git -C "$test_count-clone" fetch "../$test_count-sub" sub2 && + test_must_fail git -C "$test_count-clone" subtree merge --prefix="sub" --squash FETCH_HEAD && + git -C "$test_count-clone" subtree merge --prefix="sub" --squash FETCH_HEAD "../$test_count-sub" +' + # # Tests for 'git subtree split' # @@ -277,7 +308,7 @@ test_expect_success 'split requires option --prefix' ' cd "$test_count" && git fetch ./"sub proj" HEAD && git subtree add --prefix="sub dir" FETCH_HEAD && - echo "You must provide the --prefix option." >expected && + echo "fatal: you must provide the --prefix option." >expected && test_must_fail git subtree split >actual 2>&1 && test_debug "printf '"expected: "'" && test_debug "cat expected" && @@ -296,7 +327,7 @@ test_expect_success 'split requires path given by option --prefix must exist' ' cd "$test_count" && git fetch ./"sub proj" HEAD && git subtree add --prefix="sub dir" FETCH_HEAD && - echo "'\''non-existent-directory'\'' does not exist; use '\''git subtree add'\''" >expected && + echo "fatal: '\''non-existent-directory'\'' does not exist; use '\''git subtree add'\''" >expected && test_must_fail git subtree split --prefix=non-existent-directory >actual 2>&1 && test_debug "printf '"expected: "'" && test_debug "cat expected" && @@ -551,6 +582,12 @@ test_expect_success 'split "sub dir"/ with --branch for an incompatible branch' ) ' +test_expect_success 'split after annotated tag was added/merged with --squash pre-v2.32.0' ' + test_create_pre2_32_repo "$test_count" && + test_must_fail git -C "$test_count-clone" subtree split --prefix="sub" HEAD && + git -C "$test_count-clone" subtree split --prefix="sub" HEAD "../$test_count-sub" +' + # # Tests for 'git subtree pull' # @@ -570,7 +607,7 @@ test_expect_success 'pull requires option --prefix' ' cd "$test_count" && test_must_fail git subtree pull ./"sub proj" HEAD >out 2>err && - echo "You must provide the --prefix option." >expected && + echo "fatal: you must provide the --prefix option." >expected && test_must_be_empty out && test_cmp expected err ) @@ -584,7 +621,7 @@ test_expect_success 'pull requires path given by option --prefix must exist' ' ( test_must_fail git subtree pull --prefix="sub dir" ./"sub proj" HEAD >out 2>err && - echo "'\''sub dir'\'' does not exist; use '\''git subtree add'\''" >expected && + echo "fatal: '\''sub dir'\'' does not exist; use '\''git subtree add'\''" >expected && test_must_be_empty out && test_cmp expected err ) @@ -630,6 +667,11 @@ test_expect_success 'pull rejects flags for split' ' ) ' +test_expect_success 'pull with --squash after annotated tag was added/merged with --squash pre-v2.32.0 ' ' + test_create_pre2_32_repo "$test_count" && + git -C "$test_count-clone" subtree -d pull --prefix="sub" --squash "../$test_count-sub" sub2 +' + # # Tests for 'git subtree push' # @@ -643,7 +685,7 @@ test_expect_success 'push requires option --prefix' ' cd "$test_count" && git fetch ./"sub proj" HEAD && git subtree add --prefix="sub dir" FETCH_HEAD && - echo "You must provide the --prefix option." >expected && + echo "fatal: you must provide the --prefix option." >expected && test_must_fail git subtree push "./sub proj" from-mainline >actual 2>&1 && test_debug "printf '"expected: "'" && test_debug "cat expected" && @@ -662,7 +704,7 @@ test_expect_success 'push requires path given by option --prefix must exist' ' cd "$test_count" && git fetch ./"sub proj" HEAD && git subtree add --prefix="sub dir" FETCH_HEAD && - echo "'\''non-existent-directory'\'' does not exist; use '\''git subtree add'\''" >expected && + echo "fatal: '\''non-existent-directory'\'' does not exist; use '\''git subtree add'\''" >expected && test_must_fail git subtree push --prefix=non-existent-directory "./sub proj" from-mainline >actual 2>&1 && test_debug "printf '"expected: "'" && test_debug "cat expected" && @@ -953,6 +995,12 @@ test_expect_success 'push "sub dir"/ with a local rev' ' ) ' +test_expect_success 'push after annotated tag was added/merged with --squash pre-v2.32.0' ' + test_create_pre2_32_repo "$test_count" && + test_create_commit "$test_count-clone" sub/main-sub1 && + git -C "$test_count-clone" subtree push --prefix="sub" "../$test_count-sub" from-mainline +' + # # Validity checking # @@ -6229,7 +6229,7 @@ static void patch_id_add_mode(git_hash_ctx *ctx, unsigned mode) } /* returns 0 upon success, and writes result into oid */ -static int diff_get_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only, int stable) +static int diff_get_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; @@ -6276,61 +6276,62 @@ static int diff_get_patch_id(struct diff_options *options, struct object_id *oid if (p->one->mode == 0) { patch_id_add_string(&ctx, "newfilemode"); patch_id_add_mode(&ctx, p->two->mode); - patch_id_add_string(&ctx, "---/dev/null"); - patch_id_add_string(&ctx, "+++b/"); - the_hash_algo->update_fn(&ctx, p->two->path, len2); } else if (p->two->mode == 0) { patch_id_add_string(&ctx, "deletedfilemode"); patch_id_add_mode(&ctx, p->one->mode); - patch_id_add_string(&ctx, "---a/"); - the_hash_algo->update_fn(&ctx, p->one->path, len1); - patch_id_add_string(&ctx, "+++/dev/null"); - } else { - patch_id_add_string(&ctx, "---a/"); - the_hash_algo->update_fn(&ctx, p->one->path, len1); - patch_id_add_string(&ctx, "+++b/"); - the_hash_algo->update_fn(&ctx, p->two->path, len2); + } else if (p->one->mode != p->two->mode) { + patch_id_add_string(&ctx, "oldmode"); + patch_id_add_mode(&ctx, p->one->mode); + patch_id_add_string(&ctx, "newmode"); + patch_id_add_mode(&ctx, p->two->mode); } - if (diff_header_only) - continue; - - if (fill_mmfile(options->repo, &mf1, p->one) < 0 || - fill_mmfile(options->repo, &mf2, p->two) < 0) - return error("unable to read files to diff"); - - if (diff_filespec_is_binary(options->repo, p->one) || + if (diff_header_only) { + /* don't do anything since we're only populating header info */ + } else if (diff_filespec_is_binary(options->repo, p->one) || diff_filespec_is_binary(options->repo, p->two)) { the_hash_algo->update_fn(&ctx, oid_to_hex(&p->one->oid), the_hash_algo->hexsz); the_hash_algo->update_fn(&ctx, oid_to_hex(&p->two->oid), the_hash_algo->hexsz); - continue; - } - - xpp.flags = 0; - xecfg.ctxlen = 3; - xecfg.flags = XDL_EMIT_NO_HUNK_HDR; - if (xdi_diff_outf(&mf1, &mf2, NULL, - patch_id_consume, &data, &xpp, &xecfg)) - return error("unable to generate patch-id diff for %s", - p->one->path); + } else { + if (p->one->mode == 0) { + patch_id_add_string(&ctx, "---/dev/null"); + patch_id_add_string(&ctx, "+++b/"); + the_hash_algo->update_fn(&ctx, p->two->path, len2); + } else if (p->two->mode == 0) { + patch_id_add_string(&ctx, "---a/"); + the_hash_algo->update_fn(&ctx, p->one->path, len1); + patch_id_add_string(&ctx, "+++/dev/null"); + } else { + patch_id_add_string(&ctx, "---a/"); + the_hash_algo->update_fn(&ctx, p->one->path, len1); + patch_id_add_string(&ctx, "+++b/"); + the_hash_algo->update_fn(&ctx, p->two->path, len2); + } - if (stable) - flush_one_hunk(oid, &ctx); + if (fill_mmfile(options->repo, &mf1, p->one) < 0 || + fill_mmfile(options->repo, &mf2, p->two) < 0) + return error("unable to read files to diff"); + xpp.flags = 0; + xecfg.ctxlen = 3; + xecfg.flags = XDL_EMIT_NO_HUNK_HDR; + if (xdi_diff_outf(&mf1, &mf2, NULL, + patch_id_consume, &data, &xpp, &xecfg)) + return error("unable to generate patch-id diff for %s", + p->one->path); + } + flush_one_hunk(oid, &ctx); } - if (!stable) - the_hash_algo->final_oid_fn(oid, &ctx); - return 0; } -int diff_flush_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only, int stable) +int diff_flush_patch_id(struct diff_options *options, struct object_id *oid, int diff_header_only) { struct diff_queue_struct *q = &diff_queued_diff; int i; - int result = diff_get_patch_id(options, oid, diff_header_only, stable); + int result = diff_get_patch_id(options, oid, diff_header_only); for (i = 0; i < q->nr; i++) diff_free_filepair(q->queue[i]); @@ -634,7 +634,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option); int run_diff_index(struct rev_info *revs, unsigned int option); int do_diff_cache(const struct object_id *, struct diff_options *); -int diff_flush_patch_id(struct diff_options *, struct object_id *, int, int); +int diff_flush_patch_id(struct diff_options *, struct object_id *, int); void flush_one_hunk(struct object_id *result, git_hash_ctx *ctx); int diff_result_code(struct diff_options *, int); @@ -13,6 +13,12 @@ enum fsck_msg_type { FSCK_WARN, }; +/* + * Documentation/fsck-msgids.txt documents these; when + * modifying this list in any way, make sure to keep the + * two in sync. + */ + #define FOREACH_FSCK_MSG_ID(FUNC) \ /* fatal errors */ \ FUNC(NUL_IN_HEADER, FATAL) \ @@ -24,7 +30,6 @@ enum fsck_msg_type { FUNC(BAD_NAME, ERROR) \ FUNC(BAD_OBJECT_SHA1, ERROR) \ FUNC(BAD_PARENT_SHA1, ERROR) \ - FUNC(BAD_TAG_OBJECT, ERROR) \ FUNC(BAD_TIMEZONE, ERROR) \ FUNC(BAD_TREE, ERROR) \ FUNC(BAD_TREE_SHA1, ERROR) \ @@ -40,7 +45,6 @@ enum fsck_msg_type { FUNC(MISSING_TAG, ERROR) \ FUNC(MISSING_TAG_ENTRY, ERROR) \ FUNC(MISSING_TREE, ERROR) \ - FUNC(MISSING_TREE_OBJECT, ERROR) \ FUNC(MISSING_TYPE, ERROR) \ FUNC(MISSING_TYPE_ENTRY, ERROR) \ FUNC(MULTIPLE_AUTHORS, ERROR) \ diff --git a/merge-ort.c b/merge-ort.c index 7e83ebfaa9..d1611ca400 100644 --- a/merge-ort.c +++ b/merge-ort.c @@ -2619,8 +2619,40 @@ static void apply_directory_rename_modifications(struct merge_options *opt, } assert(ci->filemask == 2 || ci->filemask == 4); - assert(ci->dirmask == 0); - strmap_remove(&opt->priv->paths, old_path, 0); + assert(ci->dirmask == 0 || ci->dirmask == 1); + if (ci->dirmask == 0) + strmap_remove(&opt->priv->paths, old_path, 0); + else { + /* + * This file exists on one side, but we still had a directory + * at the old location that we can't remove until after + * processing all paths below it. So, make a copy of ci in + * new_ci and only put the file information into it. + */ + new_ci = mem_pool_calloc(&opt->priv->pool, 1, sizeof(*new_ci)); + memcpy(new_ci, ci, sizeof(*ci)); + assert(!new_ci->match_mask); + new_ci->dirmask = 0; + new_ci->stages[1].mode = 0; + oidcpy(&new_ci->stages[1].oid, null_oid()); + + /* + * Now that we have the file information in new_ci, make sure + * ci only has the directory information. + */ + ci->filemask = 0; + ci->merged.clean = 1; + for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) { + if (ci->dirmask & (1 << i)) + continue; + /* zero out any entries related to files */ + ci->stages[i].mode = 0; + oidcpy(&ci->stages[i].oid, null_oid()); + } + + // Now we want to focus on new_ci, so reassign ci to it + ci = new_ci; + } branch_with_new_path = (ci->filemask == 2) ? opt->branch1 : opt->branch2; branch_with_dir_rename = (ci->filemask == 2) ? opt->branch2 : opt->branch1; diff --git a/negotiator/skipping.c b/negotiator/skipping.c index c4398f5ae1..0f5ac48e87 100644 --- a/negotiator/skipping.c +++ b/negotiator/skipping.c @@ -86,21 +86,26 @@ static int clear_marks(const char *refname, const struct object_id *oid, /* * Mark this SEEN commit and all its SEEN ancestors as COMMON. */ -static void mark_common(struct data *data, struct commit *c) +static void mark_common(struct data *data, struct commit *seen_commit) { - struct commit_list *p; + struct prio_queue queue = { NULL }; + struct commit *c; - if (c->object.flags & COMMON) - return; - c->object.flags |= COMMON; - if (!(c->object.flags & POPPED)) - data->non_common_revs--; + prio_queue_put(&queue, seen_commit); + while ((c = prio_queue_get(&queue))) { + struct commit_list *p; + if (c->object.flags & COMMON) + return; + c->object.flags |= COMMON; + if (!(c->object.flags & POPPED)) + data->non_common_revs--; - if (!c->object.parsed) - return; - for (p = c->parents; p; p = p->next) { - if (p->item->object.flags & SEEN) - mark_common(data, p->item); + if (!c->object.parsed) + return; + for (p = c->parents; p; p = p->next) { + if (p->item->object.flags & SEEN) + prio_queue_put(&queue, p->item); + } } } diff --git a/patch-ids.c b/patch-ids.c index 46c6a8f3ea..3153446626 100644 --- a/patch-ids.c +++ b/patch-ids.c @@ -11,7 +11,7 @@ static int patch_id_defined(struct commit *commit) } int commit_patch_id(struct commit *commit, struct diff_options *options, - struct object_id *oid, int diff_header_only, int stable) + struct object_id *oid, int diff_header_only) { if (!patch_id_defined(commit)) return -1; @@ -22,7 +22,7 @@ int commit_patch_id(struct commit *commit, struct diff_options *options, else diff_root_tree_oid(&commit->object.oid, "", options); diffcore_std(options); - return diff_flush_patch_id(options, oid, diff_header_only, stable); + return diff_flush_patch_id(options, oid, diff_header_only); } /* @@ -48,11 +48,11 @@ static int patch_id_neq(const void *cmpfn_data, b = container_of(entry_or_key, struct patch_id, ent); if (is_null_oid(&a->patch_id) && - commit_patch_id(a->commit, opt, &a->patch_id, 0, 0)) + commit_patch_id(a->commit, opt, &a->patch_id, 0)) return error("Could not get patch ID for %s", oid_to_hex(&a->commit->object.oid)); if (is_null_oid(&b->patch_id) && - commit_patch_id(b->commit, opt, &b->patch_id, 0, 0)) + commit_patch_id(b->commit, opt, &b->patch_id, 0)) return error("Could not get patch ID for %s", oid_to_hex(&b->commit->object.oid)); return !oideq(&a->patch_id, &b->patch_id); @@ -82,7 +82,7 @@ static int init_patch_id_entry(struct patch_id *patch, struct object_id header_only_patch_id; patch->commit = commit; - if (commit_patch_id(commit, &ids->diffopts, &header_only_patch_id, 1, 0)) + if (commit_patch_id(commit, &ids->diffopts, &header_only_patch_id, 1)) return -1; hashmap_entry_init(&patch->ent, oidhash(&header_only_patch_id)); diff --git a/patch-ids.h b/patch-ids.h index ab6c6a6804..490d739371 100644 --- a/patch-ids.h +++ b/patch-ids.h @@ -20,7 +20,7 @@ struct patch_ids { }; int commit_patch_id(struct commit *commit, struct diff_options *options, - struct object_id *oid, int, int); + struct object_id *oid, int); int init_patch_ids(struct repository *, struct patch_ids *); int free_patch_ids(struct patch_ids *); @@ -901,7 +901,13 @@ int adjust_shared_perm(const char *path) if (S_ISDIR(old_mode)) { /* Copy read bits to execute bits */ new_mode |= (new_mode & 0444) >> 2; - new_mode |= FORCE_DIR_SET_GID; + + /* + * g+s matters only if any extra access is granted + * based on group membership. + */ + if (FORCE_DIR_SET_GID && (new_mode & 060)) + new_mode |= FORCE_DIR_SET_GID; } if (((old_mode ^ new_mode) & ~S_IFMT) && diff --git a/ref-filter.c b/ref-filter.c index 914908fac5..9dc2cd1451 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -1375,12 +1375,12 @@ static void find_subpos(const char *buf, /* subject is first non-empty line */ *sub = buf; /* subject goes to first empty line before signature begins */ - if ((eol = strstr(*sub, "\n\n"))) { + if ((eol = strstr(*sub, "\n\n")) || + (eol = strstr(*sub, "\r\n\r\n"))) { eol = eol < sigstart ? eol : sigstart; - /* check if message uses CRLF */ - } else if (! (eol = strstr(*sub, "\r\n\r\n"))) { + } else { /* treat whole message as subject */ - eol = strrchr(*sub, '\0'); + eol = sigstart; } buf = eol; *sublen = buf - *sub; diff --git a/repo-settings.c b/repo-settings.c index e8b58151bc..3021921c53 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -43,6 +43,7 @@ void prepare_repo_settings(struct repository *r) /* Defaults modified by feature.