pull: optionally rebase submodules (remote submodule changes only)

Teach pull to optionally update submodules when '--recurse-submodules'
is provided.  This will teach pull to run 'submodule update --rebase'
when the '--recurse-submodules' and '--rebase' flags are given under
specific circumstances.

On a rebase workflow:
=====================

1. Both sides change the submodule
 ------------------------------
Let's assume the following history in a submodule:

  H---I---J---K---L local branch
       \
        M---N---O---P remote branch

and the following in the superproject (recorded submodule in parens):

  A(H)---B(I)---F(K)---G(L)  local branch
          \
           C(N)---D(N)---E(P) remote branch

In an ideal world this would rebase the submodule and rewrite
the submodule pointers that the superproject points at such that
the superproject looks like

  A(H)---B(I)              F(K')---G(L')  rebased branch
           \                /
           C(N)---D(N)---E(P) remote branch

and the submodule as:

        J---K---L (old dangeling tip)
       /
  H---I               J'---K'---L' rebased branch
       \             /
        M---N---O---P remote branch

And if a conflict arises in the submodule the superproject rebase
would stop at that commit at which the submodule conflict occurs.

Currently a "pull --rebase" in the superproject produces
a merge conflict as the submodule pointer changes are
conflicting and cannot be resolved.

2. Local submodule changes only
 -----------------------
Assuming histories as above, except that the remote branch
would not contain submodule changes, then a result as

  A(H)---B(I)               F(K)---G(L)  rebased branch
           \                /
           C(I)---D(I)---E(I) remote branch

is desire-able. This is what currently happens in rebase.

If the recursive flag is given, the ideal git would
produce a superproject as:

  A(H)---B(I)              F(K')---G(L')  rebased branch (incl. sub rebase!)
           \                /
           C(I)---D(I)---E(I) remote branch

and the submodule as:

        J---K---L (old dangeling tip)
       /
  H---I               J'---K'---L' locally rebased branch
       \             /
        M---N---O---P advanced branch

This patch doesn't address this issue, however
a test is added that this fails up front.

3. Remote submodule changes only
 ----------------------
Assuming histories as in (1) except that the local superproject branch
would not have touched the submodule the rebase already works out in the
superproject with no conflicts:

  A(H)---B(I)               F(P)---G(P)  rebased branch (no sub changes)
           \                 /
           C(N)---D(N)---E(P) remote branch

The recurse flag as presented in this patch would additionally
update the submodule as:

  H---I              J'---K'---L' rebased branch
       \            /
        M---N---O---P remote branch

As neither J, K, L nor J', K', L' are referred to from the superproject,
no rewriting of the superproject commits is required.

Conclusion for 'pull --rebase --recursive'
 -----------------------------------------
If there are no local superproject changes it is sufficient to call
"submodule update --rebase" as this produces the desired results. In case
of conflicts, the behavior is the same as in 'submodule update --recursive'
which is assumed to be sane.

This patch implements (3) only.

On a merge workflow:
====================

We'll start off with the same underlying DAG as in (1) in the rebase
workflow. So in an ideal world a 'pull --merge --recursive' would
produce this:

  H---I---J---K---L----X
       \              /
        M---N---O---P

with X as the new merge-commit in the submodule and the superproject
as:

  A(H)---B(I)---F(K)---G(L)---Y(X)
          \                  /
           C(N)---D(N)---E(P)

However modifying the submodules on the fly is not supported in git-merge
such that Y(X) is not easy to produce in a single patch. In fact git-merge
doesn't know about submodules at all.

However when at least one side does not contain commits touching the
submodule at all, then we do not need to perform the merge for the
submodule but a fast-forward can be done via checking out either L or P
in the submodule.  This strategy is implemented in 68d03e4a6e (Implement
automatic fast-forward merge for submodules, 2010-07-07) already, so
to align with the rebase behavior we need to also update the worktree
of the submodule.

Signed-off-by: Brandon Williams <bmwill@google.com>
Signed-off-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 63 insertions, 10 deletions

diff --git a/builtin/pull.c b/builtin/pull.c
index 69417e4f36..7048fdf005 100644
--- a/builtin/pull.c
+++ b/builtin/pull.c
@@ -15,6 +15,8 @@
 #include "dir.h"
 #include "refs.h"
 #include "revision.h"
+#include "submodule.h"
+#include "submodule-config.h"
 #include "tempfile.h"
 #include "lockfile.h"
 #include "wt-status.h"
@@ -77,6 +79,7 @@ static const char * const pull_usage[] = {
 /* Shared options */
 static int opt_verbosity;
 static char *opt_progress;
+static int recurse_submodules = RECURSE_SUBMODULES_DEFAULT;
 
