From 3efb988098858bf6b974b1e673a190f9d2965d1d Mon Sep 17 00:00:00 2001 From: Jeff King Date: Thu, 24 Sep 2015 19:12:23 -0400 Subject: react to errors in xdi_diff When we call into xdiff to perform a diff, we generally lose the return code completely. Typically by ignoring the return of our xdi_diff wrapper, but sometimes we even propagate that return value up and then ignore it later. This can lead to us silently producing incorrect diffs (e.g., "git log" might produce no output at all, not even a diff header, for a content-level diff). In practice this does not happen very often, because the typical reason for xdiff to report failure is that it malloc() failed (it uses straight malloc, and not our xmalloc wrapper). But it could also happen when xdiff triggers one our callbacks, which returns an error (e.g., outf() in builtin/rerere.c tries to report a write failure in this way). And the next patch also plans to add more failure modes. Let's notice an error return from xdiff and react appropriately. In most of the diff.c code, we can simply die(), which matches the surrounding code (e.g., that is what we do if we fail to load a file for diffing in the first place). This is not that elegant, but we are probably better off dying to let the user know there was a problem, rather than simply generating bogus output. We could also just die() directly in xdi_diff, but the callers typically have a bit more context, and can provide a better message (and if we do later decide to pass errors up, we're one step closer to doing so). There is one interesting case, which is in diff_grep(). Here if we cannot generate the diff, there is nothing to match, and we silently return "no hits". This is actually what the existing code does already, but we make it a little more explicit. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/blame.c | 9 +++++++-- builtin/merge-tree.c | 3 ++- builtin/rerere.c | 10 ++++++---- 3 files changed, 15 insertions(+), 7 deletions(-) (limited to 'builtin') diff --git a/builtin/blame.c b/builtin/blame.c index 2b1f9dd6cd..66b4fbf466 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -972,7 +972,10 @@ static void pass_blame_to_parent(struct scoreboard *sb, fill_origin_blob(&sb->revs->diffopt, target, &file_o); num_get_patch++; - diff_hunks(&file_p, &file_o, 0, blame_chunk_cb, &d); + if (diff_hunks(&file_p, &file_o, 0, blame_chunk_cb, &d)) + die("unable to generate diff (%s -> %s)", + sha1_to_hex(parent->commit->object.sha1), + sha1_to_hex(target->commit->object.sha1)); /* The rest are the same as the parent */ blame_chunk(&d.dstq, &d.srcq, INT_MAX, d.offset, INT_MAX, parent); *d.dstq = NULL; @@ -1118,7 +1121,9 @@ static void find_copy_in_blob(struct scoreboard *sb, * file_p partially may match that image. */ memset(split, 0, sizeof(struct blame_entry [3])); - diff_hunks(file_p, &file_o, 1, handle_split_cb, &d); + if (diff_hunks(file_p, &file_o, 1, handle_split_cb, &d)) + die("unable to generate diff (%s)", + sha1_to_hex(parent->commit->object.sha1)); /* remainder, if any, all match the preimage */ handle_split(sb, ent, d.tlno, d.plno, ent->num_lines, parent, split); } diff --git a/builtin/merge-tree.c b/builtin/merge-tree.c index f9ab48597e..2a4aafec6a 100644 --- a/builtin/merge-tree.c +++ b/builtin/merge-tree.c @@ -118,7 +118,8 @@ static void show_diff(struct merge_list *entry) if (!dst.ptr) size = 0; dst.size = size; - xdi_diff(&src, &dst, &xpp, &xecfg, &ecb); + if (xdi_diff(&src, &dst, &xpp, &xecfg, &ecb)) + die("unable to generate diff"); free(src.ptr); free(dst.ptr); } diff --git a/builtin/rerere.c b/builtin/rerere.c index 98eb8c5404..aab8f3b1f0 100644 --- a/builtin/rerere.c +++ b/builtin/rerere.c @@ -29,9 +29,10 @@ static int diff_two(const char *file1, const char *label1, xdemitconf_t xecfg; xdemitcb_t ecb; mmfile_t minus, plus; + int ret; if (read_mmfile(&minus, file1) || read_mmfile(&plus, file2)) - return 1; + return -1; printf("--- a/%s\n+++ b/%s\n", label1, label2); fflush(stdout); @@ -40,11 +41,11 @@ static int diff_two(const char *file1, const char *label1, memset(&xecfg, 0, sizeof(xecfg)); xecfg.ctxlen = 3; ecb.outf = outf; - xdi_diff(&minus, &plus, &xpp, &xecfg, &ecb); + ret = xdi_diff(&minus, &plus, &xpp, &xecfg, &ecb); free(minus.ptr); free(plus.ptr); - return 0; + return ret; } int cmd_rerere(int argc, const char **argv, const char *prefix) @@ -104,7 +105,8 @@ int cmd_rerere(int argc, const char **argv, const char *prefix) for (i = 0; i < merge_rr.nr; i++) { const char *path = merge_rr.items[i].string; const char *name = (const char *)merge_rr.items[i].util; - diff_two(rerere_path(name, "preimage"), path, path, path); + if (diff_two(rerere_path(name, "preimage"), path, path, path)) + die("unable to generate diff for %s", name); } else usage_with_options(rerere_usage, options); -- cgit v1.3-5-g9baa From 83c4d380171a2ecd24dd2e04072692ec54a7aaa5 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Fri, 25 Sep 2015 17:58:09 -0400 Subject: merge-file: enforce MAX_XDIFF_SIZE on incoming files The previous commit enforces MAX_XDIFF_SIZE at the interfaces to xdiff: xdi_diff (which calls xdl_diff) and ll_xdl_merge (which calls xdl_merge). But we have another direct call to xdl_merge in merge-file.c. If it were written today, this probably would just use the ll_merge machinery. But it predates that code, and uses slightly different options to xdl_merge (e.g., ZEALOUS_ALNUM). We could try to abstract out an xdi_merge to match the existing xdi_diff, but even that is difficult. Rather than simply report error, we try to treat large files as binary, and that distinction would happen outside of xdi_merge. The simplest fix is to just replicate the MAX_XDIFF_SIZE check in merge-file.c. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin/merge-file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'builtin') diff --git a/builtin/merge-file.c b/builtin/merge-file.c index 232b76857c..04ae36a452 100644 --- a/builtin/merge-file.c +++ b/builtin/merge-file.c @@ -75,7 +75,8 @@ int cmd_merge_file(int argc, const char **argv, const char *prefix) names[i] = argv[i]; if (read_mmfile(mmfs + i, fname)) return -1; - if (buffer_is_binary(mmfs[i].ptr, mmfs[i].size)) + if (mmfs[i].size > MAX_XDIFF_SIZE || + buffer_is_binary(mmfs[i].ptr, mmfs[i].size)) return error("Cannot merge binary files: %s", argv[i]); } -- cgit v1.3-5-g9baa