* */ if (experimental) { r->settings.fetch_negotiation_algorithm = FETCH_NEGOTIATION_SKIPPING; + r->settings.gc_cruft_packs = 1; } if (manyfiles) { r->settings.index_version = 4; diff --git a/repository.h b/repository.h index 24316ac944..6c461c5b9d 100644 --- a/repository.h +++ b/repository.h @@ -34,6 +34,7 @@ struct repo_settings { int commit_graph_generation_version; int commit_graph_read_changed_paths; int gc_write_commit_graph; + int gc_cruft_packs; int fetch_write_commit_graph; int command_requires_full_index; int sparse_index; diff --git a/sequencer.c b/sequencer.c index debb2ecbaf..e658df7e8f 100644 --- a/sequencer.c +++ b/sequencer.c @@ -5050,6 +5050,8 @@ int sequencer_continue(struct repository *r, struct replay_opts *opts) if (read_populate_opts(opts)) return -1; if (is_rebase_i(opts)) { + char *previous_reflog_action; + if ((res = read_populate_todo(r, &todo_list, opts))) goto release_todo_list; @@ -5060,10 +5062,13 @@ int sequencer_continue(struct repository *r, struct replay_opts *opts) unlink(rebase_path_dropped()); } + previous_reflog_action = xstrdup(getenv(GIT_REFLOG_ACTION)); + setenv(GIT_REFLOG_ACTION, reflog_message(opts, "continue", NULL), 1); if (commit_staged_changes(r, opts, &todo_list)) { res = -1; goto release_todo_list; } + setenv(GIT_REFLOG_ACTION, previous_reflog_action, 1); } else if (!file_exists(get_todo_path(opts))) return continue_single_pick(r, opts); else if ((res = read_populate_todo(r, &todo_list, opts))) diff --git a/shortlog.h b/shortlog.h index 3f7e9aabca..28d04f951a 100644 --- a/shortlog.h +++ b/shortlog.h @@ -2,6 +2,7 @@ #define SHORTLOG_H #include "string-list.h" +#include "date.h" struct commit; @@ -15,13 +16,16 @@ struct shortlog { int in2; int user_format; int abbrev; + struct date_mode date_mode; enum { SHORTLOG_GROUP_AUTHOR = (1 << 0), SHORTLOG_GROUP_COMMITTER = (1 << 1), SHORTLOG_GROUP_TRAILER = (1 << 2), + SHORTLOG_GROUP_FORMAT = (1 << 3), } groups; struct string_list trailers; + struct string_list format; int email; struct string_list mailmap; @@ -29,6 +33,7 @@ struct shortlog { }; void shortlog_init(struct shortlog *log); +void shortlog_finish_setup(struct shortlog *log); void shortlog_add_commit(struct shortlog *log, struct commit *commit); diff --git a/submodule.c b/submodule.c index f7c71f1f4b..b958162d28 100644 --- a/submodule.c +++ b/submodule.c @@ -2367,26 +2367,20 @@ void absorb_git_dir_into_superproject(const char *path, if (flags & ABSORB_GITDIR_RECURSE_SUBMODULES) { struct child_process cp = CHILD_PROCESS_INIT; - struct strbuf sb = STRBUF_INIT; if (flags & ~ABSORB_GITDIR_RECURSE_SUBMODULES) BUG("we don't know how to pass the flags down?"); - strbuf_addstr(&sb, get_super_prefix_or_empty()); - strbuf_addstr(&sb, path); - strbuf_addch(&sb, '/'); - cp.dir = path; cp.git_cmd = 1; cp.no_stdin = 1; - strvec_pushl(&cp.args, "--super-prefix", sb.buf, - "submodule--helper", + strvec_pushf(&cp.args, "--super-prefix=%s%s/", + get_super_prefix_or_empty(), path); + strvec_pushl(&cp.args, "submodule--helper", "absorbgitdirs", NULL); prepare_submodule_repo_env(&cp.env); if (run_command(&cp)) die(_("could not recurse into submodule '%s'"), path); - - strbuf_release(&sb); } } diff --git a/t/helper/test-bundle-uri.c b/t/helper/test-bundle-uri.c new file mode 100644 index 0000000000..25afd39342 --- /dev/null +++ b/t/helper/test-bundle-uri.c @@ -0,0 +1,95 @@ +#include "test-tool.h" +#include "parse-options.h" +#include "bundle-uri.h" +#include "strbuf.h" +#include "string-list.h" + +enum input_mode { + KEY_VALUE_PAIRS, + CONFIG_FILE, +}; + +static int cmd__bundle_uri_parse(int argc, const char **argv, enum input_mode mode) +{ + const char *key_value_usage[] = { + "test-tool bundle-uri parse-key-values <input>", + NULL + }; + const char *config_usage[] = { + "test-tool bundle-uri parse-config <input>", + NULL + }; + const char **usage = key_value_usage; + struct option options[] = { + OPT_END(), + }; + struct strbuf sb = STRBUF_INIT; + struct bundle_list list; + int err = 0; + FILE *fp; + + if (mode == CONFIG_FILE) + usage = config_usage; + + argc = parse_options(argc, argv, NULL, options, usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + init_bundle_list(&list); + + switch (mode) { + case KEY_VALUE_PAIRS: + if (argc != 1) + goto usage; + fp = fopen(argv[0], "r"); + if (!fp) + die("failed to open '%s'", argv[0]); + while (strbuf_getline(&sb, fp) != EOF) { + if (bundle_uri_parse_line(&list, sb.buf)) + err = error("bad line: '%s'", sb.buf); + } + fclose(fp); + break; + + case CONFIG_FILE: + if (argc != 1) + goto usage; + err = bundle_uri_parse_config_format("<uri>", argv[0], &list); + break; + } + strbuf_release(&sb); + + print_bundle_list(stdout, &list); + + clear_bundle_list(&list); + + return !!err; + +usage: + usage_with_options(usage, options); +} + +int cmd__bundle_uri(int argc, const char **argv) +{ + const char *usage[] = { + "test-tool bundle-uri <subcommand> [<options>]", + NULL + }; + struct option options[] = { + OPT_END(), + }; + + argc = parse_options(argc, argv, NULL, options, usage, + PARSE_OPT_STOP_AT_NON_OPTION | + PARSE_OPT_KEEP_ARGV0); + if (argc == 1) + goto usage; + + if (!strcmp(argv[1], "parse-key-values")) + return cmd__bundle_uri_parse(argc - 1, argv + 1, KEY_VALUE_PAIRS); + if (!strcmp(argv[1], "parse-config")) + return cmd__bundle_uri_parse(argc - 1, argv + 1, CONFIG_FILE); + error("there is no test-tool bundle-uri tool '%s'", argv[1]); + +usage: + usage_with_options(usage, options); +} diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c index d1d013bcd9..01cda9358d 100644 --- a/t/helper/test-tool.c +++ b/t/helper/test-tool.c @@ -13,6 +13,7 @@ static struct test_cmd cmds[] = { { "advise", cmd__advise_if_enabled }, { "bitmap", cmd__bitmap }, { "bloom", cmd__bloom }, + { "bundle-uri", cmd__bundle_uri }, { "chmtime", cmd__chmtime }, { "config", cmd__config }, { "crontab", cmd__crontab }, diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h index 6b46b6444b..ca2948066f 100644 --- a/t/helper/test-tool.h +++ b/t/helper/test-tool.h @@ -7,6 +7,7 @@ int cmd__advise_if_enabled(int argc, const char **argv); int cmd__bitmap(int argc, const char **argv); int cmd__bloom(int argc, const char **argv); +int cmd__bundle_uri(int argc, const char **argv); int cmd__chmtime(int argc, const char **argv); int cmd__config(int argc, const char **argv); int cmd__crontab(int argc, const char **argv); diff --git a/t/helper/test-trace2.c b/t/helper/test-trace2.c index a714130ece..1b092c6071 100644 --- a/t/helper/test-trace2.c +++ b/t/helper/test-trace2.c @@ -229,6 +229,187 @@ static int ut_010bug_BUG(int argc, const char **argv) } /* + * Single-threaded timer test. Create several intervals using the + * TEST1 timer. The test script can verify that an aggregate Trace2 + * "timer" event is emitted indicating that we started+stopped the + * timer the requested number of times. + */ +static int ut_100timer(int argc, const char **argv) +{ + const char *usage_error = + "expect <count> <ms_delay>"; + + int count = 0; + int delay = 0; + int k; + + if (argc != 2) + die("%s", usage_error); + if (get_i(&count, argv[0])) + die("%s", usage_error); + if (get_i(&delay, argv[1])) + die("%s", usage_error); + + for (k = 0; k < count; k++) { + trace2_timer_start(TRACE2_TIMER_ID_TEST1); + sleep_millisec(delay); + trace2_timer_stop(TRACE2_TIMER_ID_TEST1); + } + + return 0; +} + +struct ut_101_data { + int count; + int delay; +}; + +static void *ut_101timer_thread_proc(void *_ut_101_data) +{ + struct ut_101_data *data = _ut_101_data; + int k; + + trace2_thread_start("ut_101"); + + for (k = 0; k < data->count; k++) { + trace2_timer_start(TRACE2_TIMER_ID_TEST2); + sleep_millisec(data->delay); + trace2_timer_stop(TRACE2_TIMER_ID_TEST2); + } + + trace2_thread_exit(); + return NULL; +} + +/* + * Multi-threaded timer test. Create several threads that each create + * several intervals using the TEST2 timer. The test script can verify + * that an individual Trace2 "th_timer" events for each thread and an + * aggregate "timer" event are generated. + */ +static int ut_101timer(int argc, const char **argv) +{ + const char *usage_error = + "expect <count> <ms_delay> <threads>"; + + struct ut_101_data data = { 0, 0 }; + int nr_threads = 0; + int k; + pthread_t *pids = NULL; + + if (argc != 3) + die("%s", usage_error); + if (get_i(&data.count, argv[0])) + die("%s", usage_error); + if (get_i(&data.delay, argv[1])) + die("%s", usage_error); + if (get_i(&nr_threads, argv[2])) + die("%s", usage_error); + + CALLOC_ARRAY(pids, nr_threads); + + for (k = 0; k < nr_threads; k++) { + if (pthread_create(&pids[k], NULL, ut_101timer_thread_proc, &data)) + die("failed to create thread[%d]", k); + } + + for (k = 0; k < nr_threads; k++) { + if (pthread_join(pids[k], NULL)) + die("failed to join thread[%d]", k); + } + + free(pids); + + return 0; +} + +/* + * Single-threaded counter test. Add several values to the TEST1 counter. + * The test script can verify that the final sum is reported in the "counter" + * event. + */ +static int ut_200counter(int argc, const char **argv) +{ + const char *usage_error = + "expect <v1> [<v2> [...]]"; + int value; + int k; + + if (argc < 1) + die("%s", usage_error); + + for (k = 0; k < argc; k++) { + if (get_i(&value, argv[k])) + die("invalid value[%s] -- %s", + argv[k], usage_error); + trace2_counter_add(TRACE2_COUNTER_ID_TEST1, value); + } + + return 0; +} + +/* + * Multi-threaded counter test. Create seveal threads that each increment + * the TEST2 global counter. The test script can verify that an individual + * "th_counter" event is generated with a partial sum for each thread and + * that a final aggregate "counter" event is generated. + */ + +struct ut_201_data { + int v1; + int v2; +}; + +static void *ut_201counter_thread_proc(void *_ut_201_data) +{ + struct ut_201_data *data = _ut_201_data; + + trace2_thread_start("ut_201"); + + trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v1); + trace2_counter_add(TRACE2_COUNTER_ID_TEST2, data->v2); + + trace2_thread_exit(); + return NULL; +} + +static int ut_201counter(int argc, const char **argv) +{ + const char *usage_error = + "expect <v1> <v2> <threads>"; + + struct ut_201_data data = { 0, 0 }; + int nr_threads = 0; + int k; + pthread_t *pids = NULL; + + if (argc != 3) + die("%s", usage_error); + if (get_i(&data.v1, argv[0])) + die("%s", usage_error); + if (get_i(&data.v2, argv[1])) + die("%s", usage_error); + if (get_i(&nr_threads, argv[2])) + die("%s", usage_error); + + CALLOC_ARRAY(pids, nr_threads); + + for (k = 0; k < nr_threads; k++) { + if (pthread_create(&pids[k], NULL, ut_201counter_thread_proc, &data)) + die("failed to create thread[%d]", k); + } + + for (k = 0; k < nr_threads; k++) { + if (pthread_join(pids[k], NULL)) + die("failed to join thread[%d]", k); + } + + free(pids); + + return 0; +} + +/* * Usage: * test-tool trace2 <ut_name_1> <ut_usage_1> * test-tool trace2 <ut_name_2> <ut_usage_2> @@ -248,6 +429,12 @@ static struct unit_test ut_table[] = { { ut_008bug, "008bug", "" }, { ut_009bug_BUG, "009bug_BUG","" }, { ut_010bug_BUG, "010bug_BUG","" }, + + { ut_100timer, "100timer", "<count> <ms_delay>" }, + { ut_101timer, "101timer", "<count> <ms_delay> <threads>" }, + + { ut_200counter, "200counter", "<v1> [<v2> [<v3> [...]]]" }, + { ut_201counter, "201counter", "<v1> <v2> <threads>" }, }; /* clang-format on */ diff --git a/t/t0211-trace2-perf.sh b/t/t0211-trace2-perf.sh index 22d0845544..0b3436e8ca 100755 --- a/t/t0211-trace2-perf.sh +++ b/t/t0211-trace2-perf.sh @@ -173,4 +173,99 @@ test_expect_success 'using global config, perf stream, return code 0' ' test_cmp expect actual ' +# Exercise the stopwatch timers in a loop and confirm that we have +# as many start/stop intervals as expected. We cannot really test the +# actual (total, min, max) timer values, so we have to assume that they +# are good, but we can verify the interval count. +# +# The timer "test/test1" should only emit a global summary "timer" event. +# The timer "test/test2" should emit per-thread "th_timer" events and a +# global summary "timer" event. + +have_timer_event () { + thread=$1 event=$2 category=$3 name=$4 intervals=$5 file=$6 && + + pattern="d0|${thread}|${event}||||${category}|name:${name} intervals:${intervals}" && + + grep "${pattern}" ${file} +} + +test_expect_success 'stopwatch timer test/test1' ' + test_when_finished "rm trace.perf actual" && + test_config_global trace2.perfBrief 1 && + test_config_global trace2.perfTarget "$(pwd)/trace.perf" && + + # Use the timer "test1" 5 times from "main". + test-tool trace2 100timer 5 10 && + + perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual && + + have_timer_event "main" "timer" "test" "test1" 5 actual +' + +test_expect_success 'stopwatch timer test/test2' ' + test_when_finished "rm trace.perf actual" && + test_config_global trace2.perfBrief 1 && + test_config_global trace2.perfTarget "$(pwd)/trace.perf" && + + # Use the timer "test2" 5 times each in 3 threads. + test-tool trace2 101timer 5 10 3 && + + perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual && + + # So we should have 3 per-thread events of 5 each. + have_timer_event "th01:ut_101" "th_timer" "test" "test2" 5 actual && + have_timer_event "th02:ut_101" "th_timer" "test" "test2" 5 actual && + have_timer_event "th03:ut_101" "th_timer" "test" "test2" 5 actual && + + # And we should have 15 total uses. + have_timer_event "main" "timer" "test" "test2" 15 actual +' + +# Exercise the global counters and confirm that we get the expected values. +# +# The counter "test/test1" should only emit a global summary "counter" event. +# The counter "test/test2" could emit per-thread "th_counter" events and a +# global summary "counter" event. + +have_counter_event () { + thread=$1 event=$2 category=$3 name=$4 value=$5 file=$6 && + + pattern="d0|${thread}|${event}||||${category}|name:${name} value:${value}" && + + grep "${patern}" ${file} +} + +test_expect_success 'global counter test/test1' ' + test_when_finished "rm trace.perf actual" && + test_config_global trace2.perfBrief 1 && + test_config_global trace2.perfTarget "$(pwd)/trace.perf" && + + # Use the counter "test1" and add n integers. + test-tool trace2 200counter 1 2 3 4 5 && + + perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual && + + have_counter_event "main" "counter" "test" "test1" 15 actual +' + +test_expect_success 'global counter test/test2' ' + test_when_finished "rm trace.perf actual" && + test_config_global trace2.perfBrief 1 && + test_config_global trace2.perfTarget "$(pwd)/trace.perf" && + + # Add 2 integers to the counter "test2" in each of 3 threads. + test-tool trace2 201counter 7 13 3 && + + perl "$TEST_DIRECTORY/t0211/scrub_perf.perl" <trace.perf >actual && + + # So we should have 3 per-thread events of 5 each. + have_counter_event "th01:ut_201" "th_counter" "test" "test2" 20 actual && + have_counter_event "th02:ut_201" "th_counter" "test" "test2" 20 actual && + have_counter_event "th03:ut_201" "th_counter" "test" "test2" 20 actual && + + # And we should have a single event with the total across all threads. + have_counter_event "main" "counter" "test" "test2" 60 actual +' + test_done diff --git a/t/t0211/scrub_perf.perl b/t/t0211/scrub_perf.perl index 299999f0f8..7a50bae646 100644 --- a/t/t0211/scrub_perf.perl +++ b/t/t0211/scrub_perf.perl @@ -64,6 +64,12 @@ while (<>) { goto SKIP_LINE; } } + elsif ($tokens[$col_event] =~ m/timer/) { + # This also captures "th_timer" events + $tokens[$col_rest] =~ s/ total:\d+\.