aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2012-07-28 11:03:01 -0400
committerJunio C Hamano <gitster@pobox.com>2012-07-29 15:04:32 -0700
commite54501004abbd20fa8d813c1e5b82c3b50bb9361 (patch)
tree8d15f023e4b6488b6a6fd229dc27bc25de877763
parentd0f1ea6003d97e63110fa7d50bb07f546a909b6e (diff)
downloadgit-e54501004abbd20fa8d813c1e5b82c3b50bb9361.tar.gz
git-e54501004abbd20fa8d813c1e5b82c3b50bb9361.tar.xz
diff: do not use null sha1 as a sentinel value
The diff code represents paths using the diff_filespec struct. This struct has a sha1 to represent the sha1 of the content at that path, as well as a sha1_valid member which indicates whether its sha1 field is actually useful. If sha1_valid is not true, then the filespec represents a working tree file (e.g., for the no-index case, or for when the index is not up-to-date). The diff_filespec is only used internally, though. At the interfaces to the diff subsystem, callers feed the sha1 directly, and we create a diff_filespec from it. It's at that point that we look at the sha1 and decide whether it is valid or not; callers may pass the null sha1 as a sentinel value to indicate that it is not. We should not typically see the null sha1 coming from any other source (e.g., in the index itself, or from a tree). However, a corrupt tree might have a null sha1, which would cause "diff --patch" to accidentally diff the working tree version of a file instead of treating it as a blob. This patch extends the edges of the diff interface to accept a "sha1_valid" flag whenever we accept a sha1, and to use that flag when creating a filespec. In some cases, this means passing the flag through several layers, making the code change larger than would be desirable. One alternative would be to simply die() upon seeing corrupted trees with null sha1s. However, this fix more directly addresses the problem (while bogus sha1s in a tree are probably a bad thing, it is really the sentinel confusion sending us down the wrong code path that is what makes it devastating). And it means that git is more capable of examining and debugging these corrupted trees. For example, you can still "diff --raw" such a tree to find out when the bogus entry was introduced; you just cannot do a "--patch" diff (just as you could not with any other corrupted tree, as we do not have any content to diff). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--builtin.h2
-rw-r--r--builtin/blame.c9
-rw-r--r--builtin/cat-file.c2
-rw-r--r--builtin/diff.c8
-rw-r--r--combine-diff.c4
-rw-r--r--diff-lib.c20
-rw-r--r--diff-no-index.c4
-rw-r--r--diff.c16
-rw-r--r--diff.h5
-rw-r--r--diffcore-rename.c2
-rw-r--r--diffcore.h2
-rw-r--r--revision.c2
-rwxr-xr-xt/t4054-diff-bogus-tree.sh83
-rw-r--r--tree-diff.c8
14 files changed, 135 insertions, 32 deletions
diff --git a/builtin.h b/builtin.h
index 857b9c8aa..47f540f37 100644
--- a/builtin.h
+++ b/builtin.h
@@ -42,7 +42,7 @@ void finish_copy_notes_for_rewrite(struct notes_rewrite_cfg *c);
extern int check_pager_config(const char *cmd);
-extern int textconv_object(const char *path, unsigned mode, const unsigned char *sha1, char **buf, unsigned long *buf_size);
+extern int textconv_object(const char *path, unsigned mode, const unsigned char *sha1, int sha1_valid, char **buf, unsigned long *buf_size);
extern int cmd_add(int argc, const char **argv, const char *prefix);
extern int cmd_annotate(int argc, const char **argv, const char *prefix);
diff --git a/builtin/blame.c b/builtin/blame.c
index 5a67c202f..fac0e93e6 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -96,6 +96,7 @@ struct origin {
int textconv_object(const char *path,
unsigned mode,
const unsigned char *sha1,
+ int sha1_valid,
char **buf,
unsigned long *buf_size)
{
@@ -103,7 +104,7 @@ int textconv_object(const char *path,
struct userdiff_driver *textconv;
df = alloc_filespec(path);
- fill_filespec(df, sha1, mode);
