diff mbox

[v5] qemu-nbd: Implement socket activation.

Message ID 20170204100317.32425-2-rjones@redhat.com (mailing list archive)
State New, archived
Headers show

Commit Message

Richard W.M. Jones Feb. 4, 2017, 10:03 a.m. UTC
Socket activation (sometimes known as systemd socket activation)
allows an Internet superserver to pass a pre-opened listening socket
to the process, instead of having qemu-nbd open a socket itself.  This
is done via the LISTEN_FDS and LISTEN_PID environment variables, and a
standard file descriptor range.

This change partially implements socket activation for qemu-nbd.  If
the environment variables are set correctly, then socket activation
will happen automatically, otherwise everything works as before.  The
limitation is that LISTEN_FDS must be 1.

Signed-off-by: Richard W.M. Jones.
---
 qemu-nbd.c | 172 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 163 insertions(+), 9 deletions(-)

Comments

Paolo Bonzini Feb. 6, 2017, 4:10 p.m. UTC | #1
On 04/02/2017 11:03, Richard W.M. Jones wrote:
> Socket activation (sometimes known as systemd socket activation)
> allows an Internet superserver to pass a pre-opened listening socket
> to the process, instead of having qemu-nbd open a socket itself.  This
> is done via the LISTEN_FDS and LISTEN_PID environment variables, and a
> standard file descriptor range.
> 
> This change partially implements socket activation for qemu-nbd.  If
> the environment variables are set correctly, then socket activation
> will happen automatically, otherwise everything works as before.  The
> limitation is that LISTEN_FDS must be 1.
> 
> Signed-off-by: Richard W.M. Jones.
> ---
>  qemu-nbd.c | 172 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
>  1 file changed, 163 insertions(+), 9 deletions(-)
> 
> diff --git a/qemu-nbd.c b/qemu-nbd.c
> index c734f62..e4fede6 100644
> --- a/qemu-nbd.c
> +++ b/qemu-nbd.c
> @@ -463,6 +463,135 @@ static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp)
>      return creds;
>  }
>  
> +static void setup_address_and_port(const char **address, const char **port)
> +{
> +    if (*address == NULL) {
> +        *address = "0.0.0.0";
> +    }
> +
> +    if (*port == NULL) {
> +        *port = stringify(NBD_DEFAULT_PORT);
> +    }
> +}
> +
> +#define FIRST_SOCKET_ACTIVATION_FD 3 /* defined by systemd ABI */
> +
> +#ifndef _WIN32
> +/*
> + * Check if socket activation was requested via use of the
> + * LISTEN_FDS and LISTEN_PID environment variables.
> + *
> + * Returns 0 if no socket activation, or the number of FDs.
> + */
> +static unsigned int check_socket_activation(void)
> +{
> +    const char *s;
> +    unsigned long pid;
> +    unsigned long nr_fds;
> +    unsigned int i;
> +    int fd;
> +    int err;
> +
> +    s = getenv("LISTEN_PID");
> +    if (s == NULL) {
> +        return 0;
> +    }
> +    err = qemu_strtoul(s, NULL, 10, &pid);
> +    if (err) {
> +        if (verbose) {
> +            fprintf(stderr, "malformed %s environment variable (ignored)\n",
> +                    "LISTEN_PID");
> +        }
> +        return 0;
> +    }
> +    if (pid != getpid()) {
> +        if (verbose) {
> +            fprintf(stderr, "%s was not for us (ignored)\n",
> +                    "LISTEN_PID");
> +        }
> +        return 0;
> +    }
> +
> +    s = getenv("LISTEN_FDS");
> +    if (s == NULL) {
> +        return 0;
> +    }
> +    err = qemu_strtoul(s, NULL, 10, &nr_fds);
> +    if (err) {
> +        if (verbose) {
> +            fprintf(stderr, "malformed %s environment variable (ignored)\n",
> +                    "LISTEN_FDS");
> +        }
> +        return 0;
> +    }
> +    assert(nr_fds <= UINT_MAX);
> +
> +    /* A limitation of current qemu-nbd is that it can only listen on
> +     * a single socket.  When that limitation is lifted, we can change
> +     * this function to allow LISTEN_FDS > 1, and remove the assertion
> +     * in the main function below.
> +     */
> +    if (nr_fds > 1) {
> +        error_report("qemu-nbd does not support socket activation with %s > 1",
> +                     "LISTEN_FDS");
> +        exit(EXIT_FAILURE);
> +    }
> +
> +    /* So these are not passed to any child processes we might start. */
> +    unsetenv("LISTEN_FDS");
> +    unsetenv("LISTEN_PID");
> +
> +    /* So the file descriptors don't leak into child processes. */
> +    for (i = 0; i < nr_fds; ++i) {
> +        fd = FIRST_SOCKET_ACTIVATION_FD + i;
> +        if (fcntl(fd, F_SETFD, FD_CLOEXEC) == -1) {
> +            /* If we cannot set FD_CLOEXEC then it probably means the file