\d*/ total:_T_TOTAL_/; + $tokens[$col_rest] =~ s/ min:\d+\.\d*/ min:_T_MIN_/; + $tokens[$col_rest] =~ s/ max:\d+\.\d*/ max:_T_MAX_/; + } # t_abs and t_rel are either blank or a float. Replace the float # with a constant for matching the HEREDOC in the test script. diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh index 7d8edff9c3..7f605f865b 100755 --- a/t/t3200-branch.sh +++ b/t/t3200-branch.sh @@ -268,6 +268,17 @@ test_expect_success 'git branch -M topic topic should work when main is checked git branch -M topic topic ' +test_expect_success 'git branch -M and -C fail on detached HEAD' ' + git checkout HEAD^{} && + test_when_finished git checkout - && + echo "fatal: cannot rename the current branch while not on any." >expect && + test_must_fail git branch -M must-fail 2>err && + test_cmp expect err && + echo "fatal: cannot copy the current branch while not on any." >expect && + test_must_fail git branch -C must-fail 2>err && + test_cmp expect err +' + test_expect_success 'git branch -v -d t should work' ' git branch t && git rev-parse --verify refs/heads/t && @@ -1383,7 +1394,7 @@ test_expect_success 'branch --delete --force removes dangling branch' ' test_expect_success 'use --edit-description' ' EDITOR=: git branch --edit-description && - test_must_fail git config branch.main.description && + test_expect_code 1 git config branch.main.description && write_script editor <<-\EOF && echo "New contents" >"$1" diff --git a/t/t3406-rebase-message.sh b/t/t3406-rebase-message.sh index d17b450e81..ceca160005 100755 --- a/t/t3406-rebase-message.sh +++ b/t/t3406-rebase-message.sh @@ -10,10 +10,16 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME test_expect_success 'setup' ' test_commit O fileO && test_commit X fileX && + git branch fast-forward && test_commit A fileA && test_commit B fileB && test_commit Y fileY && + git checkout -b conflicts O && + test_commit P && + test_commit conflict-X fileX && + test_commit Q && + git checkout -b topic O && git cherry-pick A B && test_commit Z fileZ && @@ -79,54 +85,165 @@ test_expect_success 'error out early upon -C<n> or --whitespace=<bad>' ' test_i18ngrep "Invalid whitespace option" err ' -test_expect_success 'GIT_REFLOG_ACTION' ' - git checkout start && - test_commit reflog-onto && - git checkout -b reflog-topic start && - test_commit reflog-to-rebase && +write_reflog_expect () { + if test $mode = --apply + then + sed 's/(continue)/(pick)/' + else + cat + fi >expect +} - git rebase reflog-onto && - git log -g --format=%gs -3 >actual && - cat >expect <<-\EOF && - rebase (finish): returning to refs/heads/reflog-topic - rebase (pick): reflog-to-rebase - rebase (start): checkout reflog-onto +test_reflog () { + mode=$1 + reflog_action="$2" + + test_expect_success "rebase $mode reflog${reflog_action:+ GIT_REFLOG_ACTION=$reflog_action}" ' + git checkout conflicts && + test_when_finished "git reset --hard Q" && + + ( + if test -n "$reflog_action" + then + GIT_REFLOG_ACTION="$reflog_action" && + export GIT_REFLOG_ACTION + fi && + test_must_fail git rebase $mode main && + echo resolved >fileX && + git add fileX && + git rebase --continue + ) && + + git log -g --format=%gs -5 >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (finish): returning to refs/heads/conflicts + ${reflog_action:-rebase} (pick): Q + ${reflog_action:-rebase} (continue): conflict-X + ${reflog_action:-rebase} (pick): P + ${reflog_action:-rebase} (start): checkout main EOF test_cmp expect actual && - git checkout -b reflog-prefix reflog-to-rebase && - GIT_REFLOG_ACTION=change-the-reflog git rebase reflog-onto && - git log -g --format=%gs -3 >actual && - cat >expect <<-\EOF && - change-the-reflog (finish): returning to refs/heads/reflog-prefix - change-the-reflog (pick): reflog-to-rebase - change-the-reflog (start): checkout reflog-onto + git log -g --format=%gs -1 conflicts >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (finish): refs/heads/conflicts onto $(git rev-parse main) + EOF + test_cmp expect actual && + + # check there is only one new entry in the branch reflog + test_cmp_rev conflicts@{1} Q + ' + + test_expect_success "rebase $mode fast-forward reflog${reflog_action:+ GIT_REFLOG_ACTION=$reflog_action}" ' + git checkout fast-forward && + test_when_finished "git reset --hard X" && + + ( + if test -n "$reflog_action" + then + GIT_REFLOG_ACTION="$reflog_action" && + export GIT_REFLOG_ACTION + fi && + git rebase $mode main + ) && + + git log -g --format=%gs -2 >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (finish): returning to refs/heads/fast-forward + ${reflog_action:-rebase} (start): checkout main + EOF + test_cmp expect actual && + + git log -g --format=%gs -1 fast-forward >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (finish): refs/heads/fast-forward onto $(git rev-parse main) + EOF + test_cmp expect actual && + + # check there is only one new entry in the branch reflog + test_cmp_rev fast-forward@{1} X + ' + + test_expect_success "rebase $mode --skip reflog${reflog_action:+ GIT_REFLOG_ACTION=$reflog_action}" ' + git checkout conflicts && + test_when_finished "git reset --hard Q" && + + ( + if test -n "$reflog_action" + then + GIT_REFLOG_ACTION="$reflog_action" && + export GIT_REFLOG_ACTION + fi && + test_must_fail git rebase $mode main && + git rebase --skip + ) && + + git log -g --format=%gs -4 >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (finish): returning to refs/heads/conflicts + ${reflog_action:-rebase} (pick): Q + ${reflog_action:-rebase} (pick): P + ${reflog_action:-rebase} (start): checkout main EOF test_cmp expect actual -' + ' -test_expect_success 'rebase --apply reflog' ' - git checkout -b reflog-apply start && - old_head_reflog="$(git log -g --format=%gs -1 HEAD)" && + test_expect_success "rebase $mode --abort reflog${reflog_action:+ GIT_REFLOG_ACTION=$reflog_action}" ' + git checkout conflicts && + test_when_finished "git reset --hard Q" && - git rebase --apply Y && + git log -g -1 conflicts >branch-expect && + ( + if test -n "$reflog_action" + then + GIT_REFLOG_ACTION="$reflog_action" && + export GIT_REFLOG_ACTION + fi && + test_must_fail git rebase $mode main && + git rebase --abort + ) && - git log -g --format=%gs -4 HEAD >actual && - cat >expect <<-EOF && - rebase finished: returning to refs/heads/reflog-apply - rebase: Z - rebase: checkout Y - $old_head_reflog + git log -g --format=%gs -3 >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (abort): returning to refs/heads/conflicts + ${reflog_action:-rebase} (pick): P + ${reflog_action:-rebase} (start): checkout main EOF test_cmp expect actual && - git log -g --format=%gs -2 reflog-apply >actual && - cat >expect <<-EOF && - rebase finished: refs/heads/reflog-apply onto $(git rev-parse Y) - branch: Created from start + # check branch reflog is unchanged + git log -g -1 conflicts >branch-actual && + test_cmp branch-expect branch-actual + ' + + test_expect_success "rebase $mode --abort detached HEAD reflog${reflog_action:+ GIT_REFLOG_ACTION=$reflog_action}" ' + git checkout Q && + test_when_finished "git reset --hard Q" && + + ( + if test -n "$reflog_action" + then + GIT_REFLOG_ACTION="$reflog_action" && + export GIT_REFLOG_ACTION + fi && + test_must_fail git rebase $mode main && + git rebase --abort + ) && + + git log -g --format=%gs -3 >actual && + write_reflog_expect <<-EOF && + ${reflog_action:-rebase} (abort): returning to $(git rev-parse Q) + ${reflog_action:-rebase} (pick): P + ${reflog_action:-rebase} (start): checkout main EOF test_cmp expect actual -' + ' +} + +test_reflog --merge +test_reflog --merge my-reflog-action +test_reflog --apply +test_reflog --apply my-reflog-action test_expect_success 'rebase -i onto unrelated history' ' git init unrelated && diff --git a/t/t3416-rebase-onto-threedots.sh b/t/t3416-rebase-onto-threedots.sh index 3e04802cb0..ea501f2b42 100755 --- a/t/t3416-rebase-onto-threedots.sh +++ b/t/t3416-rebase-onto-threedots.sh @@ -79,8 +79,10 @@ test_expect_success 'rebase -i --onto main...topic' ' git reset --hard && git checkout topic && git reset --hard G && - set_fake_editor && - EXPECT_COUNT=1 git rebase -i --onto main...topic F && + ( + set_fake_editor && + EXPECT_COUNT=1 git rebase -i --onto main...topic F + ) && git rev-parse HEAD^1 >actual && git rev-parse C^0 >expect && test_cmp expect actual @@ -90,20 +92,22 @@ test_expect_success 'rebase -i --onto main...' ' git reset --hard && git checkout topic && git reset --hard G && - set_fake_editor && - EXPECT_COUNT=1 git rebase -i --onto main... F && + ( + set_fake_editor && + EXPECT_COUNT=1 git rebase -i --onto main... F + ) && git rev-parse HEAD^1 >actual && git rev-parse C^0 >expect && test_cmp expect actual ' -test_expect_success 'rebase -i --onto main...side' ' +test_expect_success 'rebase --onto main...side requires a single merge-base' ' git reset --hard && git checkout side && git reset --hard K && - set_fake_editor && - test_must_fail git rebase -i --onto main...side J + test_must_fail git rebase -i --onto main...side J 2>err && + grep "need exactly one merge base" err ' test_expect_success 'rebase --keep-base --onto incompatible' ' @@ -156,8 +160,10 @@ test_expect_success 'rebase -i --keep-base main from topic' ' git checkout topic && git reset --hard G && - set_fake_editor && - EXPECT_COUNT=2 git rebase -i --keep-base main && + ( + set_fake_editor && + EXPECT_COUNT=2 git rebase -i --keep-base main + ) && git rev-parse C >base.expect && git merge-base main HEAD >base.actual && test_cmp base.expect base.actual && @@ -171,8 +177,10 @@ test_expect_success 'rebase -i --keep-base main topic from main' ' git checkout main && git branch -f topic G && - set_fake_editor && - EXPECT_COUNT=2 git rebase -i --keep-base main topic && + ( + set_fake_editor && + EXPECT_COUNT=2 git rebase -i --keep-base main topic + ) && git rev-parse C >base.expect && git merge-base main HEAD >base.actual && test_cmp base.expect base.actual && @@ -182,13 +190,39 @@ test_expect_success 'rebase -i --keep-base main topic from main' ' test_cmp expect actual ' -test_expect_success 'rebase -i --keep-base main from side' ' +test_expect_success 'rebase --keep-base requires a single merge base' ' git reset --hard && git checkout side && git reset --hard K && - set_fake_editor && - test_must_fail git rebase -i --keep-base main + test_must_fail git rebase -i --keep-base main 2>err && + grep "need exactly one merge base with branch" err +' + +test_expect_success 'rebase --keep-base keeps cherry picks' ' + git checkout -f -B main E && + git cherry-pick F && + ( + set_fake_editor && + EXPECT_COUNT=2 git rebase -i --keep-base HEAD G + ) && + test_cmp_rev HEAD G +' + +test_expect_success 'rebase --keep-base --no-reapply-cherry-picks' ' + git checkout -f -B main E && + git cherry-pick F && + ( + set_fake_editor && + EXPECT_COUNT=1 git rebase -i --keep-base \ + --no-reapply-cherry-picks HEAD G + ) && + test_cmp_rev HEAD^ C +' + +# This must be the last test in this file +test_expect_success '$EDITOR and friends are unchanged' ' + test_editor_unchanged ' test_done diff --git a/t/t3419-rebase-patch-id.sh b/t/t3419-rebase-patch-id.sh index 295040f2fe..7181f176b8 100755 --- a/t/t3419-rebase-patch-id.sh +++ b/t/t3419-rebase-patch-id.sh @@ -43,15 +43,26 @@ test_expect_success 'setup: 500 lines' ' git add newfile && git commit -q -m "add small file" && - git cherry-pick main >/dev/null 2>&1 -' + git cherry-pick main >/dev/null 2>&1 && + + git branch -f squashed main && + git checkout -q -f squashed && + git reset -q --soft HEAD~2 && + git commit -q -m squashed && + + git branch -f mode main && + git checkout -q -f mode && + test_chmod +x file && + git commit -q -a --amend && -test_expect_success 'setup attributes' ' - echo "file binary" >.gitattributes + git branch -f modeother other && + git checkout -q -f modeother && + test_chmod +x file && + git commit -q -a --amend ' test_expect_success 'detect upstream patch' ' - git checkout -q main && + git checkout -q main^{} && scramble file && git add file && git commit -q -m "change big file again" && @@ -61,14 +72,46 @@ test_expect_success 'detect upstream patch' ' test_must_be_empty revs ' +test_expect_success 'detect upstream patch binary' ' + echo "file binary" >.gitattributes && + git checkout -q other^{} && + git rebase main && + git rev-list main...HEAD~ >revs && + test_must_be_empty revs && + test_when_finished "rm .gitattributes" +' + +test_expect_success 'detect upstream patch modechange' ' + git checkout -q modeother^{} && + git rebase mode && + git rev-list mode...HEAD~ >revs && + test_must_be_empty revs +' + test_expect_success 'do not drop patch' ' - git branch -f squashed main && - git checkout -q -f squashed && - git reset -q --soft HEAD~2 && - git commit -q -m squashed && git checkout -q other^{} && test_must_fail git rebase squashed && - git rebase --quit + test_when_finished "git rebase --abort" +' + +test_expect_success 'do not drop patch binary' ' + echo "file binary" >.gitattributes && + git checkout -q other^{} && + test_must_fail git rebase squashed && + test_when_finished "git rebase --abort" && + test_when_finished "rm .gitattributes" +' + +test_expect_success 'do not drop patch modechange' ' + git checkout -q modeother^{} && + git rebase other && + cat >expected <<-\EOF && + diff --git a/file b/file + old mode 100644 + new mode 100755 + EOF + git diff HEAD~ >modediff && + test_cmp expected modediff ' test_done diff --git a/t/t3431-rebase-fork-point.sh b/t/t3431-rebase-fork-point.sh index 1d0b15380e..70e8136356 100755 --- a/t/t3431-rebase-fork-point.sh +++ b/t/t3431-rebase-fork-point.sh @@ -50,7 +50,7 @@ test_rebase () { test_rebase 'G F E D B A' test_rebase 'G F D B A' --onto D -test_rebase 'G F B A' --keep-base +test_rebase 'G F C B A' --keep-base test_rebase 'G F C E D B A' --no-fork-point test_rebase 'G F C D B A' --no-fork-point --onto D test_rebase 'G F C B A' --no-fork-point --keep-base diff --git a/t/t4141-apply-too-large.sh b/t/t4141-apply-too-large.sh new file mode 100755 index 0000000000..58742d4fc5 --- /dev/null +++ b/t/t4141-apply-too-large.sh @@ -0,0 +1,23 @@ +#!