+ fill_filespec(df, sha1, sha1_valid, mode);
textconv = get_textconv(df);
if (!textconv) {
free_filespec(df);
@@ -128,7 +129,7 @@ static void fill_origin_blob(struct diff_options *opt,
num_read_blob++;
if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) &&
- textconv_object(o->path, o->mode, o->blob_sha1, &file->ptr, &file_size))
+ textconv_object(o->path, o->mode, o->blob_sha1, 1, &file->ptr, &file_size))
;
else
file->ptr = read_sha1_file(o->blob_sha1, &type, &file_size);
@@ -2114,7 +2115,7 @@ static struct commit *fake_working_tree_commit(struct diff_options *opt,
switch (st.st_mode & S_IFMT) {
case S_IFREG:
if (DIFF_OPT_TST(opt, ALLOW_TEXTCONV) &&
- textconv_object(read_from, mode, null_sha1, &buf_ptr, &buf_len))
+ textconv_object(read_from, mode, null_sha1, 0, &buf_ptr, &buf_len))
strbuf_attach(&buf, buf_ptr, buf_len, buf_len + 1);
else if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
die_errno("cannot open or read '%s'", read_from);
@@ -2506,7 +2507,7 @@ parse_done:
die("no such path %s in %s", path, final_commit_name);
if (DIFF_OPT_TST(&sb.revs->diffopt, ALLOW_TEXTCONV) &&
- textconv_object(path, o->mode, o->blob_sha1, (char **) &sb.final_buf,
+ textconv_object(path, o->mode, o->blob_sha1, 1, (char **) &sb.final_buf,
&sb.final_buf_size))
;
else
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 07bd98408..72205faea 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -143,7 +143,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
die("git cat-file --textconv %s: <object> must be <sha1:path>",
obj_name);
- if (!textconv_object(obj_context.path, obj_context.mode, sha1, &buf, &size))
+ if (!textconv_object(obj_context.path, obj_context.mode, sha1, 1, &buf, &size))
die("git cat-file --textconv: unable to run textconv on %s",
obj_name);
break;
diff --git a/builtin/diff.c b/builtin/diff.c
index 387afa756..ac2b1cc63 100644
--- a/builtin/diff.c
+++ b/builtin/diff.c
@@ -29,6 +29,8 @@ static void stuff_change(struct diff_options *opt,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
+ int old_sha1_valid,
+ int new_sha1_valid,
const char *old_name,
const char *new_name)
{
@@ -54,8 +56,8 @@ static void stuff_change(struct diff_options *opt,
one = alloc_filespec(old_name);
two = alloc_filespec(new_name);
- fill_filespec(one, old_sha1, old_mode);
- fill_filespec(two, new_sha1, new_mode);
+ fill_filespec(one, old_sha1, old_sha1_valid, old_mode);
+ fill_filespec(two, new_sha1, new_sha1_valid, new_mode);
diff_queue(&diff_queued_diff, one, two);
}
@@ -84,6 +86,7 @@ static int builtin_diff_b_f(struct rev_info *revs,
stuff_change(&revs->diffopt,
blob[0].mode, canon_mode(st.st_mode),
blob[0].sha1, null_sha1,
+ 1, 0,
path, path);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
@@ -108,6 +111,7 @@ static int builtin_diff_blobs(struct rev_info *revs,
stuff_change(&revs->diffopt,
blob[0].mode, blob[1].mode,
blob[0].sha1, blob[1].sha1,
+ 1, 1,
blob[0].name, blob[1].name);
diffcore_std(&revs->diffopt);
diff_flush(&revs->diffopt);
diff --git a/combine-diff.c b/combine-diff.c
index a2e8dcf85..e9abdbd0b 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -111,7 +111,7 @@ static char *grab_blob(const unsigned char *sha1, unsigned int mode,
return xcalloc(1, 1);
} else if (textconv) {
struct diff_filespec *df = alloc_filespec(path);
- fill_filespec(df, sha1, mode);
+ fill_filespec(df, sha1, 1, mode);
*size = fill_textconv(textconv, df, &blob);
free_filespec(df);
} else {
@@ -823,7 +823,7 @@ static void show_patch_diff(struct combine_diff_path *elem, int num_parent,
&result_size, NULL, NULL);
} else if (textconv) {
struct diff_filespec *df = alloc_filespec(elem->path);
- fill_filespec(df, null_sha1, st.st_mode);
+ fill_filespec(df, null_sha1, 0, st.st_mode);
result_size = fill_textconv(textconv, df, &result);
free_filespec(df);
} else if (0 <= (fd = open(elem->path, O_RDONLY))) {
diff --git a/diff-lib.c b/diff-lib.c
