attr: fix out-of-bounds write when parsing huge number of attributes

It is possible to trigger an integer overflow when parsing attribute
names when there are more than 2^31 of them for a single pattern. This
can either lead to us dying due to trying to request too many bytes:

     blob=$(perl -e 'print "f" . " a=" x 2147483649' | git hash-object -w --stdin)
     git update-index --add --cacheinfo 100644,$blob,.gitattributes
     git attr-check --all file

    =================================================================
    ==1022==ERROR: AddressSanitizer: requested allocation size 0xfffffff800000032 (0xfffffff800001038 after adjustments for alignment, red zones etc.) exceeds maximum supported size of 0x10000000000 (thread T0)
        #0 0x7fd3efabf411 in __interceptor_calloc /usr/src/debug/gcc/libsanitizer/asan/asan_malloc_linux.cpp:77
        #1 0x5563a0a1e3d3 in xcalloc wrapper.c:150
        #2 0x5563a058d005 in parse_attr_line attr.c:384
        #3 0x5563a058e661 in handle_attr_line attr.c:660
        #4 0x5563a058eddb in read_attr_from_index attr.c:769
        #5 0x5563a058ef12 in read_attr attr.c:797
        #6 0x5563a058f24c in bootstrap_attr_stack attr.c:867
        #7 0x5563a058f4a3 in prepare_attr_stack attr.c:902
        #8 0x5563a05905da in collect_some_attrs attr.c:1097
        #9 0x5563a059093d in git_all_attrs attr.c:1128
        #10 0x5563a02f636e in check_attr builtin/check-attr.c:67
        #11 0x5563a02f6c12 in cmd_check_attr builtin/check-attr.c:183
        #12 0x5563a02aa993 in run_builtin git.c:466
        #13 0x5563a02ab397 in handle_builtin git.c:721
        #14 0x5563a02abb2b in run_argv git.c:788
        #15 0x5563a02ac991 in cmd_main git.c:926
        #16 0x5563a05432bd in main common-main.c:57
        #17 0x7fd3ef82228f  (/usr/lib/libc.so.6+0x2328f)

    ==1022==HINT: if you don't care about these errors you may set allocator_may_return_null=1
    SUMMARY: AddressSanitizer: allocation-size-too-big /usr/src/debug/gcc/libsanitizer/asan/asan_malloc_linux.cpp:77 in __interceptor_calloc
    ==1022==ABORTING

Or, much worse, it can lead to an out-of-bounds write because we
underallocate and then memcpy(3P) into an array:

    perl -e '
        print "A " . "\rh="x2000000000;
        print "\rh="x2000000000;
        print "\rh="x294967294 . "\n"
    ' >.gitattributes
    git add .gitattributes
    git commit -am "evil attributes"

    $ git clone --quiet /path/to/repo
    =================================================================
    ==15062==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x602000002550 at pc 0x5555559884d5 bp 0x7fffffffbc60 sp 0x7fffffffbc58
    WRITE of size 8 at 0x602000002550 thread T0
        #0 0x5555559884d4 in parse_attr_line attr.c:393
        #1 0x5555559884d4 in handle_attr_line attr.c:660
        #2 0x555555988902 in read_attr_from_index attr.c:784
        #3 0x555555988902 in read_attr_from_index attr.c:747
        #4 0x555555988a1d in read_attr attr.c:800
        #5 0x555555989b0c in bootstrap_attr_stack attr.c:882
        #6 0x555555989b0c in prepare_attr_stack attr.c:917
        #7 0x555555989b0c in collect_some_attrs attr.c:1112
        #8 0x55555598b141 in git_check_attr attr.c:1126
        #9 0x555555a13004 in convert_attrs convert.c:1311
        #10 0x555555a95e04 in checkout_entry_ca entry.c:553
        #11 0x555555d58bf6 in checkout_entry entry.h:42
        #12 0x555555d58bf6 in check_updates unpack-trees.c:480
        #13 0x555555d5eb55 in unpack_trees unpack-trees.c:2040
        #14 0x555555785ab7 in checkout builtin/clone.c:724
        #15 0x555555785ab7 in cmd_clone builtin/clone.c:1384
        #16 0x55555572443c in run_builtin git.c:466
        #17 0x55555572443c in handle_builtin git.c:721
        #18 0x555555727872 in run_argv git.c:788
        #19 0x555555727872 in cmd_main git.c:926
        #20 0x555555721fa0 in main common-main.c:57
        #21 0x7ffff73f1d09 in __libc_start_main ../csu/libc-start.c:308
        #22 0x555555723f39 in _start (git+0x1cff39)

