fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE

copy_fd_bitmaps(new, old, count) is expected to copy the first
count/BITS_PER_LONG bits from old->full_fds_bits[] and fill
the rest with zeroes.  What it does is copying enough words
(BITS_TO_LONGS(count/BITS_PER_LONG)), then memsets the rest.
That works fine, *if* all bits past the cutoff point are
clear.  Otherwise we are risking garbage from the last word
we'd copied.

For most of the callers that is true - expand_fdtable() has
count equal to old->max_fds, so there's no open descriptors
past count, let alone fully occupied words in ->open_fds[],
which is what bits in ->full_fds_bits[] correspond to.

The other caller (dup_fd()) passes sane_fdtable_size(old_fdt, max_fds),
which is the smallest multiple of BITS_PER_LONG that covers all
opened descriptors below max_fds.  In the common case (copying on
fork()) max_fds is ~0U, so all opened descriptors will be below
it and we are fine, by the same reasons why the call in expand_fdtable()
is safe.

Unfortunately, there is a case where max_fds is less than that
and where we might, indeed, end up with junk in ->full_fds_bits[] -
close_range(from, to, CLOSE_RANGE_UNSHARE) with
	* descriptor table being currently shared
	* 'to' being above the current capacity of descriptor table
	* 'from' being just under some chunk of opened descriptors.
In that case we end up with observably wrong behaviour - e.g. spawn
a child with CLONE_FILES, get all descriptors in range 0..127 open,
then close_range(64, ~0U, CLOSE_RANGE_UNSHARE) and watch dup(0) ending
up with descriptor #128, despite #64 being observably not open.

The minimally invasive fix would be to deal with that in dup_fd().
If this proves to add measurable overhead, we can go that way, but
let's try to fix copy_fd_bitmaps() first.

* new helper: bitmap_copy_and_expand(to, from, bits_to_copy, size).
* make copy_fd_bitmaps() take the bitmap size in words, rather than
bits; it's 'count' argument is always a multiple of BITS_PER_LONG,
so we are not losing any information, and that way we can use the
same helper for all three bitmaps - compiler will see that count
is a multiple of BITS_PER_LONG for the large ones, so it'll generate
plain memcpy()+memset().

Reproducer added to tools/testing/selftests/core/close_range_test.c

Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/file.c b/fs/file.c
index a11e59b5d6026a2e2b195815582f3b48e5b4e331..655338effe9c725574cf19e737a9384e7a460356 100644 (file)
--- a/fs/file.c
+++ b/fs/file.c
@@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
 #define BITBIT_NR(nr)  BITS_TO_LONGS(BITS_TO_LONGS(nr))
 #define BITBIT_SIZE(nr)        (BITBIT_NR(nr) * sizeof(long))
 
+#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
 /*
  * Copy 'count' fd bits from the old table to the new table and clear the extra
  * space if any.  This does not copy the file pointers.  Called with the files
  * spinlock held for write.
  */
-static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
-                           unsigned int count)
+static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
+                           unsigned int copy_words)
 {
-       unsigned int cpy, set;
-
-       cpy = count / BITS_PER_BYTE;
-       set = (nfdt->max_fds - count) / BITS_PER_BYTE;
-       memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
-       memset((char *)nfdt->open_fds + cpy, 0, set);
-       memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
-       memset((char *)nfdt->close_on_exec + cpy, 0, set);
-
-       cpy = BITBIT_SIZE(count);
-       set = BITBIT_SIZE(nfdt->max_fds) - cpy;
-       memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
-       memset((char *)nfdt->full_fds_bits + cpy, 0, set);
+       unsigned int nwords = fdt_words(nfdt);
+
+       bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
+                       copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+       bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
+                       copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+       bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
+                       copy_words, nwords);
 }
 
 /*
@@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
        memcpy(nfdt->fd, ofdt->fd, cpy);
        memset((char *)nfdt->fd + cpy, 0, set);
 
-       copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
+       copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
 }
 
 /*
@@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
                open_files = sane_fdtable_size(old_fdt, max_fds);
        }
 
-       copy_fd_bitmaps(new_fdt, old_fdt, open_files);
+       copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
 
        old_fds = old_fdt->fd;
        new_fds = new_fdt->fd;

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 8c4768c44a01b3221b3da74970ba3c445eaa7fbd..d3b66d77df7a3c029e6e2c8b50abcf531eb88dfb 100644 (file)
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
                dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
 }
 
+static inline void bitmap_copy_and_extend(unsigned long *to,
+                                         const unsigned long *from,
+                                         unsigned int count, unsigned int size)
+{
+       unsigned int copy = BITS_TO_LONGS(count);
+
+       memcpy(to, from, copy * sizeof(long));
+       if (count % BITS_PER_LONG)
+               to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
+       memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
+}
+
 /*
  * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
  * machines the order of hi and lo parts of numbers match the bitmap structure.

diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 991c473e385938030340db7ed7a998c8bff62b5d..12b4eb9d04347f71f19a2c5a696632bf330cca12 100644 (file)
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot)
        EXPECT_EQ(close(fd3), 0);
 }
 
+TEST(close_range_bitmap_corruption)
+{
+       pid_t pid;
+       int status;
+       struct __clone_args args = {
+               .flags = CLONE_FILES,
+               .exit_signal = SIGCHLD,
+       };
+
+       /* get the first 128 descriptors open */
+       for (int i = 2; i < 128; i++)
+               EXPECT_GE(dup2(0, i), 0);
+
+       /* get descriptor table shared */
+       pid = sys_clone3(&args, sizeof(args));
+       ASSERT_GE(pid, 0);
+
+       if (pid == 0) {
+               /* unshare and truncate descriptor table down to 64 */
+               if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE))
+                       exit(EXIT_FAILURE);
+
+               ASSERT_EQ(fcntl(64, F_GETFD), -1);
+               /* ... and verify that the range 64..127 is not
+                  stuck "fully used" according to secondary bitmap */
+               EXPECT_EQ(dup(0), 64)
+                       exit(EXIT_FAILURE);
+               exit(EXIT_SUCCESS);
+       }
+
+       EXPECT_EQ(waitpid(pid, &status, 0), pid);
+       EXPECT_EQ(true, WIFEXITED(status));
+       EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
 TEST_HARNESS_MAIN