index fc0dff31b..f35de0ffa 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -206,7 +206,8 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
if (silent_on_removed)
continue;
diff_addremove(&revs->diffopt, '-', ce->ce_mode,
- ce->sha1, ce->name, 0);
+ ce->sha1, !is_null_sha1(ce->sha1),
+ ce->name, 0);
continue;
}
changed = match_stat_with_submodule(&revs->diffopt, ce, &st,
@@ -220,6 +221,7 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
newmode = ce_mode_from_stat(ce, st.st_mode);
diff_change(&revs->diffopt, oldmode, newmode,
ce->sha1, (changed ? null_sha1 : ce->sha1),
+ !is_null_sha1(ce->sha1), (changed ? 0 : !is_null_sha1(ce->sha1)),
ce->name, 0, dirty_submodule);
}
@@ -236,11 +238,12 @@ int run_diff_files(struct rev_info *revs, unsigned int option)
static void diff_index_show_file(struct rev_info *revs,
const char *prefix,
struct cache_entry *ce,
- const unsigned char *sha1, unsigned int mode,
+ const unsigned char *sha1, int sha1_valid,
+ unsigned int mode,
unsigned dirty_submodule)
{
diff_addremove(&revs->diffopt, prefix[0], mode,
- sha1, ce->name, dirty_submodule);
+ sha1, sha1_valid, ce->name, dirty_submodule);
}
static int get_stat_data(struct cache_entry *ce,
@@ -295,7 +298,7 @@ static void show_new_file(struct rev_info *revs,
&dirty_submodule, &revs->diffopt) < 0)
return;
- diff_index_show_file(revs, "+", new, sha1, mode, dirty_submodule);
+ diff_index_show_file(revs, "+", new, sha1, !is_null_sha1(sha1), mode, dirty_submodule);
}
static int show_modified(struct rev_info *revs,
@@ -312,7 +315,7 @@ static int show_modified(struct rev_info *revs,
&dirty_submodule, &revs->diffopt) < 0) {
if (report_missing)
diff_index_show_file(revs, "-", old,
- old->sha1, old->ce_mode, 0);
+ old->sha1, 1, old->ce_mode, 0);
return -1;
}
@@ -347,7 +350,8 @@ static int show_modified(struct rev_info *revs,
return 0;
diff_change(&revs->diffopt, oldmode, mode,
- old->sha1, sha1, old->name, 0, dirty_submodule);
+ old->sha1, sha1, 1, !is_null_sha1(sha1),
+ old->name, 0, dirty_submodule);
return 0;
}
@@ -380,7 +384,7 @@ static void do_oneway_diff(struct unpack_trees_options *o,
struct diff_filepair *pair;
pair = diff_unmerge(&revs->diffopt, idx->name);
if (tree)
- fill_filespec(pair->one, tree->sha1, tree->ce_mode);
+ fill_filespec(pair->one, tree->sha1, 1, tree->ce_mode);
return;
}
@@ -396,7 +400,7 @@ static void do_oneway_diff(struct unpack_trees_options *o,
* Something removed from the tree?
*/
if (!idx) {
- diff_index_show_file(revs, "-", tree, tree->sha1, tree->ce_mode, 0);
+ diff_index_show_file(revs, "-", tree, tree->sha1, 1, tree->ce_mode, 0);
return;
}
diff --git a/diff-no-index.c b/diff-no-index.c
index 3a3614468..6568eea6f 100644
--- a/diff-no-index.c
+++ b/diff-no-index.c
@@ -141,8 +141,8 @@ static int queue_diff(struct diff_options *o,
name2 = "/dev/null";
d1 = alloc_filespec(name1);
d2 = alloc_filespec(name2);
- fill_filespec(d1, null_sha1, mode1);
- fill_filespec(d2, null_sha1, mode2);
+ fill_filespec(d1, null_sha1, 0, mode1);
+ fill_filespec(d2, null_sha1, 0, mode2);
diff_queue(&diff_queued_diff, d1, d2);
return 0;
diff --git a/diff.c b/diff.c
index 5388ded21..8933dd199 100644
--- a/diff.c
+++ b/diff.c
@@ -2443,12 +2443,12 @@ void free_filespec(struct diff_filespec *spec)
}
void fill_filespec(struct diff_filespec *spec, const unsigned char *sha1,
- unsigned short mode)
+ int sha1_valid, unsigned short mode)
{
if (mode) {
spec->mode = canon_mode(mode);
hashcpy(spec->sha1, sha1);
- spec->sha1_valid = !is_null_sha1(sha1);
+ spec->sha1_valid = sha1_valid;
}
}
@@ -4589,6 +4589,7 @@ static int is_submodule_ignored(const char *path, struct diff_options *options)
void diff_addremove(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
+ int sha1_valid,
const char *concatpath, unsigned dirty_submodule)
{
struct diff_filespec *one, *two;
@@ -4620,9 +4621,9 @@ void diff_addremove(struct diff_options *options,
two = alloc_filespec(concatpath);