    0x602000002552 is located 0 bytes to the right of 2-byte region [0x602000002550,0x602000002552) allocated by thread T0 here:
        #0 0x7ffff768c037 in __interceptor_calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:154
        #1 0x555555d7fff7 in xcalloc wrapper.c:150
        #2 0x55555598815f in parse_attr_line attr.c:384
        #3 0x55555598815f in handle_attr_line attr.c:660
        #4 0x555555988902 in read_attr_from_index attr.c:784
        #5 0x555555988902 in read_attr_from_index attr.c:747
        #6 0x555555988a1d in read_attr attr.c:800
        #7 0x555555989b0c in bootstrap_attr_stack attr.c:882
        #8 0x555555989b0c in prepare_attr_stack attr.c:917
        #9 0x555555989b0c in collect_some_attrs attr.c:1112
        #10 0x55555598b141 in git_check_attr attr.c:1126
        #11 0x555555a13004 in convert_attrs convert.c:1311
        #12 0x555555a95e04 in checkout_entry_ca entry.c:553
        #13 0x555555d58bf6 in checkout_entry entry.h:42
        #14 0x555555d58bf6 in check_updates unpack-trees.c:480
        #15 0x555555d5eb55 in unpack_trees unpack-trees.c:2040
        #16 0x555555785ab7 in checkout builtin/clone.c:724
        #17 0x555555785ab7 in cmd_clone builtin/clone.c:1384
        #18 0x55555572443c in run_builtin git.c:466
        #19 0x55555572443c in handle_builtin git.c:721
        #20 0x555555727872 in run_argv git.c:788
        #21 0x555555727872 in cmd_main git.c:926
        #22 0x555555721fa0 in main common-main.c:57
        #23 0x7ffff73f1d09 in __libc_start_main ../csu/libc-start.c:308

    SUMMARY: AddressSanitizer: heap-buffer-overflow attr.c:393 in parse_attr_line
    Shadow bytes around the buggy address:
      0x0c047fff8450: fa fa 00 02 fa fa 00 07 fa fa fd fd fa fa 00 00
      0x0c047fff8460: fa fa 02 fa fa fa fd fd fa fa 00 06 fa fa 05 fa
      0x0c047fff8470: fa fa fd fd fa fa 00 02 fa fa 06 fa fa fa 05 fa
      0x0c047fff8480: fa fa 07 fa fa fa fd fd fa fa 00 01 fa fa 00 02
      0x0c047fff8490: fa fa 00 03 fa fa 00 fa fa fa 00 01 fa fa 00 03
    =>0x0c047fff84a0: fa fa 00 01 fa fa 00 02 fa fa[02]fa fa fa fa fa
      0x0c047fff84b0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
      0x0c047fff84c0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
      0x0c047fff84d0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
      0x0c047fff84e0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
      0x0c047fff84f0: fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa fa
    Shadow byte legend (one shadow byte represents 8 application bytes):
      Addressable:           00
      Partially addressable: 01 02 03 04 05 06 07
      Heap left redzone:       fa
      Freed heap region:       fd
      Stack left redzone:      f1
      Stack mid redzone:       f2
      Stack right redzone:     f3
      Stack after return:      f5
      Stack use after scope:   f8
      Global redzone:          f9
      Global init order:       f6
      Poisoned by user:        f7
      Container overflow:      fc
      Array cookie:            ac
      Intra object redzone:    bb
      ASan internal:           fe
      Left alloca redzone:     ca
      Right alloca redzone:    cb
      Shadow gap:              cc
    ==15062==ABORTING

Fix this bug by using `size_t` instead to count the number of attributes
so that this value cannot reasonably overflow without running out of
memory before already.

Reported-by: Markus Vervier <markus.vervier@x41-dsec.de>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 8 insertions, 8 deletions

diff --git a/attr.c b/attr.c
index 4a10ba4..525f6da 100644
--- a/attr.c
+++ b/attr.c
@@ -272,7 +272,7 @@ struct match_attr {
 		const struct git_attr *attr;
 	} u;
 	char is_macro;
-	unsigned num_attr;
+	size_t num_attr;
 	struct attr_state state[FLEX_ARRAY];
 };
 
@@ -333,8 +333,7 @@ static const char *parse_attr(const char *src, int lineno, const char *cp,
 static struct match_attr *parse_attr_line(const char *line, const char *src,
 					  int lineno, int macro_ok)
 {
-	size_t namelen;
-	int num_attr, i;
+	size_t namelen, num_attr, i;
 	const char *cp, *name, *states;
 	struct match_attr *res = NULL;
 	int is_macro;
@@ -451,7 +450,8 @@ static void attr_stack_free(struct attr_stack *e)
 	free(e->origin);
 	for (i = 0; i < e->num_matches; i++) {
 		struct match_attr *a = e->attrs[i];
-		int j;
+		size_t j;
+
 		for (j = 0; j < a->num_attr; j++) {
 			const char *setto = a->state[j].setto;
 			if (setto == ATTR__TRUE ||
@@ -1001,12 +1001,12 @@ static int macroexpand_one(struct all_attrs_item *all_attrs, int nr, int rem);
 static int fill_one(const char *what, struct all_attrs_item *all_attrs,
 		    const struct match_attr *a, int rem)
 {
-	int i;
+	size_t i;
 
-	for (i = a->num_attr - 1; rem > 0 && i >= 0; i--) {
-		const struct git_attr *attr = a->state[i].attr;
+	for (i = a->num_attr; rem > 0 && i > 0; i--) {
+		const struct git_attr *attr = a->state[i - 1].attr;
 		const char **n = &(all_attrs[attr->attr_nr].value);
-		const char *v = a->state[i].setto;
+		const char *v = a->state[i - 1].setto;
 
 		if (*n == ATTR__UNKNOWN) {
 			debug_set(what,