copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
}
+/*
+ * Note how the fdtable bitmap allocations very much have to be a multiple of
+ * BITS_PER_LONG. This is not only because we walk those things in chunks of
+ * 'unsigned long' in some places, but simply because that is how the Linux
+ * kernel bitmaps are defined to work: they are not "bits in an array of bytes",
+ * they are very much "bits in an array of unsigned long".
+ *
+ * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied
+ * by that "1024/sizeof(ptr)" before, we already know there are sufficient
+ * clear low bits. Clang seems to realize that, gcc ends up being confused.
+ *
+ * On a 128-bit machine, the ALIGN() would actually matter. In the meantime,
+ * let's consider it documentation (and maybe a test-case for gcc to improve
+ * its code generation ;)
+ */
static struct fdtable * alloc_fdtable(unsigned int nr)
{
struct fdtable *fdt;
nr /= (1024 / sizeof(struct file *));
nr = roundup_pow_of_two(nr + 1);
nr *= (1024 / sizeof(struct file *));
+ nr = ALIGN(nr, BITS_PER_LONG);
/*
* Note that this can drive nr *below* what we had passed if sysctl_nr_open
* had been set lower between the check in expand_files() and here. Deal
return i;
}
+/*
+ * Note that a sane fdtable size always has to be a multiple of
+ * BITS_PER_LONG, since we have bitmaps that are sized by this.
+ *
+ * 'max_fds' will normally already be properly aligned, but it
+ * turns out that in the close_range() -> __close_range() ->
+ * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end
+ * up having a 'max_fds' value that isn't already aligned.
+ *
+ * Rather than make close_range() have to worry about this,
+ * just make that BITS_PER_LONG alignment be part of a sane
+ * fdtable size. Becuase that's really what it is.
+ */
static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
{
unsigned int count;
count = count_open_files(fdt);
if (max_fds < NR_OPEN_DEFAULT)
max_fds = NR_OPEN_DEFAULT;
- return min(count, max_fds);
+ return ALIGN(min(count, max_fds), BITS_PER_LONG);
}
/*
*res = NULL;
return -ENOENT;
}
+EXPORT_SYMBOL(close_fd_get_file);
/*
* variant of close_fd that gets a ref on the file for later fput.
spin_unlock(&files->file_lock);
}
+static inline struct file *__fget_files_rcu(struct files_struct *files,
+ unsigned int fd, fmode_t mask, unsigned int refs)
+{
+ for (;;) {
+ struct file *file;
+ struct fdtable *fdt = rcu_dereference_raw(files->fdt);
+ struct file __rcu **fdentry;
+
+ if (unlikely(fd >= fdt->max_fds))
+ return NULL;
+
+ fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds);
+ file = rcu_dereference_raw(*fdentry);
+ if (unlikely(!file))
+ return NULL;
+
+ if (unlikely(file->f_mode & mask))
+ return NULL;
+
+ /*
+ * Ok, we have a file pointer. However, because we do
+ * this all locklessly under RCU, we may be racing with
+ * that file being closed.
+ *
+ * Such a race can take two forms:
+ *
+ * (a) the file ref already went down to zero,
+ * and get_file_rcu_many() fails. Just try
+ * again:
+ */
+ if (unlikely(!get_file_rcu_many(file, refs)))
+ continue;
+
+ /*
+ * (b) the file table entry has changed under us.
+ * Note that we don't need to re-check the 'fdt->fd'
+ * pointer having changed, because it always goes
+ * hand-in-hand with 'fdt'.
+ *
+ * If so, we need to put our refs and try again.
+ */
+ if (unlikely(rcu_dereference_raw(files->fdt) != fdt) ||
+ unlikely(rcu_dereference_raw(*fdentry) != file)) {
+ fput_many(file, refs);
+ continue;
+ }
+
+ /*
+ * Ok, we have a ref to the file, and checked that it
+ * still exists.
+ */
+ return file;
+ }
+}
+
static struct file *__fget_files(struct files_struct *files, unsigned int fd,
fmode_t mask, unsigned int refs)
{
struct file *file;
rcu_read_lock();
-loop:
- file = files_lookup_fd_rcu(files, fd);
- if (file) {
- /* File object ref couldn't be taken.
- * dup2() atomicity guarantee is the reason
- * we loop to catch the new file (or NULL pointer)
- */
- if (file->f_mode & mask)
- file = NULL;
- else if (!get_file_rcu_many(file, refs))
- goto loop;
- }
+ file = __fget_files_rcu(files, fd, mask, refs);
rcu_read_unlock();
return file;
return new_fd;
}
+int receive_fd(struct file *file, unsigned int o_flags)
+{
+ return __receive_fd(file, NULL, o_flags);
+}
+EXPORT_SYMBOL_GPL(receive_fd);
+
static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{
int err = -EBADF;