> +             * descriptor is invalid, so socket activation has gone wrong
> +             * and we should exit.
> +             */
> +            error_report("Socket activation failed: "
> +                         "invalid file descriptor fd = %d: %m",
> +                         fd);
> +            exit(EXIT_FAILURE);
> +        }
> +    }
> +
> +    return (unsigned int) nr_fds;
> +}
> +
> +#else /* !_WIN32 */
> +static unsigned int check_socket_activation(void)
> +{
> +    return 0;
> +}
> +#endif
> +
> +/*
> + * Check socket parameters compatibility when socket activation is used.
> + */
> +static const char *socket_activation_validate_opts(const char *device,
> +                                                   const char *sockpath,
> +                                                   const char *address,
> +                                                   const char *port)
> +{
> +    if (device != NULL) {
> +        return "NBD device can't be set when using socket activation";
> +    }
> +
> +    if (sockpath != NULL) {
> +        return "Unix socket can't be set when using socket activation";
> +    }
> +
> +    if (address != NULL) {
> +        return "The interface can't be set when using socket activation";
> +    }
> +
> +    if (port != NULL) {
> +        return "TCP port number can't be set when using socket activation";
> +    }
> +
> +    return NULL;
> +}
>  
>  int main(int argc, char **argv)
>  {
> @@ -471,7 +600,7 @@ int main(int argc, char **argv)
>      off_t dev_offset = 0;
>      uint16_t nbdflags = 0;
>      bool disconnect = false;
> -    const char *bindto = "0.0.0.0";
> +    const char *bindto = NULL;
>      const char *port = NULL;
>      char *sockpath = NULL;
>      char *device = NULL;
> @@ -533,6 +662,7 @@ int main(int argc, char **argv)
>      char *trace_file = NULL;
>      bool fork_process = false;
>      int old_stderr = -1;
> +    unsigned socket_activation;
>  
>      /* The client thread uses SIGTERM to interrupt the server.  A signal
>       * handler ensures that "qemu-nbd -v -c" exits with a nice status code.
> @@ -751,6 +881,19 @@ int main(int argc, char **argv)
>      trace_init_file(trace_file);
>      qemu_set_log(LOG_TRACE);
>  
> +    socket_activation = check_socket_activation();
> +    if (socket_activation == 0) {
> +        setup_address_and_port(&bindto, &port);
> +    } else {
> +        /* Using socket activation - check user didn't use -p etc. */
> +        const char *err_msg = socket_activation_validate_opts(device, sockpath,
> +                                                              bindto, port);
> +        if (err_msg != NULL) {
> +            error_report("%s", err_msg);
> +            exit(EXIT_FAILURE);
> +        }
> +    }
> +
>      if (tlscredsid) {
>          if (sockpath) {
>              error_report("TLS is only supported with IPv4/IPv6");
> @@ -855,7 +998,25 @@ int main(int argc, char **argv)
>          snprintf(sockpath, 128, SOCKET_PATH, basename(device));
>      }
>  
> -    saddr = nbd_build_socket_address(sockpath, bindto, port);
> +    if (socket_activation == 0) {
> +        server_ioc = qio_channel_socket_new();
> +        saddr = nbd_build_socket_address(sockpath, bindto, port);
> +        if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
> +            object_unref(OBJECT(server_ioc));
> +            error_report_err(local_err);
> +            return 1;
> +        }
> +    } else {
> +        /* See comment in check_socket_activation above. */
> +        assert(socket_activation == 1);
> +        server_ioc = qio_channel_socket_new_fd(FIRST_SOCKET_ACTIVATION_FD,
> +                                               &local_err);
> +        if (server_ioc == NULL) {
> +            error_report("Failed to use socket activation: %s",
> +                         error_get_pretty(local_err));
> +            exit(EXIT_FAILURE);
> +        }
> +    }
>  
>      if (qemu_init_main_loop(&local_err)) {
>          error_report_err(local_err);
> @@ -950,13 +1111,6 @@ int main(int argc, char **argv)
>          exit(EXIT_FAILURE);
>      }
>  
> -    server_ioc = qio_channel_socket_new();
> -    if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
> -        object_unref(OBJECT(server_ioc));
> -        error_report_err(local_err);
> -        return 1;
> -    }
> -
>      if (device) {
>          int ret;
>  
> 

Queued, thanks.

Paolo
Richard W.M. Jones Feb. 6, 2017, 4:29 p.m. UTC | #2
On Mon, Feb 06, 2017 at 05:10:13PM +0100, Paolo Bonzini wrote:
> Queued, thanks.

