This introduces a new QEMU API qemu_close_range() that closes all
open file descriptors from first to last (included).

This API will try a more efficient call to close_range(), or walk
through of /proc/self/fd whenever these are possible, otherwise it
falls back to a plain close loop.

Co-developed-by: Zhangjin Wu <falcon@tinylab.org>
Signed-off-by: Bin Meng <bmeng@tinylab.org>

---

Changes in v4:
- add 'first > last' check logic
- reorder the ifdefs logic
- change i to unsigned int type
- use qemu_strtoi() instead of atoi()
- limit last upper value to sysconf(_SC_OPEN_MAX) - 1

Changes in v3:
- fix win32 build failure

Changes in v2:
- new patch: "util/osdep: Introduce qemu_close_range()"

 include/qemu/osdep.h |  1 +
 util/osdep.c         | 60 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index cc61b00ba9..e22434ce10 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -560,6 +560,7 @@ int qemu_open_old(const char *name, int flags, ...);
 int qemu_open(const char *name, int flags, Error **errp);
 int qemu_create(const char *name, int flags, mode_t mode, Error **errp);
 int qemu_close(int fd);
+int qemu_close_range(unsigned int first, unsigned int last);
 int qemu_unlink(const char *name);
 #ifndef _WIN32
 int qemu_dup_flags(int fd, int flags);
diff --git a/util/osdep.c b/util/osdep.c
index e996c4744a..1d8c719b3f 100644
--- a/util/osdep.c
+++ b/util/osdep.c
@@ -411,6 +411,66 @@ int qemu_close(int fd)
     return close(fd);
 }
 
+int qemu_close_range(unsigned int first, unsigned int last)
+{
+    if (first > last) {
+        errno = EINVAL;
+        return -1;
+    }
+
+#ifndef _WIN32
+    if (last >= sysconf(_SC_OPEN_MAX)) {
+        last = sysconf(_SC_OPEN_MAX) - 1;
+    }
+#endif
+
+#ifdef CONFIG_CLOSE_RANGE
+    int r = close_range(first, last, 0);
+    if (!r) {
+        /* Success, no need to try other ways */
+        return 0;
+    }
+#endif
+
+#ifdef __linux__
+    DIR *dir = opendir("/proc/self/fd");
+    if (dir) {
+        /* Avoid closing the directory */
+        int dfd = dirfd(dir);
+
+        for (struct dirent *de = readdir(dir); de; de = readdir(dir)) {
+            int fd, ret;
+
+            ret = qemu_strtoi(de->d_name, NULL, 10, &fd);
+            if (ret) {
+                /* skip "." and ".." */
+                continue;
+            }
+            if (fd < first || fd > last) {
+                /* Exclude the fds outside the target range */
+                continue;
+            }
+            if (fd != dfd) {
+                close(fd);
+            }
+        }
+        closedir(dir);
+
+        return 0;
+    }
+#endif
+
+    /*
+     * If /proc is not mounted or /proc/self/fd is not supported,
+     * try close() from first to last.
+     */
+    for (unsigned int i = first; i <= last; i++) {
+        close(i);
+    }
+
+    return 0;
+}
+
 /*
  * Delete a file from the filesystem, unless the filename is /dev/fdset/...
  *
-- 
2.34.1

Bin Meng <bmeng@tinylab.org> writes:

> This introduces a new QEMU API qemu_close_range() that closes all
> open file descriptors from first to last (included).
>
> This API will try a more efficient call to close_range(), or walk
> through of /proc/self/fd whenever these are possible, otherwise it
> falls back to a plain close loop.
>
> Co-developed-by: Zhangjin Wu <falcon@tinylab.org>
> Signed-off-by: Bin Meng <bmeng@tinylab.org>
>
> ---
>
> Changes in v4:
> - add 'first > last' check logic
> - reorder the ifdefs logic
> - change i to unsigned int type
> - use qemu_strtoi() instead of atoi()
> - limit last upper value to sysconf(_SC_OPEN_MAX) - 1
>
> Changes in v3:
> - fix win32 build failure
>
> Changes in v2:
> - new patch: "util/osdep: Introduce qemu_close_range()"
>
>  include/qemu/osdep.h |  1 +
>  util/osdep.c         | 60 ++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 61 insertions(+)
>
> diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
> index cc61b00ba9..e22434ce10 100644
> --- a/include/qemu/osdep.h
> +++ b/include/qemu/osdep.h
> @@ -560,6 +560,7 @@ int qemu_open_old(const char *name, int flags, ...);
>  int qemu_open(const char *name, int flags, Error **errp);
>  int qemu_create(const char *name, int flags, mode_t mode, Error **errp);
>  int qemu_close(int fd);
> +int qemu_close_range(unsigned int first, unsigned int last);
>  int qemu_unlink(const char *name);
>  #ifndef _WIN32
>  int qemu_dup_flags(int fd, int flags);
> diff --git a/util/osdep.c b/util/osdep.c
> index e996c4744a..1d8c719b3f 100644
> --- a/util/osdep.c
> +++ b/util/osdep.c
> @@ -411,6 +411,66 @@ int qemu_close(int fd)
>      return close(fd);
>  }
>  
> +int qemu_close_range(unsigned int first, unsigned int last)
> +{
> +    if (first > last) {
> +        errno = EINVAL;
> +        return -1;
> +    }
> +
> +#ifndef _WIN32
> +    if (last >= sysconf(_SC_OPEN_MAX)) {
> +        last = sysconf(_SC_OPEN_MAX) - 1;
> +    }
> +#endif
> +
> +#ifdef CONFIG_CLOSE_RANGE
> +    int r = close_range(first, last, 0);

TOCTTOU if sysconf(_SC_OPEN_MAX) can change at run time.

Say the caller passes ~0U to @last, like the example program in
close_range()'s manual page does.

Since this is larger than sysconf(_SC_OPEN_MAX), we clamp it to
sysconf(_SC_OPEN_MAX).  If the actual value increases before we get to
call close_range(), we can fail to close all fds.

Can't happen if we simply drop the clamping.

> +    if (!r) {
> +        /* Success, no need to try other ways */
> +        return 0;
> +    }
> +#endif

What are the failure modes of close_range() where the other ways are
worth trying?  I asked this in review of v3, and you replied it should
only ever fail when first > last, which you catch before getting here in
v4.

Why not simply return r?

> +
> +#ifdef __linux__
> +    DIR *dir = opendir("/proc/self/fd");
> +    if (dir) {
> +        /* Avoid closing the directory */
> +        int dfd = dirfd(dir);
> +
> +        for (struct dirent *de = readdir(dir); de; de = readdir(dir)) {
> +            int fd, ret;
> +
> +            ret = qemu_strtoi(de->d_name, NULL, 10, &fd);
> +            if (ret) {
> +                /* skip "." and ".." */

Anything that isn't a decimal integer, actually.  Should be just "." and
".." in practice.

> +                continue;
> +            }
> +            if (fd < first || fd > last) {

Not clamping @last is just fine here.

> +                /* Exclude the fds outside the target range */

Suggest to put this comment right before the if.

> +                continue;
> +            }
> +            if (fd != dfd) {
> +                close(fd);
> +            }

Do we still need this now we skip "."?

> +        }
> +        closedir(dir);
> +
> +        return 0;
> +    }
> +#endif
> +
> +    /*
> +     * If /proc is not mounted or /proc/self/fd is not supported,
> +     * try close() from first to last.
> +     */
> +    for (unsigned int i = first; i <= last; i++) {

Here, we do need to stop at sysconf(_SC_OPEN_MAX) - 1.  Recommend to
move the clamping before this loop.

Still a TOCTTOU, but acceptable here, because this fallback is
fundamentally racy no matter what.

> +        close(i);
> +    }
> +
> +    return 0;
> +}
> +
>  /*
>   * Delete a file from the filesystem, unless the filename is /dev/fdset/...
>   *