if (addremove != '+')
- fill_filespec(one, sha1, mode);
+ fill_filespec(one, sha1, sha1_valid, mode);
if (addremove != '-') {
- fill_filespec(two, sha1, mode);
+ fill_filespec(two, sha1, sha1_valid, mode);
two->dirty_submodule = dirty_submodule;
}
@@ -4635,6 +4636,7 @@ void diff_change(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
+ int old_sha1_valid, int new_sha1_valid,
const char *concatpath,
unsigned old_dirty_submodule, unsigned new_dirty_submodule)
{
@@ -4649,6 +4651,8 @@ void diff_change(struct diff_options *options,
const unsigned char *tmp_c;
tmp = old_mode; old_mode = new_mode; new_mode = tmp;
tmp_c = old_sha1; old_sha1 = new_sha1; new_sha1 = tmp_c;
+ tmp = old_sha1_valid; old_sha1_valid = new_sha1_valid;
+ new_sha1_valid = tmp;
tmp = old_dirty_submodule; old_dirty_submodule = new_dirty_submodule;
new_dirty_submodule = tmp;
}
@@ -4659,8 +4663,8 @@ void diff_change(struct diff_options *options,
one = alloc_filespec(concatpath);
two = alloc_filespec(concatpath);
- fill_filespec(one, old_sha1, old_mode);
- fill_filespec(two, new_sha1, new_mode);
+ fill_filespec(one, old_sha1, old_sha1_valid, old_mode);
+ fill_filespec(two, new_sha1, new_sha1_valid, new_mode);
one->dirty_submodule = old_dirty_submodule;
two->dirty_submodule = new_dirty_submodule;
diff --git a/diff.h b/diff.h
index 7af5f1e2a..b5ba1402a 100644
--- a/diff.h
+++ b/diff.h
@@ -19,12 +19,14 @@ typedef void (*change_fn_t)(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
+ int old_sha1_valid, int new_sha1_valid,
const char *fullpath,
unsigned old_dirty_submodule, unsigned new_dirty_submodule);
typedef void (*add_remove_fn_t)(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
+ int sha1_valid,
const char *fullpath, unsigned dirty_submodule);
typedef void (*diff_format_fn_t)(struct diff_queue_struct *q,
@@ -209,12 +211,15 @@ extern void diff_addremove(struct diff_options *,
int addremove,
unsigned mode,
const unsigned char *sha1,
+ int sha1_valid,
const char *fullpath, unsigned dirty_submodule);
extern void diff_change(struct diff_options *,
unsigned mode1, unsigned mode2,
const unsigned char *sha1,
const unsigned char *sha2,
+ int sha1_valid,
+ int sha2_valid,
const char *fullpath,
unsigned dirty_submodule1, unsigned dirty_submodule2);
diff --git a/diffcore-rename.c b/diffcore-rename.c
index f639601c7..e6f9be64c 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -48,7 +48,7 @@ static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
memmove(rename_dst + first + 1, rename_dst + first,
(rename_dst_nr - first - 1) * sizeof(*rename_dst));
rename_dst[first].two = alloc_filespec(two->path);
- fill_filespec(rename_dst[first].two, two->sha1, two->mode);
+ fill_filespec(rename_dst[first].two, two->sha1, two->sha1_valid, two->mode);
rename_dst[first].pair = NULL;
return &(rename_dst[first]);
}
diff --git a/diffcore.h b/diffcore.h
index 8f32b824c..c964ec114 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -54,7 +54,7 @@ struct diff_filespec {
extern struct diff_filespec *alloc_filespec(const char *);
extern void free_filespec(struct diff_filespec *);
extern void fill_filespec(struct diff_filespec *, const unsigned char *,
- unsigned short);
+ int, unsigned short);
extern int diff_populate_filespec(struct diff_filespec *, int);
extern void diff_free_filespec_data(struct diff_filespec *);
diff --git a/revision.c b/revision.c
index 18be62b31..21ef729cf 100644
--- a/revision.c
+++ b/revision.c
@@ -332,6 +332,7 @@ static int tree_difference = REV_TREE_SAME;
static void file_add_remove(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
+ int sha1_valid,
const char *fullpath, unsigned dirty_submodule)
{
int diff = addremove == '+' ? REV_TREE_NEW : REV_TREE_OLD;
@@ -345,6 +346,7 @@ static void file_change(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
+ int old_sha1_valid, int new_sha1_valid,
const char *fullpath,