Could you change this comment s/!_WIN32/_WIN32/, or do you
want me to submit another patch?

> > +#else /* !_WIN32 */
> > +static unsigned int check_socket_activation(void)
> > +{
> > +    return 0;
> > +}
> > +#endif
> > +

Rich.
Paolo Bonzini Feb. 6, 2017, 4:49 p.m. UTC | #3
On 06/02/2017 17:29, Richard W.M. Jones wrote:
> On Mon, Feb 06, 2017 at 05:10:13PM +0100, Paolo Bonzini wrote:
>> Queued, thanks.
> 
> Could you change this comment s/!_WIN32/_WIN32/, or do you
> want me to submit another patch?
> 
>>> +#else /* !_WIN32 */
>>> +static unsigned int check_socket_activation(void)
>>> +{
>>> +    return 0;
>>> +}
>>> +#endif
>>> +
> 
> Rich.
> 

Will do, and use CONFIG_WIN32 while at it.

Paolo
Eric Blake Feb. 6, 2017, 7:04 p.m. UTC | #4
On 02/04/2017 04:03 AM, Richard W.M. Jones wrote:
> Socket activation (sometimes known as systemd socket activation)
> allows an Internet superserver to pass a pre-opened listening socket
> to the process, instead of having qemu-nbd open a socket itself.  This
> is done via the LISTEN_FDS and LISTEN_PID environment variables, and a
> standard file descriptor range.
> 
> This change partially implements socket activation for qemu-nbd.  If
> the environment variables are set correctly, then socket activation
> will happen automatically, otherwise everything works as before.  The
> limitation is that LISTEN_FDS must be 1.
> 
> Signed-off-by: Richard W.M. Jones.
> ---

> +
> +    /* So the file descriptors don't leak into child processes. */
> +    for (i = 0; i < nr_fds; ++i) {
> +        fd = FIRST_SOCKET_ACTIVATION_FD + i;
> +        if (fcntl(fd, F_SETFD, FD_CLOEXEC) == -1) {

This is not the right way to do things (it risks clearing any other FD_
flags currently set on the fd, even though there aren't any such FD_
flags in common use).  You HAVE to do F_GETFD before F_SETFD
(read-modify-write) for correct usage - and the best way to do that is
to use qemu_set_cloexec() from util/oslib-posix.c.

Except that qemu_set_cloexec() doesn't pay attention to errors...

> +            /* If we cannot set FD_CLOEXEC then it probably means the file
> +             * descriptor is invalid, so socket activation has gone wrong
> +             * and we should exit.
> +             */
> +            error_report("Socket activation failed: "
> +                         "invalid file descriptor fd = %d: %m",
> +                         fd);

...while you use it for argument validation.  Hmm.
Paolo Bonzini Feb. 6, 2017, 9:54 p.m. UTC | #5
On 06/02/2017 20:04, Eric Blake wrote:
> This is not the right way to do things (it risks clearing any other FD_
> flags currently set on the fd, even though there aren't any such FD_
> flags in common use).

There aren't any such flags at all really, and because no one uses
F_GETFD, it's unlikely that there will ever be any.  Has any other POSIX
OS ever had one?

Paolo
diff mbox

Patch

diff --git a/qemu-nbd.c b/qemu-nbd.c
index c734f62..e4fede6 100644
--- a/qemu-nbd.c
+++ b/qemu-nbd.c
@@ -463,6 +463,135 @@  static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp)
     return creds;
 }
 