/bin/sh + +test_description='git apply with too-large patch' + +TEST_PASSES_SANITIZE_LEAK=true +. ./test-lib.sh + +test_expect_success EXPENSIVE 'git apply rejects patches that are too large' ' + sz=$((1024 * 1024 * 1023)) && + { + cat <<-\EOF && + diff --git a/file b/file + new file mode 100644 + --- /dev/null + +++ b/file + @@ -0,0 +1 @@ + EOF + test-tool genzeros + } | test_copy_bytes $sz | test_must_fail git apply 2>err && + grep "git apply: failed to read" err +' + +test_done diff --git a/t/t4201-shortlog.sh b/t/t4201-shortlog.sh index 3095b1b2ff..8e4effebdb 100755 --- a/t/t4201-shortlog.sh +++ b/t/t4201-shortlog.sh @@ -83,6 +83,13 @@ test_expect_success 'pretty format' ' test_cmp expect log.predictable ' +test_expect_success 'pretty format (with --date)' ' + sed "s/SUBJECT/2005-04-07 OBJECT_NAME/" expect.template >expect && + git shortlog --format="%ad %H" --date=short HEAD >log && + fuzz log >log.predictable && + test_cmp expect log.predictable +' + test_expect_success '--abbrev' ' sed s/SUBJECT/OBJID/ expect.template >expect && git shortlog --format="%h" --abbrev=35 HEAD >log && @@ -237,6 +244,26 @@ test_expect_success 'shortlog --group=trailer:signed-off-by' ' test_cmp expect actual ' +test_expect_success 'shortlog --group=format' ' + git shortlog -s --date="format:%Y" --group="format:%cN (%cd)" \ + HEAD >actual && + cat >expect <<-\EOF && + 4 C O Mitter (2005) + 1 Sin Nombre (2005) + EOF + test_cmp expect actual +' + +test_expect_success 'shortlog --group=<format> DWIM' ' + git shortlog -s --date="format:%Y" --group="%cN (%cd)" HEAD >actual && + test_cmp expect actual +' + +test_expect_success 'shortlog bogus --group' ' + test_must_fail git shortlog --group=bogus HEAD 2>err && + grep "unknown group type" err +' + test_expect_success 'trailer idents are split' ' cat >expect <<-\EOF && 2 C O Mitter @@ -319,6 +346,18 @@ test_expect_success 'shortlog can match multiple groups' ' test_cmp expect actual ' +test_expect_success 'shortlog can match multiple format groups' ' + GIT_COMMITTER_NAME="$GIT_AUTHOR_NAME" \ + git commit --allow-empty -m "identical names" && + test_tick && + cat >expect <<-\EOF && + 2 A U Thor + 1 C O Mitter + EOF + git shortlog -ns --group="%cn" --group="%an" -2 HEAD >actual && + test_cmp expect actual +' + test_expect_success 'set up option selection tests' ' git commit --allow-empty -F - <<-\EOF subject diff --git a/t/t4204-patch-id.sh b/t/t4204-patch-id.sh index a730c0db98..a7fa94ce0a 100755 --- a/t/t4204-patch-id.sh +++ b/t/t4204-patch-id.sh @@ -8,13 +8,13 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME . ./test-lib.sh test_expect_success 'setup' ' - as="a a a a a a a a" && # eight a - test_write_lines $as >foo && - test_write_lines $as >bar && + str="ab cd ef gh ij kl mn op" && + test_write_lines $str >foo && + test_write_lines $str >bar && git add foo bar && git commit -a -m initial && - test_write_lines $as b >foo && - test_write_lines $as b >bar && + test_write_lines $str b >foo && + test_write_lines $str b >bar && git commit -a -m first && git checkout -b same main && git commit --amend -m same-msg && @@ -22,8 +22,23 @@ test_expect_success 'setup' ' echo c >foo && echo c >bar && git commit --amend -a -m notsame-msg && + git checkout -b with_space main~ && + cat >foo <<-\EOF && + a b + c d + e f + g h + i j + k l + m n + op + EOF + cp foo bar && + git add foo bar && + git commit --amend -m "with spaces" && test_write_lines bar foo >bar-then-foo && test_write_lines foo bar >foo-then-bar + ' test_expect_success 'patch-id output is well-formed' ' @@ -42,7 +57,7 @@ calc_patch_id () { } get_top_diff () { - git log -p -1 "$@" -O bar-then-foo -- + git log -p -1 "$@" -O bar-then-foo --full-index -- } get_patch_id () { @@ -61,6 +76,33 @@ test_expect_success 'patch-id detects inequality' ' get_patch_id notsame && ! test_cmp patch-id_main patch-id_notsame ' +test_expect_success 'patch-id detects equality binary' ' + cat >.gitattributes <<-\EOF && + foo binary + bar binary + EOF + get_patch_id main && + get_patch_id same && + git log -p -1 --binary main >top-diff.output && + calc_patch_id <top-diff.output main_binpatch && + git log -p -1 --binary same >top-diff.output && + calc_patch_id <top-diff.output same_binpatch && + test_cmp patch-id_main patch-id_main_binpatch && + test_cmp patch-id_same patch-id_same_binpatch && + test_cmp patch-id_main patch-id_same && + test_when_finished "rm .gitattributes" +' + +test_expect_success 'patch-id detects inequality binary' ' + cat >.gitattributes <<-\EOF && + foo binary + bar binary + EOF + get_patch_id main && + get_patch_id notsame && + ! test_cmp patch-id_main patch-id_notsame && + test_when_finished "rm .gitattributes" +' test_expect_success 'patch-id supports git-format-patch output' ' get_patch_id main && @@ -101,9 +143,21 @@ test_patch_id_file_order () { git format-patch -1 --stdout -O foo-then-bar >format-patch.output && calc_patch_id <format-patch.output "ordered-$name" "$@" && cmp_patch_id $relevant "$name" "ordered-$name" +} +test_patch_id_whitespace () { + relevant="$1" + shift + name="ws-${1}-$relevant" + shift + get_top_diff "main~" >top-diff.output && + calc_patch_id <top-diff.output "$name" "$@" && + get_top_diff "with_space" >top-diff.output && + calc_patch_id <top-diff.output "ws-$name" "$@" && + cmp_patch_id $relevant "$name" "ws-$name" } + # combined test for options: add more tests here to make them # run with all options test_patch_id () { @@ -119,6 +173,14 @@ test_expect_success 'file order is relevant with --unstable' ' test_patch_id_file_order relevant --unstable --unstable ' +test_expect_success 'whitespace is relevant with --verbatim' ' + test_patch_id_whitespace relevant --verbatim --verbatim +' + +test_expect_success 'whitespace is irrelevant without --verbatim' ' + test_patch_id_whitespace irrelevant --stable --stable +' + #Now test various option combinations. test_expect_success 'default is unstable' ' test_patch_id relevant default @@ -134,6 +196,17 @@ test_expect_success 'patchid.stable = false is unstable' ' test_patch_id relevant patchid.stable=false ' +test_expect_success 'patchid.verbatim = true is correct and stable' ' + test_config patchid.verbatim true && + test_patch_id_whitespace relevant patchid.verbatim=true && + test_patch_id irrelevant patchid.verbatim=true +' + +test_expect_success 'patchid.verbatim = false is unstable' ' + test_config patchid.verbatim false && + test_patch_id relevant patchid.verbatim=false +' + test_expect_success '--unstable overrides patchid.stable = true' ' test_config patchid.stable true && test_patch_id relevant patchid.stable=true--unstable --unstable @@ -144,6 +217,11 @@ test_expect_success '--stable overrides patchid.stable = false' ' test_patch_id irrelevant patchid.stable=false--stable --stable ' +test_expect_success '--verbatim overrides patchid.stable = false' ' + test_config patchid.stable false && + test_patch_id_whitespace relevant stable=false--verbatim --verbatim +' + test_expect_success 'patch-id supports git-format-patch MIME output' ' get_patch_id main && git checkout same && @@ -198,7 +276,10 @@ test_expect_success 'patch-id handles no-nl-at-eof markers' ' EOF calc_patch_id nonl <nonl && calc_patch_id withnl <withnl && - test_cmp patch-id_nonl patch-id_withnl + test_cmp patch-id_nonl patch-id_withnl && + calc_patch_id nonl-inc-ws --verbatim <nonl && + calc_patch_id withnl-inc-ws --verbatim <withnl && + ! test_cmp patch-id_nonl-inc-ws patch-id_withnl-inc-ws ' test_expect_success 'patch-id handles diffs with one line of before/after' ' diff --git a/t/t4301-merge-tree-write-tree.sh b/t/t4301-merge-tree-write-tree.sh index 013b77144b..cac85591b5 100755 --- a/t/t4301-merge-tree-write-tree.sh +++ b/t/t4301-merge-tree-write-tree.sh @@ -819,4 +819,45 @@ test_expect_success SANITY 'merge-ort fails gracefully in a read-only repository test_must_fail git -C read-only merge-tree side1 side2 ' +test_expect_success '--stdin with both a successful and a conflicted merge' ' + printf "side1 side3\nside1 side2" | git merge-tree --stdin >actual && + + git checkout side1^0 && + git merge side3 && + + printf "1\0" >expect && + git rev-parse HEAD^{tree} | lf_to_nul >>expect && + printf "\0" >>expect && + + git checkout side1^0 && + test_must_fail git merge side2 && + sed s/HEAD/side1/ greeting >tmp && + mv tmp greeting && + git add -u && + git mv whatever~HEAD whatever~side1 && + + printf "0\0" >>expect && + git write-tree | lf_to_nul >>expect && + + cat <<-EOF | q_to_tab | lf_to_nul >>expect && + 100644 $(git rev-parse side1~1:greeting) 1Qgreeting + 100644 $(git rev-parse side1:greeting) 2Qgreeting + 100644 $(git rev-parse side2:greeting) 3Qgreeting + 100644 $(git rev-parse side1~1:whatever) 1Qwhatever~side1 + 100644 $(git rev-parse side1:whatever) 2Qwhatever~side1 + EOF + + q_to_nul <<-EOF >>expect && + Q1QgreetingQAuto-mergingQAuto-merging greeting + Q1QgreetingQCONFLICT (contents)QCONFLICT (content): Merge conflict in greeting + Q1QnumbersQAuto-mergingQAuto-merging numbers + Q2Qwhatever~side1QwhateverQCONFLICT (file/directory)QCONFLICT (file/directory): directory in the way of whatever from side1; moving it to whatever~side1 instead. + Q1Qwhatever~side1QCONFLICT (modify/delete)QCONFLICT (modify/delete): whatever~side1 deleted in side2 and modified in side1. Version side1 of whatever~side1 left in tree. + EOF + + printf "\0\0" >>expect && + + test_cmp expect actual +' + test_done diff --git a/t/t5516-fetch-push.sh b/t/t5516-fetch-push.sh index 79dc470c01..4f2bfaf005 100755 --- a/t/t5516-fetch-push.sh +++ b/t/t5516-fetch-push.sh @@ -1853,37 +1853,6 @@ test_expect_success 'refuse to push a hidden ref, and make sure do not pollute t test_dir_is_empty testrepo/.git/objects/pack ' -test_expect_success LIBCURL 'fetch warns or fails when using username:password' ' - message="URL '\''https://username:<redacted>@localhost/'\'' uses plaintext credentials" && - test_must_fail git -c transfer.credentialsInUrl=allow fetch https://username:password@localhost 2>err && - ! grep "$message" err && - - test_must_fail git -c transfer.credentialsInUrl=warn fetch https://username:password@localhost 2>err && - grep "warning: $message" err >warnings && - test_line_count = 3 warnings && - - test_must_fail git -c transfer.credentialsInUrl=die fetch https://username:password@localhost 2>err && - grep "fatal: $message" err >warnings && - test_line_count = 1 warnings && - - test_must_fail git -c transfer.credentialsInUrl=die fetch https://username:@localhost 2>err && - grep "fatal: $message" err >warnings && - test_line_count = 1 warnings -' - - -test_expect_success LIBCURL 'push warns or fails when using username:password' ' - message="URL '\''https://username:<redacted>@localhost/'\'' uses plaintext credentials" && - test_must_fail git -c transfer.credentialsInUrl=allow push https://username:password@localhost 2>err && - ! grep "$message" err && - - test_must_fail git -c transfer.credentialsInUrl=warn push https://username:password@localhost 2>err && - grep "warning: $message" err >warnings && - test_must_fail git -c transfer.credentialsInUrl=die push https://username:password@localhost 2>err && - grep "fatal: $message" err >warnings && - test_line_count = 1 warnings -' - test_expect_success 'push with config push.useBitmaps' ' mk_test testrepo heads/main && git checkout main && diff --git a/t/t5551-http-fetch-smart.sh b/t/t5551-http-fetch-smart.sh index 6a38294a47..64c6c9f59e 100755 --- a/t/t5551-http-fetch-smart.sh +++ b/t/t5551-http-fetch-smart.sh @@ -580,4 +580,81 @@ test_expect_success 'passing hostname resolution information works' ' git -c "http.curloptResolve=$BOGUS_HOST:$LIB_HTTPD_PORT:127.0.0.1" ls-remote "$BOGUS_HTTPD_URL/smart/repo.git" >/dev/null ' +# here user%40host is the URL-encoded version of user@host, +# which is our intentionally-odd username to catch parsing errors +url_user=$HTTPD_URL_USER/auth/smart/repo.git +url_userpass=$HTTPD_URL_USER_PASS/auth/smart/repo.git +url_userblank=$HTTPD_PROTO://user%40host:@$HTTPD_DEST/auth/smart/repo.git +message="URL .*:<redacted>@.* uses plaintext credentials" + +test_expect_success 'clone warns or fails when using username:password' ' + test_when_finished "rm -rf attempt*" && + + git -c transfer.credentialsInUrl=allow \ + clone $url_userpass attempt1 2>err && + ! grep "$message" err && + + git -c transfer.credentialsInUrl=warn \ + clone $url_userpass attempt2 2>err && + grep "warning: $message" err >warnings && + test_line_count -ge 1 warnings && + + test_must_fail git -c transfer.credentialsInUrl=die \ + clone $url_userpass attempt3 2>err && + grep "fatal: $message" err >warnings && + test_line_count -ge 1 warnings && + + test_must_fail git -c transfer.credentialsInUrl=die \ + clone $url_userblank attempt4 2>err && + grep "fatal: $message" err >warnings && + test_line_count -ge 1 warnings +' + +test_expect_success 'clone does not detect username:password when it is https://username@domain:port/' ' + test_when_finished "rm -rf attempt1" && + + # we are relying on lib-httpd for url construction, so document our + # assumptions + case "$HTTPD_URL_USER" in + *:[0-9]*) : ok ;; + *) BUG "httpd url does not have port: $HTTPD_URL_USER" + esac && + + git -c transfer.credentialsInUrl=warn clone $url_user attempt1 2>err && + ! grep "uses plaintext credentials" err +' + +test_expect_success 'fetch warns or fails when using username:password' ' + git -c transfer.credentialsInUrl=allow fetch $url_userpass 2>err && + ! grep "$message" err && + + git -c transfer.credentialsInUrl=warn fetch $url_userpass 2>err && + grep "warning: $message" err >warnings && + test_line_count -ge 1 warnings && + + test_must_fail git -c transfer.credentialsInUrl=die \ + fetch $url_userpass 2>err && + grep "fatal: $message" err >warnings && + test_line_count -ge 1 warnings && + + test_must_fail git -c transfer.credentialsInUrl=die \ + fetch $url_userblank 2>err && + grep "fatal: $message" err >warnings && + test_line_count -ge 1 warnings +' + + +test_expect_success 'push warns or fails when using username:password' ' + git -c transfer.credentialsInUrl=allow push $url_userpass 2>err && + ! grep "$message" err && + + git -c transfer.credentialsInUrl=warn push $url_userpass 2>err && + grep "warning: $message" err >warnings && + + test_must_fail git -c transfer.credentialsInUrl=die \ + push $url_userpass 2>err && + grep "fatal: $message" err >warnings && + test_line_count -ge 1 warnings +' + test_done diff --git a/t/t5558-clone-bundle-uri.sh b/t/t5558-clone-bundle-uri.sh index ad666a2d28..9155f31fa2 100755 --- a/t/t5558-clone-bundle-uri.sh +++ b/t/t5558-clone-bundle-uri.sh @@ -41,6 +41,215 @@ test_expect_success 'clone with file:// bundle' ' test_cmp expect actual ' +# To get interesting tests for bundle lists, we need to construct a +# somewhat-interesting commit history. +# +# ---------------- bundle-4 +# +# 4 +# / \ +# ----|---|------- bundle-3 +# | | +# | 3 +# | | +# ----|---|------- bundle-2 +# | | +# 2 | +# | | +# ----|---|------- bundle-1 +# \ / +# 1 +# | +# (previous commits) +test_expect_success 'construct incremental bundle list' ' + ( + cd clone-from && + git checkout -b base && + test_commit 1 && + git checkout -b left && + test_commit 2 && + git checkout -b right base && + test_commit 3 && + git checkout -b merge left && + git merge right -m "4" && + + git bundle create bundle-1.bundle base && + git bundle create bundle-2.bundle base..left && + git bundle create bundle-3.bundle base..right && + git bundle create bundle-4.bundle merge --not left right + ) +' + +test_expect_success 'clone bundle list (file, no heuristic)' ' + cat >bundle-list <<-EOF && + [bundle] + version = 1 + mode = all + + [bundle "bundle-1"] + uri = file://$(pwd)/clone-from/bundle-1.bundle + + [bundle "bundle-2"] + uri = file://$(pwd)/clone-from/bundle-2.bundle + + [bundle "bundle-3"] + uri = file://$(pwd)/clone-from/bundle-3.bundle + + [bundle "bundle-4"] + uri = file://$(pwd)/clone-from/bundle-4.bundle + EOF + + git clone --bundle-uri="file://$(pwd)/bundle-list" \ + clone-from clone-list-file 2>err && + ! grep "Repository lacks these prerequisite commits" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-list-file cat-file --batch-check <oids && + + git -C clone-list-file for-each-ref --format="%(refname)" >refs && + grep "refs/bundles/" refs >actual && + cat >expect <<-\EOF && + refs/bundles/base + refs/bundles/left + refs/bundles/merge + refs/bundles/right + EOF + test_cmp expect actual +' + +test_expect_success 'clone bundle list (file, all mode, some failures)' ' + cat >bundle-list <<-EOF && + [bundle] + version = 1 + mode = all + + # Does not exist. Should be skipped. + [bundle "bundle-0"] + uri = file://$(pwd)/clone-from/bundle-0.bundle + + [bundle "bundle-1"] + uri = file://$(pwd)/clone-from/bundle-1.bundle + + [bundle "bundle-2"] + uri = file://$(pwd)/clone-from/bundle-2.bundle + + # No bundle-3 means bundle-4 will not apply. + + [bundle "bundle-4"] + uri = file://$(pwd)/clone-from/bundle-4.bundle + + # Does not exist. Should be skipped. + [bundle "bundle-5"] + uri = file://$(pwd)/clone-from/bundle-5.bundle + EOF + + GIT_TRACE2_PERF=1 \ + git clone --bundle-uri="file://$(pwd)/bundle-list" \ + clone-from clone-all-some 2>err && + ! grep "Repository lacks these prerequisite commits" err && + ! grep "fatal" err && + grep "warning: failed to download bundle from URI" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-all-some cat-file --batch-check <oids && + + git -C clone-all-some for-each-ref --format="%(refname)" >refs && + grep "refs/bundles/" refs >actual && + cat >expect <<-\EOF && + refs/bundles/base + refs/bundles/left + EOF + test_cmp expect actual +' + +test_expect_success 'clone bundle list (file, all mode, all failures)' ' + cat >bundle-list <<-EOF && + [bundle] + version = 1 + mode = all + + # Does not exist. Should be skipped. + [bundle "bundle-0"] + uri = file://$(pwd)/clone-from/bundle-0.bundle + + # Does not exist. Should be skipped. + [bundle "bundle-5"] + uri = file://$(pwd)/clone-from/bundle-5.bundle + EOF + + git clone --bundle-uri="file://$(pwd)/bundle-list" \ + clone-from clone-all-fail 2>err && + ! grep "Repository lacks these prerequisite commits" err && + ! grep "fatal" err && + grep "warning: failed to download bundle from URI" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-all-fail cat-file --batch-check <oids && + + git -C clone-all-fail for-each-ref --format="%(refname)" >refs && + ! grep "refs/bundles/" refs +' + +test_expect_success 'clone bundle list (file, any mode)' ' + cat >bundle-list <<-EOF && + [bundle] + version = 1 + mode = any + + # Does not exist. Should be skipped. + [bundle "bundle-0"] + uri = file://$(pwd)/clone-from/bundle-0.bundle + + [bundle "bundle-1"] + uri = file://$(pwd)/clone-from/bundle-1.bundle + + # Does not exist. Should be skipped. + [bundle "bundle-5"] + uri = file://$(pwd)/clone-from/bundle-5.bundle + EOF + + git clone --bundle-uri="file://$(pwd)/bundle-list" \ + clone-from clone-any-file 2>err && + ! grep "Repository lacks these prerequisite commits" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-any-file cat-file --batch-check <oids && + + git -C clone-any-file for-each-ref --format="%(refname)" >refs && + grep "refs/bundles/" refs >actual && + cat >expect <<-\EOF && + refs/bundles/base + EOF + test_cmp expect actual +' + +test_expect_success 'clone bundle list (file, any mode, all failures)' ' + cat >bundle-list <<-EOF && + [bundle] + version = 1 + mode = any + + # Does not exist. Should be skipped. + [bundle "bundle-0"] + uri = $HTTPD_URL/bundle-0.bundle + + # Does not exist. Should be skipped. + [bundle "bundle-5"] + uri = $HTTPD_URL/bundle-5.bundle + EOF + + git clone --bundle-uri="file://$(pwd)/bundle-list" \ + clone-from clone-any-fail 2>err && + ! grep "fatal" err && + grep "warning: failed to download bundle from URI" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-any-fail cat-file --batch-check <oids && + + git -C clone-any-fail for-each-ref --format="%(refname)" >refs && + ! grep "refs/bundles/" refs +' + ######################################################################### # HTTP tests begin here @@ -75,6 +284,72 @@ test_expect_success 'clone HTTP bundle' ' test_config -C clone-http log.excludedecoration refs/bundle/ ' +test_expect_success 'clone bundle list (HTTP, no heuristic)' ' + cp clone-from/bundle-*.bundle "$HTTPD_DOCUMENT_ROOT_PATH/" && + cat >"$HTTPD_DOCUMENT_ROOT_PATH/bundle-list" <<-EOF && + [bundle] + version = 1 + mode = all + + [bundle "bundle-1"] + uri = $HTTPD_URL/bundle-1.bundle + + [bundle "bundle-2"] + uri = $HTTPD_URL/bundle-2.bundle + + [bundle "bundle-3"] + uri = $HTTPD_URL/bundle-3.bundle + + [bundle "bundle-4"] + uri = $HTTPD_URL/bundle-4.bundle + EOF + + git clone --bundle-uri="$HTTPD_URL/bundle-list" \ + clone-from clone-list-http 2>err && + ! grep "Repository lacks these prerequisite commits" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-list-http cat-file --batch-check <oids +' + +test_expect_success 'clone bundle list (HTTP, any mode)' ' + cp clone-from/bundle-*.bundle "$HTTPD_DOCUMENT_ROOT_PATH/" && + cat >"$HTTPD_DOCUMENT_ROOT_PATH/bundle-list" <<-EOF && + [bundle] + version = 1 + mode = any + + # Does not exist. Should be skipped. + [bundle "bundle-0"] + uri = $HTTPD_URL/bundle-0.bundle + + [bundle "bundle-1"] + uri = $HTTPD_URL/bundle-1.bundle + + # Does not exist. Should be skipped. + [bundle "bundle-5"] + uri = $HTTPD_URL/bundle-5.bundle + EOF + + git clone --bundle-uri="$HTTPD_URL/bundle-list" \ + clone-from clone-any-http 2>err && + ! grep "fatal" err && + grep "warning: failed to download bundle from URI" err && + + git -C clone-from for-each-ref --format="%(objectname)" >oids && + git -C clone-any-http cat-file --batch-check <oids && + + git -C clone-list-file for-each-ref --format="%(refname)" >refs && + grep "refs/bundles/" refs >actual && + cat >expect <<-\EOF && + refs/bundles/base + refs/bundles/left + refs/bundles/merge + refs/bundles/right + EOF + test_cmp expect actual +' + # Do not add tests here unless they use the HTTP server, as they will # not run unless the HTTP dependencies exist. diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh index 45f0803ed4..b2524a24c2 100755 --- a/t/t5601-clone.sh +++ b/t/t5601-clone.sh @@ -71,29 +71,6 @@ test_expect_success 'clone respects GIT_WORK_TREE' ' ' -test_expect_success LIBCURL 'clone warns or fails when using username:password' ' - message="URL '\''https://username:<redacted>@localhost/'\'' uses plaintext credentials" && - test_must_fail git -c transfer.credentialsInUrl=allow clone https://username:password@localhost attempt1 2>err && - ! grep "$message" err && - - test_must_fail git -c transfer.credentialsInUrl=warn clone https://username:password@localhost attempt2 2>err && - grep "warning: $message" err >warnings && - test_line_count = 2 warnings && - - test_must_fail git -c transfer.credentialsInUrl=die clone https://username:password@localhost attempt3 2>err && - grep "fatal: $message" err >warnings && - test_line_count = 1 warnings && - - test_must_fail git -c transfer.credentialsInUrl=die clone https://username:@localhost attempt3 2>err && - grep "fatal: $message" err >warnings && - test_line_count = 1 warnings -' - -test_expect_success LIBCURL 'clone does not detect username:password when it is https://username@domain:port/' ' - test_must_fail git -c transfer.credentialsInUrl=warn clone https://username@localhost:8080 attempt3 2>err && - ! grep "uses plaintext credentials" err -' - test_expect_success 'clone from hooks' ' test_create_repo r0 && diff --git a/t/t5750-bundle-uri-parse.sh b/t/t5750-bundle-uri-parse.sh new file mode 100755 index 0000000000..c2fe3f9c5a --- /dev/null +++ b/t/t5750-bundle-uri-parse.sh @@ -0,0 +1,171 @@ +#!/bin/sh + +test_description="Test bundle-uri bundle_uri_parse_line()" + +TEST_NO_CREATE_REPO=1 +TEST_PASSES_SANITIZE_LEAK=true +. ./test-lib.sh + +test_expect_success 'bundle_uri_parse_line() just URIs' ' + cat >in <<-\EOF && + bundle.one.uri=http://example.com/bundle.bdl + bundle.two.uri=https://example.com/bundle.bdl + bundle.three.uri=file:///usr/share/git/bundle.bdl + EOF + + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + [bundle "one"] + uri = http://example.com/bundle.bdl + [bundle "two"] + uri = https://example.com/bundle.bdl + [bundle "three"] + uri = file:///usr/share/git/bundle.bdl + EOF + + test-tool bundle-uri parse-key-values in >actual 2>err && + test_must_be_empty err && + test_cmp_config_output expect actual +' + +test_expect_success 'bundle_uri_parse_line() parsing edge cases: empty key or value' ' + cat >in <<-\EOF && + =bogus-value + bogus-key= + EOF + + cat >err.expect <<-EOF && + error: bundle-uri: line has empty key or value + error: bad line: '\''=bogus-value'\'' + error: bundle-uri: line has empty key or value + error: bad line: '\''bogus-key='\'' + EOF + + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + EOF + + test_must_fail test-tool bundle-uri parse-key-values in >actual 2>err && + test_cmp err.expect err && + test_cmp_config_output expect actual +' + +test_expect_success 'bundle_uri_parse_line() parsing edge cases: empty lines' ' + cat >in <<-\EOF && + bundle.one.uri=http://example.com/bundle.bdl + + bundle.two.uri=https://example.com/bundle.bdl + + bundle.three.uri=file:///usr/share/git/bundle.bdl + EOF + + cat >err.expect <<-\EOF && + error: bundle-uri: got an empty line + error: bad line: '\'''\'' + error: bundle-uri: got an empty line + error: bad line: '\'''\'' + EOF + + # We fail, but try to continue parsing regardless + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + [bundle "one"] + uri = http://example.com/bundle.bdl + [bundle "two"] + uri = https://example.com/bundle.bdl + [bundle "three"] + uri = file:///usr/share/git/bundle.bdl + EOF + + test_must_fail test-tool bundle-uri parse-key-values in >actual 2>err && + test_cmp err.expect err && + test_cmp_config_output expect actual +' + +test_expect_success 'bundle_uri_parse_line() parsing edge cases: duplicate lines' ' + cat >in <<-\EOF && + bundle.one.uri=http://example.com/bundle.bdl + bundle.two.uri=https://example.com/bundle.bdl + bundle.one.uri=https://example.com/bundle-2.bdl + bundle.three.uri=file:///usr/share/git/bundle.bdl + EOF + + cat >err.expect <<-\EOF && + error: bad line: '\''bundle.one.uri=https://example.com/bundle-2.bdl'\'' + EOF + + # We fail, but try to continue parsing regardless + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + [bundle "one"] + uri = http://example.com/bundle.bdl + [bundle "two"] + uri = https://example.com/bundle.bdl + [bundle "three"] + uri = file:///usr/share/git/bundle.bdl + EOF + + test_must_fail test-tool bundle-uri parse-key-values in >actual 2>err && + test_cmp err.expect err && + test_cmp_config_output expect actual +' + +test_expect_success 'parse config format: just URIs' ' + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + [bundle "one"] + uri = http://example.com/bundle.bdl + [bundle "two"] + uri = https://example.com/bundle.bdl + [bundle "three"] + uri = file:///usr/share/git/bundle.bdl + EOF + + test-tool bundle-uri parse-config expect >actual 2>err && + test_must_be_empty err && + test_cmp_config_output expect actual +' + +test_expect_success 'parse config format edge cases: empty key or value' ' + cat >in1 <<-\EOF && + = bogus-value + EOF + + cat >err1 <<-EOF && + error: bad config line 1 in file in1 + EOF + + cat >expect <<-\EOF && + [bundle] + version = 1 + mode = all + EOF + + test_must_fail test-tool bundle-uri parse-config in1 >actual 2>err && + test_cmp err1 err && + test_cmp_config_output expect actual && + + cat >in2 <<-\EOF && + bogus-key = + EOF + + cat >err2 <<-EOF && + error: bad config line 1 in file in2 + EOF + + test_must_fail test-tool bundle-uri parse-config in2 >actual 2>err && + test_cmp err2 err && + test_cmp_config_output expect actual +' + +test_done diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh index dcaab7265f..fa38b87441 100755 --- a/t/t6300-for-each-ref.sh +++ b/t/t6300-for-each-ref.sh @@ -1406,4 +1406,44 @@ test_expect_success 'for-each-ref reports broken tags' ' refs/tags/broken-tag-* ' +test_expect_success 'set up tag with signature and no blank lines' ' + git tag -F - fake-sig-no-blanks <<-\EOF + this is the subject + -----BEGIN PGP SIGNATURE----- + not a real signature, but we just care about the + subject/body parsing. It is important here that + there are no blank lines in the signature. + -----END PGP SIGNATURE----- + EOF +' + +test_atom refs/tags/fake-sig-no-blanks contents:subject 'this is the subject' +test_atom refs/tags/fake-sig-no-blanks contents:body '' +test_atom refs/tags/fake-sig-no-blanks contents:signature "$sig" + +test_expect_success 'set up tag with CRLF signature' ' + append_cr <<-\EOF | + this is the subject + -----BEGIN PGP SIGNATURE----- + + not a real signature, but we just care about + the subject/body parsing. It is important here + that there is a blank line separating this + from the signature header. + -----END PGP SIGNATURE----- + EOF + git tag -F - --cleanup=verbatim fake-sig-crlf +' + +test_atom refs/tags/fake-sig-crlf contents:subject 'this is the subject' +test_atom refs/tags/fake-sig-crlf contents:body '' + +# CRLF is retained in the signature, so we have to pass our expected value +# through append_cr. But test_atom requires a shell string, which means command +# substitution, and the shell will strip trailing newlines from the output of +# the substitution. Hack around it by adding and then removing a dummy line. +sig_crlf="$(printf "%s" "$sig" | append_cr; echo dummy)" +sig_crlf=${sig_crlf%dummy} +test_atom refs/tags/fake-sig-crlf contents:signature "$sig_crlf" + test_done diff --git a/t/t6423-merge-rename-directories.sh b/t/t6423-merge-rename-directories.sh index a4941878fe..944de75b80 100755 --- a/t/t6423-merge-rename-directories.sh +++ b/t/t6423-merge-rename-directories.sh @@ -5304,6 +5304,62 @@ test_expect_merge_algorithm failure success '12l (A into B): Rename into each ot ) ' +# Testcase 12m, Directory rename, plus change of parent dir to symlink +# Commit O: dir/subdir/file +# Commit A: renamed-dir/subdir/file +# Commit B: dir/subdir +# In words: +# A: dir/subdir/ -> renamed-dir/subdir +# B: delete dir/subdir/file, add dir/subdir as symlink +# +# Expected: CONFLICT (rename/delete): renamed-dir/subdir/file, +# CONFLICT (file location): renamed-dir/subdir vs. dir/subdir +# CONFLICT (directory/file): renamed-dir/subdir symlink has +# renamed-dir/subdir in the way + +test_setup_12m () { + git init 12m && + ( + cd 12m && + + mkdir -p dir/subdir && + echo 1 >dir/subdir/file && + git add . && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git switch A && + git mv dir/ renamed-dir/ && + git add . && + git commit -m "A" && + + git switch B && + git rm dir/subdir/file && + mkdir dir && + ln -s /dev/null dir/subdir && + git add . && + git commit -m "B" + ) +} + +test_expect_merge_algorithm failure success '12m: Change parent of renamed-dir to symlink on other side' ' + test_setup_12m && + ( + cd 12m && + + git checkout -q A^0 && + + test_must_fail git -c merge.directoryRenames=conflict merge -s recursive B^0 && + + test_stdout_line_count = 3 git ls-files -s && + test_stdout_line_count = 2 ls -1 renamed-dir && + test_path_is_missing dir + ) +' + ########################################################################### # SECTION 13: Checking informational and conflict messages # diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh index cd6c53360d..d9acb63951 100755 --- a/t/t6500-gc.sh +++ b/t/t6500-gc.sh @@ -202,6 +202,102 @@ test_expect_success 'one of gc.reflogExpire{Unreachable,}=never does not skip "e grep -E "^trace: (built-in|exec|run_command): git reflog expire --" trace.out ' +prepare_cruft_history () { + test_commit base && + + test_commit --no-tag foo && + test_commit --no-tag bar && + git reset HEAD^^ +} + +assert_cruft_packs () { + find .git/objects/pack -name "*.mtimes" >mtimes && + sed -e 's/\.mtimes$/\.pack/g' mtimes >packs && + + test_file_not_empty packs && + while read pack + do + test_path_is_file "$pack" || return 1 + done <packs +} + +assert_no_cruft_packs () { + find .git/objects/pack -name "*.mtimes" >mtimes && + test_must_be_empty mtimes +} + +test_expect_success 'gc --cruft generates a cruft pack' ' + test_when_finished "rm -fr crufts" && + git init crufts && + ( + cd crufts && + + prepare_cruft_history && + git gc --cruft && + assert_cruft_packs + ) +' + +test_expect_success 'gc.cruftPacks=true generates a cruft pack' ' + test_when_finished "rm -fr crufts" && + git init crufts && + ( + cd crufts && + + prepare_cruft_history && + git -c gc.cruftPacks=true gc && + assert_cruft_packs + ) +' + +test_expect_success 'feature.experimental=true generates a cruft pack' ' + git init crufts && + test_when_finished "rm -fr crufts" && + ( + cd crufts && + + prepare_cruft_history && + git -c feature.experimental=true gc && + assert_cruft_packs + ) +' + +test_expect_success 'feature.experimental=false allows explicit cruft packs' ' + git init crufts && + test_when_finished "rm -fr crufts" && + ( + cd crufts && + + prepare_cruft_history && + git -c gc.cruftPacks=true -c feature.experimental=false gc && + assert_cruft_packs + ) +' + +test_expect_success 'feature.experimental=true can be overridden' ' + git init crufts && + test_when_finished "rm -fr crufts" && + ( + cd crufts && + + prepare_cruft_history && + git -c feature.expiremental=true -c gc.cruftPacks=false gc && + assert_no_cruft_packs + ) +' + +test_expect_success 'feature.experimental=false avoids cruft packs by default' ' + git init crufts && + test_when_finished "rm -fr crufts" && + ( + cd crufts && + + prepare_cruft_history && + git -c feature.experimental=false gc && + assert_no_cruft_packs + ) +' + run_and_wait_for_auto_gc () { # We read stdout from gc for the side effect of waiting until the # background gc process exits, closing its fd 9. Furthermore, the diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh index 10e4e9663b..5be483bf88 100755 --- a/t/t7700-repack.sh +++ b/t/t7700-repack.sh @@ -477,6 +477,22 @@ test_expect_success TTY '--quiet disables progress' ' test_must_be_empty stderr ' +test_expect_success 'clean up .tmp-* packs on error' ' + test_must_fail ok=sigpipe git \ + -c repack.cruftwindow=bogus \ + repack -ad --cruft && + find $objdir/pack -name '.tmp-*' >tmpfiles && + test_must_be_empty tmpfiles +' + +test_expect_success 'repack -ad cleans up old .tmp-* packs' ' + git rev-parse HEAD >input && + git pack-objects $objdir/pack/.tmp-1234 <input && + git repack -ad && + find $objdir/pack -name '.tmp-*' >tmpfiles && + test_must_be_empty tmpfiles +' + test_expect_success 'setup for update-server-info' ' git init update-server-info && test_commit -C update-server-info message diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index 527a714500..796093a7b3 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -273,13 +273,13 @@ debug () { # <file>, <contents>, and <tag> all default to <message>. test_commit () { - notick= && - echo=echo && - append= && - author= && - signoff= && - indir= && - tag=light && + local notick= && + local echo=echo && + local append= && + local author= && + local signoff= && + local indir= && + local tag=light && while test $# != 0 do case "$1" in @@ -322,7 +322,7 @@ test_commit () { shift done && indir=${indir:+"$indir"/} && - file=${2:-"$1.t"} && + local file=${2:-"$1.t"} && if test -n "$append" then $echo "${3-$1}" >>"$indir$file" @@ -921,10 +921,6 @@ test_path_is_missing () { then echo "Path exists:" ls -ld "$1" - if test $# -ge 1 - then - echo "$*" - fi false fi } @@ -1868,3 +1864,14 @@ test_is_magic_mtime () { rm -f .git/test-mtime-actual return $ret } + +# Given two filenames, parse both using 'git config --list --file' +# and compare the sorted output of those commands. Useful when +# wanting to ignore whitespace differences and sorting concerns. +test_cmp_config_output () { + git config --list --file="$1" >config-expect && + git config --list --file="$2" >config-actual && + sort config-expect >sorted-expect && + sort config-actual >sorted-actual && + test_cmp sorted-expect sorted-actual +} @@ -8,11 +8,13 @@ #include "version.h" #include "trace2/tr2_cfg.h" #include "trace2/tr2_cmd_name.h" +#include "trace2/tr2_ctr.h" #include "trace2/tr2_dst.h" #include "trace2/tr2_sid.h" #include "trace2/tr2_sysenv.h" #include "trace2/tr2_tgt.h" #include "trace2/tr2_tls.h" +#include "trace2/tr2_tmr.h" static int trace2_enabled; @@ -52,7 +54,7 @@ static struct tr2_tgt *tr2_tgt_builtins[] = * Force (rather than lazily) initialize any of the requested * builtin TRACE2 targets at startup (and before we've seen an * actual TRACE2 event call) so we can see if we need to setup - * the TR2 and TLS machinery. + * private data structures and thread-local storage. * * Return the number of builtin targets enabled. */ @@ -83,6 +85,39 @@ static void tr2_tgt_disable_builtins(void) tgt_j->pfn_term(); } +/* + * The signature of this function must match the pfn_timer + * method in the targets. (Think of this is an apply operation + * across the set of active targets.) + */ +static void tr2_tgt_emit_a_timer(const struct tr2_timer_metadata *meta, + const struct tr2_timer *timer, + int is_final_data) +{ + struct tr2_tgt *tgt_j; + int j; + + for_each_wanted_builtin (j, tgt_j) + if (tgt_j->pfn_timer) + tgt_j->pfn_timer(meta, timer, is_final_data); +} + +/* + * The signature of this function must match the pfn_counter + * method in the targets. + */ +static void tr2_tgt_emit_a_counter(const struct tr2_counter_metadata *meta, + const struct tr2_counter *counter, + int is_final_data) +{ + struct tr2_tgt *tgt_j; + int j; + + for_each_wanted_builtin (j, tgt_j) + if (tgt_j->pfn_counter) + tgt_j->pfn_counter(meta, counter, is_final_data); +} + static int tr2main_exit_code; /* @@ -110,6 +145,32 @@ static void tr2main_atexit_handler(void) */ tr2tls_pop_unwind_self(); + /* + * Some timers want per-thread details. If the main thread + * used one of those timers, emit the details now (before + * we emit the aggregate timer values). + * + * Likewise for counters. + */ + tr2_emit_per_thread_timers(tr2_tgt_emit_a_timer); + tr2_emit_per_thread_counters(tr2_tgt_emit_a_counter); + + /* + * Add stopwatch timer and counter data for the main thread to + * the final totals. And then emit the final values. + * + * Technically, we shouldn't need to hold the lock to update + * and output the final_timer_block and final_counter_block + * (since all other threads should be dead by now), but it + * doesn't hurt anything. + */ + tr2tls_lock(); + tr2_update_final_timers(); + tr2_update_final_counters(); + tr2_emit_final_timers(tr2_tgt_emit_a_timer); + tr2_emit_final_counters(tr2_tgt_emit_a_counter); + tr2tls_unlock(); + for_each_wanted_builtin (j, tgt_j) if (tgt_j->pfn_atexit) tgt_j->pfn_atexit(us_elapsed_absolute, @@ -466,7 +527,7 @@ void trace2_exec_result_fl(const char *file, int line, int exec_id, int code) file, line, us_elapsed_absolute, exec_id, code); } -void trace2_thread_start_fl(const char *file, int line, const char *thread_name) +void trace2_thread_start_fl(const char *file, int line, const char *thread_base_name) { struct tr2_tgt *tgt_j; int j; @@ -488,14 +549,14 @@ void trace2_thread_start_fl(const char *file, int line, const char *thread_name) */ trace2_region_enter_printf_fl(file, line, NULL, NULL, NULL, "thread-proc on main: %s", - thread_name); + thread_base_name); return; } us_now = getnanotime() / 1000; us_elapsed_absolute = tr2tls_absolute_elapsed(us_now); - tr2tls_create_self(thread_name, us_now); + tr2tls_create_self(thread_base_name, us_now); for_each_wanted_builtin (j, tgt_j) if (tgt_j->pfn_thread_start_fl) @@ -541,6 +602,25 @@ void trace2_thread_exit_fl(const char *file, int line) tr2tls_pop_unwind_self(); us_elapsed_thread = tr2tls_region_elasped_self(us_now); + /* + * Some timers want per-thread details. If this thread used + * one of those timers, emit the details now. + * + * Likewise for counters. + */ + tr2_emit_per_thread_timers(tr2_tgt_emit_a_timer); + tr2_emit_per_thread_counters(tr2_tgt_emit_a_counter); + + /* + * Add stopwatch timer and counter data from the current + * (non-main) thread to the final totals. (We'll accumulate + * data for the main thread later during "atexit".) + */ + tr2tls_lock(); + tr2_update_final_timers(); + tr2_update_final_counters(); + tr2tls_unlock(); + for_each_wanted_builtin (j, tgt_j) if (tgt_j->pfn_thread_exit_fl) tgt_j->pfn_thread_exit_fl(file, line, @@ -795,6 +875,39 @@ void trace2_printf_fl(const char *file, int line, const char *fmt, ...) va_end(ap); } +void trace2_timer_start(enum trace2_timer_id tid) +{ + if (!trace2_enabled) + return; + + if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS) + BUG("trace2_timer_start: invalid timer id: %d", tid); + + tr2_start_timer(tid); +} + +void trace2_timer_stop(enum trace2_timer_id tid) +{ + if (!trace2_enabled) + return; + + if (tid < 0 || tid >= TRACE2_NUMBER_OF_TIMERS) + BUG("trace2_timer_stop: invalid timer id: %d", tid); + + tr2_stop_timer(tid); +} + +void trace2_counter_add(enum trace2_counter_id cid, uint64_t value) +{ + if (!trace2_enabled) + return; + + if (cid < 0 || cid >= TRACE2_NUMBER_OF_COUNTERS) + BUG("trace2_counter_add: invalid counter id: %d", cid); + + tr2_counter_increment(cid, value); +} + const char *trace2_session_id(void) { return tr2_sid_get(); @@ -51,6 +51,8 @@ struct json_writer; * [] trace2_region* -- emit region nesting messages. * [] trace2_data* -- emit region/thread/repo data messages. * [] trace2_printf* -- legacy trace[1] messages. + * [] trace2_timer* -- stopwatch timers (messages are deferred). + * [] trace2_counter* -- global counters (messages are deferred). */ /* @@ -73,8 +75,7 @@ void trace2_initialize_clock(void); /* * Initialize TRACE2 tracing facility if any of the builtin TRACE2 * targets are enabled in the system config or the environment. - * This includes setting up the Trace2 thread local storage (TLS). - * Emits a 'version' message containing the version of git + * This emits a 'version' message containing the version of git * and the Trace2 protocol. * * This function should be called from `main()` as early as possible in @@ -302,21 +303,23 @@ void trace2_exec_result_fl(const char *file, int line, int exec_id, int code); /* * Emit a 'thread_start' event. This must be called from inside the - * thread-proc to set up the trace2 TLS data for the thread. + * thread-proc to allow the thread to create its own thread-local + * storage. * - * Thread names should be descriptive, like "preload_index". - * Thread names will be decorated with an instance number automatically. + * The thread base name should be descriptive, like "preload_index" or + * taken from the thread-proc function. A unique thread name will be + * created from the given base name and the thread id automatically. */ void trace2_thread_start_fl(const char *file, int line, - const char *thread_name); + const char *thread_base_name); -#define trace2_thread_start(thread_name) \ - trace2_thread_start_fl(__FILE__, __LINE__, (thread_name)) +#define trace2_thread_start(thread_base_name) \ + trace2_thread_start_fl(__FILE__, __LINE__, (thread_base_name)) /* * Emit a 'thread_exit' event. This must be called from inside the - * thread-proc to report thread-specific data and cleanup TLS data - * for the thread. + * thread-proc so that the thread can access and clean up its + * thread-local storage. */ void trace2_thread_exit_fl(const char *file, int line); @@ -485,6 +488,84 @@ void trace2_printf_fl(const char *file, int line, const char *fmt, ...); #define trace2_printf(...) trace2_printf_fl(__FILE__, __LINE__, __VA_ARGS__) /* + * Define the set of stopwatch timers. + * + * We can add more at any time, but they must be defined at compile + * time (to avoid the need to dynamically allocate and synchronize + * them between different threads). + * + * These must start at 0 and be contiguous (because we use them + * elsewhere as array indexes). + * + * Any values added to this enum must also be added to the + * `tr2_timer_metadata[]` in `trace2/tr2_tmr.c`. + */ +enum trace2_timer_id { + /* + * Define two timers for testing. See `t/helper/test-trace2.c`. + * These can be used for ad hoc testing, but should not be used + * for permanent analysis code. + */ + TRACE2_TIMER_ID_TEST1 = 0, /* emits summary event only */ + TRACE2_TIMER_ID_TEST2, /* emits summary and thread events */ + + /* Add additional timer definitions before here. */ + TRACE2_NUMBER_OF_TIMERS +}; + +/* + * Start/Stop the indicated stopwatch timer in the current thread. + * + * The time spent by the current thread between the _start and _stop + * calls will be added to the thread's partial sum for this timer. + * + * Timer events are emitted at thread and program exit. + * + * Note: Since the stopwatch API routines do not generate individual + * events, they do not take (file, line) arguments. Similarly, the + * category and timer name values are defined at compile-time in the + * timer definitions array, so they are not needed here in the API. + */ +void trace2_timer_start(enum trace2_timer_id tid); +void trace2_timer_stop(enum trace2_timer_id tid); + +/* + * Define the set of global counters. + * + * We can add more at any time, but they must be defined at compile + * time (to avoid the need to dynamically allocate and synchronize + * them between different threads). + * + * These must start at 0 and be contiguous (because we use them + * elsewhere as array indexes). + * + * Any values added to this enum be also be added to the + * `tr2_counter_metadata[]` in `trace2/tr2_tr2_ctr.c`. + */ +enum trace2_counter_id { + /* + * Define two counters for testing. See `t/helper/test-trace2.c`. + * These can be used for ad hoc testing, but should not be used + * for permanent analysis code. + */ + TRACE2_COUNTER_ID_TEST1 = 0, /* emits summary event only */ + TRACE2_COUNTER_ID_TEST2, /* emits summary and thread events */ + + /* Add additional counter definitions before here. */ + TRACE2_NUMBER_OF_COUNTERS +}; + +/* + * Increase the named global counter by value. + * + * Note that this adds `value` to the current thread's partial sum for + * this counter (without locking) and that the complete sum is not + * available until all threads have exited, so it does not return the + * new value of the counter. + */ +void trace2_counter_add(enum trace2_counter_id cid, uint64_t value); + +/* * Optional platform-specific code to dump information about the * current and any parent process(es). This is intended to allow * post-processors to know who spawned this git instance and anything diff --git a/trace2/tr2_ctr.c b/trace2/tr2_ctr.c new file mode 100644 index 0000000000..483ca7c308 --- /dev/null +++ b/trace2/tr2_ctr.c @@ -0,0 +1,101 @@ +#include "cache.h" +#include "thread-utils.h" +#include "trace2/tr2_tgt.h" +#include "trace2/tr2_tls.h" +#include "trace2/tr2_ctr.h" + +/* + * A global counter block to aggregrate values from the partial sums + * from each thread. + */ +static struct tr2_counter_block final_counter_block; /* access under tr2tls_mutex */ + +/* + * Define metadata for each global counter. + * + * This array must match the "enum trace2_counter_id" and the values + * in "struct tr2_counter_block.counter[*]". + */ +static struct tr2_counter_metadata tr2_counter_metadata[TRACE2_NUMBER_OF_COUNTERS] = { + [TRACE2_COUNTER_ID_TEST1] = { + .category = "test", + .name = "test1", + .want_per_thread_events = 0, + }, + [TRACE2_COUNTER_ID_TEST2] = { + .category = "test", + .name = "test2", + .want_per_thread_events = 1, + }, + + /* Add additional metadata before here. */ +}; + +void tr2_counter_increment(enum trace2_counter_id cid, uint64_t value) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + struct tr2_counter *c = &ctx->counter_block.counter[cid]; + + c->value += value; + + ctx->used_any_counter = 1; + if (tr2_counter_metadata[cid].want_per_thread_events) + ctx->used_any_per_thread_counter = 1; +} + +void tr2_update_final_counters(void) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + enum trace2_counter_id cid; + + if (!ctx->used_any_counter) + return; + + /* + * Access `final_counter_block` requires holding `tr2tls_mutex`. + * We assume that our caller is holding the lock. + */ + + for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) { + struct tr2_counter *c_final = &final_counter_block.counter[cid]; + const struct tr2_counter *c = &ctx->counter_block.counter[cid]; + + c_final->value += c->value; + } +} + +void tr2_emit_per_thread_counters(tr2_tgt_evt_counter_t *fn_apply) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + enum trace2_counter_id cid; + + if (!ctx->used_any_per_thread_counter) + return; + + /* + * For each counter, if the counter wants per-thread events + * and this thread used it (the value is non-zero), emit it. + */ + for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) + if (tr2_counter_metadata[cid].want_per_thread_events && + ctx->counter_block.counter[cid].value) + fn_apply(&tr2_counter_metadata[cid], + &ctx->counter_block.counter[cid], + 0); +} + +void tr2_emit_final_counters(tr2_tgt_evt_counter_t *fn_apply) +{ + enum trace2_counter_id cid; + + /* + * Access `final_counter_block` requires holding `tr2tls_mutex`. + * We assume that our caller is holding the lock. + */ + + for (cid = 0; cid < TRACE2_NUMBER_OF_COUNTERS; cid++) + if (final_counter_block.counter[cid].value) + fn_apply(&tr2_counter_metadata[cid], + &final_counter_block.counter[cid], + 1); +} diff --git a/trace2/tr2_ctr.h b/trace2/tr2_ctr.h new file mode 100644 index 0000000000..a2267ee990 --- /dev/null +++ b/trace2/tr2_ctr.h @@ -0,0 +1,104 @@ +#ifndef TR2_CTR_H +#define TR2_CTR_H + +#include "trace2.h" +#include "trace2/tr2_tgt.h" + +/* + * Define a mechanism to allow global "counters". + * + * Counters can be used count interesting activity that does not fit + * the "region and data" model, such as code called from many + * different regions and/or where you want to count a number of items, + * but don't have control of when the last item will be processed, + * such as counter the number of calls to `lstat()`. + * + * Counters differ from Trace2 "data" events. Data events are emitted + * immediately and are appropriate for documenting loop counters at + * the end of a region, for example. Counter values are accumulated + * during the program and final counter values are emitted at program + * exit. + * + * To make this model efficient, we define a compile-time fixed set of + * counters and counter ids using a fixed size "counter block" array + * in thread-local storage. This gives us constant time, lock-free + * access to each counter within each thread. This lets us avoid the + * complexities of dynamically allocating a counter and sharing that + * definition with other threads. + * + * Each thread uses the counter block in its thread-local storage to + * increment partial sums for each counter (without locking). When a + * thread exits, those partial sums are (under lock) added to the + * global final sum. + * + * Partial sums for each counter are optionally emitted when a thread + * exits. + * + * Final sums for each counter are emitted between the "exit" and + * "atexit" events. + * + * A parallel "counter metadata" table contains the "category" and + * "name" fields for each counter. This eliminates the need to + * include those args in the various counter APIs. + */ + +/* + * The definition of an individual counter as used by an individual + * thread (and later in aggregation). + */ +struct tr2_counter { + uint64_t value; +}; + +/* + * Metadata for a counter. + */ +struct tr2_counter_metadata { + const char *category; + const char *name; + + /* + * True if we should emit per-thread events for this counter + * when individual threads exit. + */ + unsigned int want_per_thread_events:1; +}; + +/* + * A compile-time fixed block of counters to insert into thread-local + * storage. This wrapper is used to avoid quirks of C and the usual + * need to pass an array size argument. + */ +struct tr2_counter_block { + struct tr2_counter counter[TRACE2_NUMBER_OF_COUNTERS]; +}; + +/* + * Private routines used by trace2.c to increment a counter for the + * current thread. + */ +void tr2_counter_increment(enum trace2_counter_id cid, uint64_t value); + +/* + * Add the current thread's counter data to the global totals. + * This is called during thread-exit. + * + * Caller must be holding the tr2tls_mutex. + */ +void tr2_update_final_counters(void); + +/* + * Emit per-thread counter data for the current thread. + * This is called during thread-exit. + */ +void tr2_emit_per_thread_counters(tr2_tgt_evt_counter_t *fn_apply); + +/* + * Emit global counter values. + * This is called during atexit handling. + * + * Caller must be holding the tr2tls_mutex. + */ +void tr2_emit_final_counters(tr2_tgt_evt_counter_t *fn_apply); + +#endif /* TR2_CTR_H */ diff --git a/trace2/tr2_tgt.h b/trace2/tr2_tgt.h index 65f94e1574..bf8745c4f0 100644 --- a/trace2/tr2_tgt.h +++ b/trace2/tr2_tgt.h @@ -4,6 +4,12 @@ struct child_process; struct repository; struct json_writer; +struct tr2_timer_metadata; +struct tr2_timer; +struct tr2_counter_metadata; +struct tr2_counter; + +#define NS_TO_SEC(ns) ((double)(ns) / 1.0e9) /* * Function prototypes for a TRACE2 "target" vtable. @@ -96,6 +102,14 @@ typedef void(tr2_tgt_evt_printf_va_fl_t)(const char *file, int line, uint64_t us_elapsed_absolute, const char *fmt, va_list ap); +typedef void(tr2_tgt_evt_timer_t)(const struct tr2_timer_metadata *meta, + const struct tr2_timer *timer, + int is_final_data); + +typedef void(tr2_tgt_evt_counter_t)(const struct tr2_counter_metadata *meta, + const struct tr2_counter *counter, + int is_final_data); + /* * "vtable" for a TRACE2 target. Use NULL if a target does not want * to emit that message. @@ -132,6 +146,8 @@ struct tr2_tgt { tr2_tgt_evt_data_fl_t *pfn_data_fl; tr2_tgt_evt_data_json_fl_t *pfn_data_json_fl; tr2_tgt_evt_printf_va_fl_t *pfn_printf_va_fl; + tr2_tgt_evt_timer_t *pfn_timer; + tr2_tgt_evt_counter_t *pfn_counter; }; /* clang-format on */ diff --git a/trace2/tr2_tgt_event.c b/trace2/tr2_tgt_event.c index 37a3163be1..16f6332755 100644 --- a/trace2/tr2_tgt_event.c +++ b/trace2/tr2_tgt_event.c @@ -9,6 +9,7 @@ #include "trace2/tr2_sysenv.h" #include "trace2/tr2_tgt.h" #include "trace2/tr2_tls.h" +#include "trace2/tr2_tmr.h" static struct tr2_dst tr2dst_event = { .sysenv_var = TR2_SYSENV_EVENT, @@ -90,7 +91,7 @@ static void event_fmt_prepare(const char *event_name, const char *file, jw_object_string(jw, "event", event_name); jw_object_string(jw, "sid", tr2_sid_get()); - jw_object_string(jw, "thread", ctx->thread_name.buf); + jw_object_string(jw, "thread", ctx->thread_name); /* * In brief mode, only emit <time> on these 2 event types. @@ -617,6 +618,48 @@ static void fn_data_json_fl(const char *file, int line, } } +static void fn_timer(const struct tr2_timer_metadata *meta, + const struct tr2_timer *timer, + int is_final_data) +{ + const char *event_name = is_final_data ? "timer" : "th_timer"; + struct json_writer jw = JSON_WRITER_INIT; + double t_total = NS_TO_SEC(timer->total_ns); + double t_min = NS_TO_SEC(timer->min_ns); + double t_max = NS_TO_SEC(timer->max_ns); + + jw_object_begin(&jw, 0); + event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw); + jw_object_string(&jw, "category", meta->category); + jw_object_string(&jw, "name", meta->name); + jw_object_intmax(&jw, "intervals", timer->interval_count); + jw_object_double(&jw, "t_total", 6, t_total); + jw_object_double(&jw, "t_min", 6, t_min); + jw_object_double(&jw, "t_max", 6, t_max); + jw_end(&jw); + + tr2_dst_write_line(&tr2dst_event, &jw.json); + jw_release(&jw); +} + +static void fn_counter(const struct tr2_counter_metadata *meta, + const struct tr2_counter *counter, + int is_final_data) +{ + const char *event_name = is_final_data ? "counter" : "th_counter"; + struct json_writer jw = JSON_WRITER_INIT; + + jw_object_begin(&jw, 0); + event_fmt_prepare(event_name, __FILE__, __LINE__, NULL, &jw); + jw_object_string(&jw, "category", meta->category); + jw_object_string(&jw, "name", meta->name); + jw_object_intmax(&jw, "count", counter->value); + jw_end(&jw); + + tr2_dst_write_line(&tr2dst_event, &jw.json); + jw_release(&jw); +} + struct tr2_tgt tr2_tgt_event = { .pdst = &tr2dst_event, @@ -648,4 +691,6 @@ struct tr2_tgt tr2_tgt_event = { .pfn_data_fl = fn_data_fl, .pfn_data_json_fl = fn_data_json_fl, .pfn_printf_va_fl = NULL, + .pfn_timer = fn_timer, + .pfn_counter = fn_counter, }; diff --git a/trace2/tr2_tgt_normal.c b/trace2/tr2_tgt_normal.c index 69f8033077..fbbef68dfc 100644 --- a/trace2/tr2_tgt_normal.c +++ b/trace2/tr2_tgt_normal.c @@ -8,6 +8,7 @@ #include "trace2/tr2_tbuf.h" #include "trace2/tr2_tgt.h" #include "trace2/tr2_tls.h" +#include "trace2/tr2_tmr.h" static struct tr2_dst tr2dst_normal = { .sysenv_var = TR2_SYSENV_NORMAL, @@ -329,6 +330,42 @@ static void fn_printf_va_fl(const char *file, int line, strbuf_release(&buf_payload); } +static void fn_timer(const struct tr2_timer_metadata *meta, + const struct tr2_timer *timer, + int is_final_data) +{ + const char *event_name = is_final_data ? "timer" : "th_timer"; + struct strbuf buf_payload = STRBUF_INIT; + double t_total = NS_TO_SEC(timer->total_ns); + double t_min = NS_TO_SEC(timer->min_ns); + double t_max = NS_TO_SEC(timer->max_ns); + + strbuf_addf(&buf_payload, ("%s %s/%s" + " intervals:%"PRIu64 + " total:%8.6f min:%8.6f max:%8.6f"), + event_name, meta->category, meta->name, + timer->interval_count, + t_total, t_min, t_max); + + normal_io_write_fl(__FILE__, __LINE__, &buf_payload); + strbuf_release(&buf_payload); +} + +static void fn_counter(const struct tr2_counter_metadata *meta, + const struct tr2_counter *counter, + int is_final_data) +{ + const char *event_name = is_final_data ? "counter" : "th_counter"; + struct strbuf buf_payload = STRBUF_INIT; + + strbuf_addf(&buf_payload, "%s %s/%s value:%"PRIu64, + event_name, meta->category, meta->name, + counter->value); + + normal_io_write_fl(__FILE__, __LINE__, &buf_payload); + strbuf_release(&buf_payload); +} + struct tr2_tgt tr2_tgt_normal = { .pdst = &tr2dst_normal, @@ -360,4 +397,6 @@ struct tr2_tgt tr2_tgt_normal = { .pfn_data_fl = NULL, .pfn_data_json_fl = NULL, .pfn_printf_va_fl = fn_printf_va_fl, + .pfn_timer = fn_timer, + .pfn_counter = fn_counter, }; diff --git a/trace2/tr2_tgt_perf.c b/trace2/tr2_tgt_perf.c index 8cb792488c..adae803263 100644 --- a/trace2/tr2_tgt_perf.c +++ b/trace2/tr2_tgt_perf.c @@ -10,6 +10,7 @@ #include "trace2/tr2_tbuf.h" #include "trace2/tr2_tgt.h" #include "trace2/tr2_tls.h" +#include "trace2/tr2_tmr.h" static struct tr2_dst tr2dst_perf = { .sysenv_var = TR2_SYSENV_PERF, @@ -108,7 +109,7 @@ static void perf_fmt_prepare(const char *event_name, strbuf_addf(buf, "d%d | ", tr2_sid_depth()); strbuf_addf(buf, "%-*s | %-*s | ", TR2_MAX_THREAD_NAME, - ctx->thread_name.buf, TR2FMT_PERF_MAX_EVENT_NAME, + ctx->thread_name, TR2FMT_PERF_MAX_EVENT_NAME, event_name); len = buf->len + TR2FMT_PERF_REPO_WIDTH; @@ -555,6 +556,44 @@ static void fn_printf_va_fl(const char *file, int line, strbuf_release(&buf_payload); } +static void fn_timer(const struct tr2_timer_metadata *meta, + const struct tr2_timer *timer, + int is_final_data) +{ + const char *event_name = is_final_data ? "timer" : "th_timer"; + struct strbuf buf_payload = STRBUF_INIT; + double t_total = NS_TO_SEC(timer->total_ns); + double t_min = NS_TO_SEC(timer->min_ns); + double t_max = NS_TO_SEC(timer->max_ns); + + strbuf_addf(&buf_payload, ("name:%s" + " intervals:%"PRIu64 + " total:%8.6f min:%8.6f max:%8.6f"), + meta->name, + timer->interval_count, + t_total, t_min, t_max); + + perf_io_write_fl(__FILE__, __LINE__, event_name, NULL, NULL, NULL, + meta->category, &buf_payload); + strbuf_release(&buf_payload); +} + +static void fn_counter(const struct tr2_counter_metadata *meta, + const struct tr2_counter *counter, + int is_final_data) +{ + const char *event_name = is_final_data ? "counter" : "th_counter"; + struct strbuf buf_payload = STRBUF_INIT; + + strbuf_addf(&buf_payload, "name:%s value:%"PRIu64, + meta->name, + counter->value); + + perf_io_write_fl(__FILE__, __LINE__, event_name, NULL, NULL, NULL, + meta->category, &buf_payload); + strbuf_release(&buf_payload); +} + struct tr2_tgt tr2_tgt_perf = { .pdst = &tr2dst_perf, @@ -586,4 +625,6 @@ struct tr2_tgt tr2_tgt_perf = { .pfn_data_fl = fn_data_fl, .pfn_data_json_fl = fn_data_json_fl, .pfn_printf_va_fl = fn_printf_va_fl, + .pfn_timer = fn_timer, + .pfn_counter = fn_counter, }; diff --git a/trace2/tr2_tls.c b/trace2/tr2_tls.c index 7da94aba52..04900bb4c3 100644 --- a/trace2/tr2_tls.c +++ b/trace2/tr2_tls.c @@ -31,10 +31,11 @@ void tr2tls_start_process_clock(void) tr2tls_us_start_process = getnanotime() / 1000; } -struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name, +struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_base_name, uint64_t us_thread_start) { struct tr2tls_thread_ctx *ctx = xcalloc(1, sizeof(*ctx)); + struct strbuf buf = STRBUF_INIT; /* * Implicitly "tr2tls_push_self()" to capture the thread's start @@ -47,12 +48,13 @@ struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name, ctx->thread_id = tr2tls_locked_increment(&tr2_next_thread_id); - strbuf_init(&ctx->thread_name, 0); + strbuf_init(&buf, 0); if (ctx->thread_id) - strbuf_addf(&ctx->thread_name, "th%02d:", ctx->thread_id); - strbuf_addstr(&ctx->thread_name, thread_name); - if (ctx->thread_name.len > TR2_MAX_THREAD_NAME) - strbuf_setlen(&ctx->thread_name, TR2_MAX_THREAD_NAME); + strbuf_addf(&buf, "th%02d:", ctx->thread_id); + strbuf_addstr(&buf, thread_base_name); + if (buf.len > TR2_MAX_THREAD_NAME) + strbuf_setlen(&buf, TR2_MAX_THREAD_NAME); + ctx->thread_name = strbuf_detach(&buf, NULL); pthread_setspecific(tr2tls_key, ctx); @@ -69,9 +71,9 @@ struct tr2tls_thread_ctx *tr2tls_get_self(void) ctx = pthread_getspecific(tr2tls_key); /* - * If the thread-proc did not call trace2_thread_start(), we won't - * have any TLS data associated with the current thread. Fix it - * here and silently continue. + * If the current thread's thread-proc did not call + * trace2_thread_start(), then the thread will not have any + * thread-local storage. Create it now and silently continue. */ if (!ctx) ctx = tr2tls_create_self("unknown", getnanotime() / 1000); @@ -95,7 +97,7 @@ void tr2tls_unset_self(void) pthread_setspecific(tr2tls_key, NULL); - strbuf_release(&ctx->thread_name); + free((char *)ctx->thread_name); free(ctx->array_us_start); free(ctx); } @@ -113,7 +115,7 @@ void tr2tls_pop_self(void) struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); if (!ctx->nr_open_regions) - BUG("no open regions in thread '%s'", ctx->thread_name.buf); + BUG("no open regions in thread '%s'", ctx->thread_name); ctx->nr_open_regions--; } @@ -179,3 +181,13 @@ int tr2tls_locked_increment(int *p) return current_value; } + +void tr2tls_lock(void) +{ + pthread_mutex_lock(&tr2tls_mutex); +} + +void tr2tls_unlock(void) +{ + pthread_mutex_unlock(&tr2tls_mutex); +} diff --git a/trace2/tr2_tls.h b/trace2/tr2_tls.h index b1e327a928..f9049805d4 100644 --- a/trace2/tr2_tls.h +++ b/trace2/tr2_tls.h @@ -2,6 +2,14 @@ #define TR2_TLS_H #include "strbuf.h" +#include "trace2/tr2_ctr.h" +#include "trace2/tr2_tmr.h" + +/* + * Notice: the term "TLS" refers to "thread-local storage" in the + * Trace2 source files. This usage is borrowed from GCC and Windows. + * There is NO relation to "transport layer security". + */ /* * Arbitry limit for thread names for column alignment. @@ -9,33 +17,40 @@ #define TR2_MAX_THREAD_NAME (24) struct tr2tls_thread_ctx { - struct strbuf thread_name; + const char *thread_name; uint64_t *array_us_start; - int alloc; - int nr_open_regions; /* plays role of "nr" in ALLOC_GROW */ + size_t alloc; + size_t nr_open_regions; /* plays role of "nr" in ALLOC_GROW */ int thread_id; + struct tr2_timer_block timer_block; + struct tr2_counter_block counter_block; + unsigned int used_any_timer:1; + unsigned int used_any_per_thread_timer:1; + unsigned int used_any_counter:1; + unsigned int used_any_per_thread_counter:1; }; /* - * Create TLS data for the current thread. This gives us a place to - * put per-thread data, such as thread start time, function nesting - * and a per-thread label for our messages. - * - * We assume the first thread is "main". Other threads are given - * non-zero thread-ids to help distinguish messages from concurrent - * threads. + * Create thread-local storage for the current thread. * - * Truncate the thread name if necessary to help with column alignment - * in printf-style messages. + * The first thread in the process will have: + * { .thread_id=0, .thread_name="main" } + * Subsequent threads are given a non-zero thread_id and a thread_name + * constructed from the id and a thread base name (which is usually just + * the name of the thread-proc function). For example: + * { .thread_id=10, .thread_name="th10:fsm-listen" } + * This helps to identify and distinguish messages from concurrent threads. + * The ctx.thread_name field is truncated if necessary to help with column + * alignment in printf-style messages. * * In this and all following functions the term "self" refers to the * current thread. */ -struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_name, +struct tr2tls_thread_ctx *tr2tls_create_self(const char *thread_base_name, uint64_t us_thread_start); /* - * Get our TLS data. + * Get the thread-local storage pointer of the current thread. */ struct tr2tls_thread_ctx *tr2tls_get_self(void); @@ -45,7 +60,7 @@ struct tr2tls_thread_ctx *tr2tls_get_self(void); int tr2tls_is_main_thread(void); /* - * Free our TLS data. + * Free the current thread's thread-local storage. */ void tr2tls_unset_self(void); @@ -81,12 +96,12 @@ uint64_t tr2tls_region_elasped_self(uint64_t us); uint64_t tr2tls_absolute_elapsed(uint64_t us); /* - * Initialize the tr2 TLS system. + * Initialize thread-local storage for Trace2. */ void tr2tls_init(void); /* - * Free all tr2 TLS resources. + * Free all Trace2 thread-local storage resources. */ void tr2tls_release(void); @@ -100,4 +115,10 @@ int tr2tls_locked_increment(int *p); */ void tr2tls_start_process_clock(void); +/* + * Explicitly lock/unlock our mutex. + */ +void tr2tls_lock(void); +void tr2tls_unlock(void); + #endif /* TR2_TLS_H */ diff --git a/trace2/tr2_tmr.c b/trace2/tr2_tmr.c new file mode 100644 index 0000000000..786762dfd2 --- /dev/null +++ b/trace2/tr2_tmr.c @@ -0,0 +1,182 @@ +#include "cache.h" +#include "thread-utils.h" +#include "trace2/tr2_tgt.h" +#include "trace2/tr2_tls.h" +#include "trace2/tr2_tmr.h" + +#define MY_MAX(a, b) ((a) > (b) ? (a) : (b)) +#define MY_MIN(a, b) ((a) < (b) ? (a) : (b)) + +/* + * A global timer block to aggregate values from the partial sums from + * each thread. + */ +static struct tr2_timer_block final_timer_block; /* access under tr2tls_mutex */ + +/* + * Define metadata for each stopwatch timer. + * + * This array must match "enum trace2_timer_id" and the values + * in "struct tr2_timer_block.timer[*]". + */ +static struct tr2_timer_metadata tr2_timer_metadata[TRACE2_NUMBER_OF_TIMERS] = { + [TRACE2_TIMER_ID_TEST1] = { + .category = "test", + .name = "test1", + .want_per_thread_events = 0, + }, + [TRACE2_TIMER_ID_TEST2] = { + .category = "test", + .name = "test2", + .want_per_thread_events = 1, + }, + + /* Add additional metadata before here. */ +}; + +void tr2_start_timer(enum trace2_timer_id tid) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + struct tr2_timer *t = &ctx->timer_block.timer[tid]; + + t->recursion_count++; + if (t->recursion_count > 1) + return; /* ignore recursive starts */ + + t->start_ns = getnanotime(); +} + +void tr2_stop_timer(enum trace2_timer_id tid) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + struct tr2_timer *t = &ctx->timer_block.timer[tid]; + uint64_t ns_now; + uint64_t ns_interval; + + assert(t->recursion_count > 0); + + t->recursion_count--; + if (t->recursion_count) + return; /* still in recursive call(s) */ + + ns_now = getnanotime(); + ns_interval = ns_now - t->start_ns; + + t->total_ns += ns_interval; + + /* + * min_ns was initialized to zero (in the xcalloc()) rather + * than UINT_MAX when the block of timers was allocated, + * so we should always set both the min_ns and max_ns values + * the first time that the timer is used. + */ + if (!t->interval_count) { + t->min_ns = ns_interval; + t->max_ns = ns_interval; + } else { + t->min_ns = MY_MIN(ns_interval, t->min_ns); + t->max_ns = MY_MAX(ns_interval, t->max_ns); + } + + t->interval_count++; + + ctx->used_any_timer = 1; + if (tr2_timer_metadata[tid].want_per_thread_events) + ctx->used_any_per_thread_timer = 1; +} + +void tr2_update_final_timers(void) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + enum trace2_timer_id tid; + + if (!ctx->used_any_timer) + return; + + /* + * Accessing `final_timer_block` requires holding `tr2tls_mutex`. + * We assume that our caller is holding the lock. + */ + + for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) { + struct tr2_timer *t_final = &final_timer_block.timer[tid]; + struct tr2_timer *t = &ctx->timer_block.timer[tid]; + + if (t->recursion_count) { + /* + * The current thread is exiting with + * timer[tid] still running. + * + * Technically, this is a bug, but I'm going + * to ignore it. + * + * I don't think it is worth calling die() + * for. I don't think it is worth killing the + * process for this bookkeeping error. We + * might want to call warning(), but I'm going + * to wait on that. + * + * The downside here is that total_ns won't + * include the current open interval (now - + * start_ns). I can live with that. + */ + } + + if (!t->interval_count) + continue; /* this timer was not used by this thread */ + + t_final->total_ns += t->total_ns; + + /* + * final_timer_block.timer[tid].min_ns was initialized to + * was initialized to zero rather than UINT_MAX, so we should + * always set both the min_ns and max_ns values the first time + * that we add a partial sum into it. + */ + if (!t_final->interval_count) { + t_final->min_ns = t->min_ns; + t_final->max_ns = t->max_ns; + } else { + t_final->min_ns = MY_MIN(t_final->min_ns, t->min_ns); + t_final->max_ns = MY_MAX(t_final->max_ns, t->max_ns); + } + + t_final->interval_count += t->interval_count; + } +} + +void tr2_emit_per_thread_timers(tr2_tgt_evt_timer_t *fn_apply) +{ + struct tr2tls_thread_ctx *ctx = tr2tls_get_self(); + enum trace2_timer_id tid; + + if (!ctx->used_any_per_thread_timer) + return; + + /* + * For each timer, if the timer wants per-thread events and + * this thread used it, emit it. + */ + for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) + if (tr2_timer_metadata[tid].want_per_thread_events && + ctx->timer_block.timer[tid].interval_count) + fn_apply(&tr2_timer_metadata[tid], + &ctx->timer_block.timer[tid], + 0); +} + +void tr2_emit_final_timers(tr2_tgt_evt_timer_t *fn_apply) +{ + enum trace2_timer_id tid; + + /* + * Accessing `final_timer_block` requires holding `tr2tls_mutex`. + * We assume that our caller is holding the lock. + */ + + for (tid = 0; tid < TRACE2_NUMBER_OF_TIMERS; tid++) + if (final_timer_block.timer[tid].interval_count) + fn_apply(&tr2_timer_metadata[tid], + &final_timer_block.timer[tid], + 1); +} diff --git a/trace2/tr2_tmr.h b/trace2/tr2_tmr.h new file mode 100644 index 0000000000..d575357613 --- /dev/null +++ b/trace2/tr2_tmr.h @@ -0,0 +1,140 @@ +#ifndef TR2_TMR_H +#define TR2_TMR_H + +#include "trace2.h" +#include "trace2/tr2_tgt.h" + +/* + * Define a mechanism to allow "stopwatch" timers. + * + * Timers can be used to measure "interesting" activity that does not + * fit the "region" model, such as code called from many different + * regions (like zlib) and/or where data for individual calls are not + * interesting or are too numerous to be efficiently logged. + * + * Timer values are accumulated during program execution and emitted + * to the Trace2 logs at program exit. + * + * To make this model efficient, we define a compile-time fixed set of + * timers and timer ids using a "timer block" array in thread-local + * storage. This gives us constant time access to each timer within + * each thread, since we want start/stop operations to be as fast as + * possible. This lets us avoid the complexities of dynamically + * allocating a timer on the first use by a thread and/or possibly + * sharing that timer definition with other concurrent threads. + * However, this does require that we define time the set of timers at + * compile time. + * + * Each thread uses the timer block in its thread-local storage to + * compute partial sums for each timer (without locking). When a + * thread exits, those partial sums are (under lock) added to the + * global final sum. + * + * Using this "timer block" model costs ~48 bytes per timer per thread + * (we have about six uint64 fields per timer). This does increase + * the size of the thread-local storage block, but it is allocated (at + * thread create time) and not on the thread stack, so I'm not worried + * about the size. + * + * Partial sums for each timer are optionally emitted when a thread + * exits. + * + * Final sums for each timer are emitted between the "exit" and + * "atexit" events. + * + * A parallel "timer metadata" table contains the "category" and "name" + * fields for each timer. This eliminates the need to include those + * args in the various timer APIs. + */ + +/* + * The definition of an individual timer and used by an individual + * thread. + */ +struct tr2_timer { + /* + * Total elapsed time for this timer in this thread in nanoseconds. + */ + uint64_t total_ns; + + /* + * The maximum and minimum interval values observed for this + * timer in this thread. + */ + uint64_t min_ns; + uint64_t max_ns; + + /* + * The value of the clock when this timer was started in this + * thread. (Undefined when the timer is not active in this + * thread.) + */ + uint64_t start_ns; + + /* + * Number of times that this timer has been started and stopped + * in this thread. (Recursive starts are ignored.) + */ + uint64_t interval_count; + + /* + * Number of nested starts on the stack in this thread. (We + * ignore recursive starts and use this to track the recursive + * calls.) + */ + unsigned int recursion_count; +}; + +/* + * Metadata for a timer. + */ +struct tr2_timer_metadata { + const char *category; + const char *name; + + /* + * True if we should emit per-thread events for this timer + * when individual threads exit. + */ + unsigned int want_per_thread_events:1; +}; + +/* + * A compile-time fixed-size block of timers to insert into + * thread-local storage. This wrapper is used to avoid quirks + * of C and the usual need to pass an array size argument. + */ +struct tr2_timer_block { + struct tr2_timer timer[TRACE2_NUMBER_OF_TIMERS]; +}; + +/* + * Private routines used by trace2.c to actually start/stop an + * individual timer in the current thread. + */ +void tr2_start_timer(enum trace2_timer_id tid); +void tr2_stop_timer(enum trace2_timer_id tid); + +/* + * Add the current thread's timer data to the global totals. + * This is called during thread-exit. + * + * Caller must be holding the tr2tls_mutex. + */ +void tr2_update_final_timers(void); + +/* + * Emit per-thread timer data for the current thread. + * This is called during thread-exit. + */ +void tr2_emit_per_thread_timers(tr2_tgt_evt_timer_t *fn_apply); + +/* + * Emit global total timer values. + * This is called during atexit handling. + * + * Caller must be holding the tr2tls_mutex. + */ +void tr2_emit_final_timers(tr2_tgt_evt_timer_t *fn_apply); + +#endif /* TR2_TMR_H */ diff --git a/transport.c b/transport.c index 70e9c188a3..e7b97194c1 100644 --- a/transport.c +++ b/transport.c @@ -178,7 +178,7 @@ static int fetch_refs_from_bundle(struct transport *transport, if (!data->get_refs_from_bundle_called) get_refs_from_bundle_inner(transport); ret = unbundle(the_repository, &data->header, data->fd, - &extra_index_pack_args); + &extra_index_pack_args, 0); transport->hash_algo = data->header.hash_algo; return ret; } |