unsigned old_dirty_submodule, unsigned new_dirty_submodule)
{
diff --git a/t/t4054-diff-bogus-tree.sh b/t/t4054-diff-bogus-tree.sh
new file mode 100755
index 000000000..0843c8789
--- /dev/null
+++ b/t/t4054-diff-bogus-tree.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+
+test_description='test diff with a bogus tree containing the null sha1'
+. ./test-lib.sh
+
+empty_tree=4b825dc642cb6eb9a060e54bf8d69288fbee4904
+
+test_expect_success 'create bogus tree' '
+ bogus_tree=$(
+ printf "100644 fooQQQQQQQQQQQQQQQQQQQQQ" |
+ q_to_nul |
+ git hash-object -w --stdin -t tree
+ )
+'
+
+test_expect_success 'create tree with matching file' '
+ echo bar >foo &&
+ git add foo &&
+ good_tree=$(git write-tree)
+ blob=$(git rev-parse :foo)
+'
+
+test_expect_success 'raw diff shows null sha1 (addition)' '
+ echo ":000000 100644 $_z40 $_z40 A foo" >expect &&
+ git diff-tree $empty_tree $bogus_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'raw diff shows null sha1 (removal)' '
+ echo ":100644 000000 $_z40 $_z40 D foo" >expect &&
+ git diff-tree $bogus_tree $empty_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'raw diff shows null sha1 (modification)' '
+ echo ":100644 100644 $blob $_z40 M foo" >expect &&
+ git diff-tree $good_tree $bogus_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'raw diff shows null sha1 (other direction)' '
+ echo ":100644 100644 $_z40 $blob M foo" >expect &&
+ git diff-tree $bogus_tree $good_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'raw diff shows null sha1 (reverse)' '
+ echo ":100644 100644 $_z40 $blob M foo" >expect &&
+ git diff-tree -R $good_tree $bogus_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'raw diff shows null sha1 (index)' '
+ echo ":100644 100644 $_z40 $blob M foo" >expect &&
+ git diff-index $bogus_tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'patch fails due to bogus sha1 (addition)' '
+ test_must_fail git diff-tree -p $empty_tree $bogus_tree
+'
+
+test_expect_success 'patch fails due to bogus sha1 (removal)' '
+ test_must_fail git diff-tree -p $bogus_tree $empty_tree
+'
+
+test_expect_success 'patch fails due to bogus sha1 (modification)' '
+ test_must_fail git diff-tree -p $good_tree $bogus_tree
+'
+
+test_expect_success 'patch fails due to bogus sha1 (other direction)' '
+ test_must_fail git diff-tree -p $bogus_tree $good_tree
+'
+
+test_expect_success 'patch fails due to bogus sha1 (reverse)' '
+ test_must_fail git diff-tree -R -p $good_tree $bogus_tree
+'
+
+test_expect_success 'patch fails due to bogus sha1 (index)' '
+ test_must_fail git diff-index -p $bogus_tree
+'
+
+test_done
diff --git a/tree-diff.c b/tree-diff.c
index 28ad6db9f..7e5483366 100644
--- a/tree-diff.c
+++ b/tree-diff.c
@@ -49,12 +49,12 @@ static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2,
if (DIFF_OPT_TST(opt, RECURSIVE) && S_ISDIR(mode1)) {
if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE)) {
opt->change(opt, mode1, mode2,
- sha1, sha2, base->buf, 0, 0);
+ sha1, sha2, 1, 1, base->buf, 0, 0);
}
strbuf_addch(base, '/');
diff_tree_sha1(sha1, sha2, base->buf, opt);
} else {
- opt->change(opt, mode1, mode2, sha1, sha2, base->buf, 0, 0);
+ opt->change(opt, mode1, mode2, sha1, sha2, 1, 1, base->buf, 0, 0);
}
strbuf_setlen(base, old_baselen);
return 0;
@@ -100,7 +100,7 @@ static void show_entry(struct diff_options *opt, const char *prefix,
die("corrupt tree sha %s", sha1_to_hex(sha1));
if (DIFF_OPT_TST(opt, TREE_IN_RECURSIVE))
- opt->add_remove(opt, *prefix, mode, sha1, base->buf, 0);
+ opt->add_remove(opt, *prefix, mode, sha1, 1, base->buf, 0);
strbuf_addch(base, '/');
@@ -108,7 +108,7 @@ static void show_entry(struct diff_options *opt, const char *prefix,
show_tree(opt, prefix, &inner, base);
free(tree);
} else
- opt->add_remove(opt, prefix[0], mode, sha1, base->buf, 0);
+ opt->add_remove(opt, prefix[0], mode, sha1, 1, base->buf, 0);
strbuf_setlen(base, old_baselen);
}