 /* Options passed to git-merge or git-rebase */
 static enum rebase_type opt_rebase = -1;
@@ -101,7 +104,6 @@ static char *opt_upload_pack;
 static int opt_force;
 static char *opt_tags;
 static char *opt_prune;
-static char *opt_recurse_submodules;
 static char *max_children;
 static int opt_dry_run;
 static char *opt_keep;
@@ -116,6 +118,10 @@ static struct option pull_options[] = {
 	OPT_PASSTHRU(0, "progress", &opt_progress, NULL,
 		N_("force progress reporting"),
 		PARSE_OPT_NOARG),
+	{ OPTION_CALLBACK, 0, "recurse-submodules",
+		   &recurse_submodules, N_("on-demand"),
+		   N_("control for recursive fetching of submodules"),
+		   PARSE_OPT_OPTARG, option_fetch_parse_recurse_submodules },
 
 	/* Options passed to git-merge or git-rebase */
 	OPT_GROUP(N_("Options related to merging")),
@@ -187,10 +193,6 @@ static struct option pull_options[] = {
 	OPT_PASSTHRU('p', "prune", &opt_prune, NULL,
 		N_("prune remote-tracking branches no longer on remote"),
 		PARSE_OPT_NOARG),
-	OPT_PASSTHRU(0, "recurse-submodules", &opt_recurse_submodules,
-		N_("on-demand"),
-		N_("control recursive fetching of submodules"),
-		PARSE_OPT_OPTARG),
 	OPT_PASSTHRU('j', "jobs", &max_children, N_("n"),
 		N_("number of submodules pulled in parallel"),
 		PARSE_OPT_OPTARG),
@@ -483,8 +485,20 @@ static int run_fetch(const char *repo, const char **refspecs)
 		argv_array_push(&args, opt_tags);
 	if (opt_prune)
 		argv_array_push(&args, opt_prune);
-	if (opt_recurse_submodules)
-		argv_array_push(&args, opt_recurse_submodules);
+	if (recurse_submodules != RECURSE_SUBMODULES_DEFAULT)
+		switch (recurse_submodules) {
+		case RECURSE_SUBMODULES_ON:
+			argv_array_push(&args, "--recurse-submodules=on");
+			break;
+		case RECURSE_SUBMODULES_OFF:
+			argv_array_push(&args, "--recurse-submodules=no");
+			break;
+		case RECURSE_SUBMODULES_ON_DEMAND:
+			argv_array_push(&args, "--recurse-submodules=on-demand");
+			break;
+		default:
+			BUG("submodule recursion option not understood");
+		}
 	if (max_children)
 		argv_array_push(&args, max_children);
 	if (opt_dry_run)
@@ -531,6 +545,30 @@ static int pull_into_void(const struct object_id *merge_head,
 	return 0;
 }
 
+static int rebase_submodules(void)
+{
+	struct child_process cp = CHILD_PROCESS_INIT;
+
+	cp.git_cmd = 1;
+	cp.no_stdin = 1;
+	argv_array_pushl(&cp.args, "submodule", "update",
+				   "--recursive", "--rebase", NULL);
+
+	return run_command(&cp);
+}
+
+static int update_submodules(void)
+{
+	struct child_process cp = CHILD_PROCESS_INIT;
+
+	cp.git_cmd = 1;
+	cp.no_stdin = 1;
+	argv_array_pushl(&cp.args, "submodule", "update",
+				   "--recursive", "--checkout", NULL);
+
+	return run_command(&cp);
+}
+
 /**
  * Runs git-merge, returning its exit status.
  */
@@ -862,6 +900,11 @@ int cmd_pull(int argc, const char **argv, const char *prefix)
 		die(_("Cannot rebase onto multiple branches."));
 
 	if (opt_rebase) {
+		int ret = 0;
+		if ((recurse_submodules == RECURSE_SUBMODULES_ON ||
+		     recurse_submodules == RECURSE_SUBMODULES_ON_DEMAND) &&
+		    submodule_touches_in_range(&rebase_fork_point, &curr_head))
+			die(_("cannot rebase with locally recorded submodule modifications"));
 		if (!autostash) {
 			struct commit_list *list = NULL;
 			struct commit *merge_head, *head;
@@ -872,11 +915,21 @@ int cmd_pull(int argc, const char **argv, const char *prefix)
 			if (is_descendant_of(merge_head, list)) {
 				/* we can fast-forward this without invoking rebase */
 				opt_ff = "--ff-only";
-				return run_merge();
+				ret = run_merge();
 			}
 		}
-		return run_rebase(&curr_head, merge_heads.oid, &rebase_fork_point);
+		ret = run_rebase(&curr_head, merge_heads.oid, &rebase_fork_point);
+
+		if (!ret && (recurse_submodules == RECURSE_SUBMODULES_ON ||
+			     recurse_submodules == RECURSE_SUBMODULES_ON_DEMAND))
+			ret = rebase_submodules();
+
+		return ret;
 	} else {
-		return run_merge();
+		int ret = run_merge();
+		if (!ret && (recurse_submodules == RECURSE_SUBMODULES_ON ||
+			     recurse_submodules == RECURSE_SUBMODULES_ON_DEMAND))
+			ret = update_submodules();
+		return ret;
 	}
 }