From: Zhangjin Wu <falcon@tinylab.org>

Current codes using a brute-force traversal of all file descriptors
do not scale on a system where the maximum number of file descriptors
is set to a very large value (e.g.: in a Docker container of Manjaro
distribution it is set to 1073741816). QEMU just looks frozen during
start-up.

The close-on-exec flag (O_CLOEXEC) was introduced since Linux kernel
2.6.23, FreeBSD 8.3, OpenBSD 5.0, Solaris 11. While it's true QEMU
doesn't need to manually close the fds for child process as the proper
O_CLOEXEC flag should have been set properly on files with its own
codes, QEMU uses a huge number of 3rd party libraries and we don't
trust them to reliably be using O_CLOEXEC on everything they open.

Modern Linux and BSDs have the close_range() call we can use to do the
job, and on Linux we have one more way to walk through /proc/self/fd
to complete the task efficiently, which is what qemu_close_range() does.

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

---

(no changes since v2)

Changes in v2:
- Change to use qemu_close_range() to close fds for child process efficiently
- v1 link: https://lore.kernel.org/qemu-devel/20230406112041.798585-1-bmeng@tinylab.org/

 net/tap.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/net/tap.c b/net/tap.c
index 1bf085d422..d482fabdff 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -446,13 +446,13 @@ static void launch_script(const char *setup_script, const char *ifname,
         return;
     }
     if (pid == 0) {
-        int open_max = sysconf(_SC_OPEN_MAX), i;
+        unsigned int last_fd = sysconf(_SC_OPEN_MAX) - 1;
+
+        /* skip stdin, stdout and stderr */
+        qemu_close_range(3, fd - 1);
+        /* skip the currently used fd */
+        qemu_close_range(fd + 1, last_fd);
 
-        for (i = 3; i < open_max; i++) {
-            if (i != fd) {
-                close(i);
-            }
-        }
         parg = args;
         *parg++ = (char *)setup_script;
         *parg++ = (char *)ifname;
@@ -536,16 +536,15 @@ static int net_bridge_run_helper(const char *helper, const char *bridge,
         return -1;
     }
     if (pid == 0) {
-        int open_max = sysconf(_SC_OPEN_MAX), i;
+        unsigned int last_fd = sysconf(_SC_OPEN_MAX) - 1, fd = sv[1];
         char *fd_buf = NULL;
         char *br_buf = NULL;
         char *helper_cmd = NULL;
 
-        for (i = 3; i < open_max; i++) {
-            if (i != sv[1]) {
-                close(i);
-            }
-        }
+        /* skip stdin, stdout and stderr */
+        qemu_close_range(3, fd - 1);
+        /* skip the currently used fd */
+        qemu_close_range(fd + 1, last_fd);
 
         fd_buf = g_strdup_printf("%s%d", "--fd=", sv[1]);
 
-- 
2.34.1

On Sat, 17 Jun 2023 13:36:21 +0800
Bin Meng <bmeng@tinylab.org> wrote:

> From: Zhangjin Wu <falcon@tinylab.org>
> 
> Current codes using a brute-force traversal of all file descriptors
> do not scale on a system where the maximum number of file descriptors
> is set to a very large value (e.g.: in a Docker container of Manjaro
> distribution it is set to 1073741816). QEMU just looks frozen during
> start-up.
> 
> The close-on-exec flag (O_CLOEXEC) was introduced since Linux kernel
> 2.6.23, FreeBSD 8.3, OpenBSD 5.0, Solaris 11. While it's true QEMU
> doesn't need to manually close the fds for child process as the proper
> O_CLOEXEC flag should have been set properly on files with its own
> codes, QEMU uses a huge number of 3rd party libraries and we don't
> trust them to reliably be using O_CLOEXEC on everything they open.
> 
> Modern Linux and BSDs have the close_range() call we can use to do the
> job, and on Linux we have one more way to walk through /proc/self/fd
> to complete the task efficiently, which is what qemu_close_range() does.
> 
> Reported-by: Zhangjin Wu <falcon@tinylab.org>
> Co-developed-by: Bin Meng <bmeng@tinylab.org>
> Signed-off-by: Zhangjin Wu <falcon@tinylab.org>
> Signed-off-by: Bin Meng <bmeng@tinylab.org>
> 
> ---
> 
> (no changes since v2)
> 
> Changes in v2:
> - Change to use qemu_close_range() to close fds for child process efficiently
> - v1 link: https://lore.kernel.org/qemu-devel/20230406112041.798585-1-bmeng@tinylab.org/
> 
>  net/tap.c | 23 +++++++++++------------
>  1 file changed, 11 insertions(+), 12 deletions(-)
> 
> diff --git a/net/tap.c b/net/tap.c
> index 1bf085d422..d482fabdff 100644
> --- a/net/tap.c
> +++ b/net/tap.c
> @@ -446,13 +446,13 @@ static void launch_script(const char *setup_script, const char *ifname,
>          return;
>      }
>      if (pid == 0) {
> -        int open_max = sysconf(_SC_OPEN_MAX), i;
> +        unsigned int last_fd = sysconf(_SC_OPEN_MAX) - 1;
> +
> +        /* skip stdin, stdout and stderr */
> +        qemu_close_range(3, fd - 1);
> +        /* skip the currently used fd */
> +        qemu_close_range(fd + 1, last_fd);
>  
> -        for (i = 3; i < open_max; i++) {
> -            if (i != fd) {
> -                close(i);
> -            }
> -        }
>          parg = args;
>          *parg++ = (char *)setup_script;
>          *parg++ = (char *)ifname;
> @@ -536,16 +536,15 @@ static int net_bridge_run_helper(const char *helper, const char *bridge,
>          return -1;
>      }
>      if (pid == 0) {
> -        int open_max = sysconf(_SC_OPEN_MAX), i;
> +        unsigned int last_fd = sysconf(_SC_OPEN_MAX) - 1, fd = sv[1];

please put fd on its own line

>          char *fd_buf = NULL;
>          char *br_buf = NULL;
>          char *helper_cmd = NULL;
>  
> -        for (i = 3; i < open_max; i++) {
> -            if (i != sv[1]) {
> -                close(i);
> -            }
> -        }
> +        /* skip stdin, stdout and stderr */
> +        qemu_close_range(3, fd - 1);
> +        /* skip the currently used fd */
> +        qemu_close_range(fd + 1, last_fd);
>  
>          fd_buf = g_strdup_printf("%s%d", "--fd=", sv[1]);
>