+static void setup_address_and_port(const char **address, const char **port)
+{
+    if (*address == NULL) {
+        *address = "0.0.0.0";
+    }
+
+    if (*port == NULL) {
+        *port = stringify(NBD_DEFAULT_PORT);
+    }
+}
+
+#define FIRST_SOCKET_ACTIVATION_FD 3 /* defined by systemd ABI */
+
+#ifndef _WIN32
+/*
+ * Check if socket activation was requested via use of the
+ * LISTEN_FDS and LISTEN_PID environment variables.
+ *
+ * Returns 0 if no socket activation, or the number of FDs.
+ */
+static unsigned int check_socket_activation(void)
+{
+    const char *s;
+    unsigned long pid;
+    unsigned long nr_fds;
+    unsigned int i;
+    int fd;
+    int err;
+
+    s = getenv("LISTEN_PID");
+    if (s == NULL) {
+        return 0;
+    }
+    err = qemu_strtoul(s, NULL, 10, &pid);
+    if (err) {
+        if (verbose) {
+            fprintf(stderr, "malformed %s environment variable (ignored)\n",
+                    "LISTEN_PID");
+        }
+        return 0;
+    }
+    if (pid != getpid()) {
+        if (verbose) {
+            fprintf(stderr, "%s was not for us (ignored)\n",
+                    "LISTEN_PID");
+        }
+        return 0;
+    }
+
+    s = getenv("LISTEN_FDS");
+    if (s == NULL) {
+        return 0;
+    }
+    err = qemu_strtoul(s, NULL, 10, &nr_fds);
+    if (err) {
+        if (verbose) {
+            fprintf(stderr, "malformed %s environment variable (ignored)\n",
+                    "LISTEN_FDS");
+        }
+        return 0;
+    }
+    assert(nr_fds <= UINT_MAX);
+
+    /* A limitation of current qemu-nbd is that it can only listen on
+     * a single socket.  When that limitation is lifted, we can change
+     * this function to allow LISTEN_FDS > 1, and remove the assertion
+     * in the main function below.
+     */
+    if (nr_fds > 1) {
+        error_report("qemu-nbd does not support socket activation with %s > 1",
+                     "LISTEN_FDS");
+        exit(EXIT_FAILURE);
+    }
+
+    /* So these are not passed to any child processes we might start. */
+    unsetenv("LISTEN_FDS");
+    unsetenv("LISTEN_PID");
+
+    /* So the file descriptors don't leak into child processes. */
+    for (i = 0; i < nr_fds; ++i) {
+        fd = FIRST_SOCKET_ACTIVATION_FD + i;
+        if (fcntl(fd, F_SETFD, FD_CLOEXEC) == -1) {
+            /* If we cannot set FD_CLOEXEC then it probably means the file
+             * descriptor is invalid, so socket activation has gone wrong
+             * and we should exit.
+             */
+            error_report("Socket activation failed: "
+                         "invalid file descriptor fd = %d: %m",
+                         fd);
+            exit(EXIT_FAILURE);
+        }
+    }
+
+    return (unsigned int) nr_fds;
+}
+
+#else /* !_WIN32 */
+static unsigned int check_socket_activation(void)
+{
+    return 0;
+}
+#endif
+
+/*
+ * Check socket parameters compatibility when socket activation is used.
+ */
+static const char *socket_activation_validate_opts(const char *device,
+                                                   const char *sockpath,
+                                                   const char *address,
+                                                   const char *port)
+{
+    if (device != NULL) {
+        return "NBD device can't be set when using socket activation";
+    }
+
+    if (sockpath != NULL) {
+        return "Unix socket can't be set when using socket activation";
+    }
+
+    if (address != NULL) {
+        return "The interface can't be set when using socket activation";
+    }
+
+    if (port != NULL) {
+        return "TCP port number can't be set when using socket activation";
+    }
+
+    return NULL;
+}
 
 int main(int argc, char **argv)
 {
@@ -471,7 +600,7 @@  int main(int argc, char **argv)
     off_t dev_offset = 0;
     uint16_t nbdflags = 0;
     bool disconnect = false;
-    const char *bindto = "0.0.0.0";
+    const char *bindto = NULL;
     const char *port = NULL;
     char *sockpath = NULL;
     char *device = NULL;
@@ -533,6 +662,7 @@  int main(int argc, char **argv)
     char *trace_file = NULL;
     bool fork_process = false;
     int old_stderr = -1;
+    unsigned socket_activation;
 
     /* The client thread uses SIGTERM to interrupt the server.  A signal
      * handler ensures that "qemu-nbd -v -c" exits with a nice status code.
@@ -751,6 +881,19 @@  int main(int argc, char **argv)
     trace_init_file(trace_file);
     qemu_set_log(LOG_TRACE);
 
+    socket_activation = check_socket_activation();
+    if (socket_activation == 0) {
+        setup_address_and_port(&bindto, &port);
+    } else {
+        /* Using socket activation - check user didn't use -p etc. */
+        const char *err_msg = socket_activation_validate_opts(device, sockpath,
+                                                              bindto, port);
+        if (err_msg != NULL) {
+            error_report("%s", err_msg);
+            exit(EXIT_FAILURE);
+        }
+    }
+
     if (tlscredsid) {
         if (sockpath) {
             error_report("TLS is only supported with IPv4/IPv6");
@@ -855,7 +998,25 @@  int main(int argc, char **argv)
         snprintf(sockpath, 128, SOCKET_PATH, basename(device));
     }
 
-    saddr = nbd_build_socket_address(sockpath, bindto, port);
+    if (socket_activation == 0) {
+        server_ioc = qio_channel_socket_new();
+        saddr = nbd_build_socket_address(sockpath, bindto, port);
+        if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
+            object_unref(OBJECT(server_ioc));
+            error_report_err(local_err);
+            return 1;
+        }
+    } else {
+        /* See comment in check_socket_activation above. */
+        assert(socket_activation == 1);
+        server_ioc = qio_channel_socket_new_fd(FIRST_SOCKET_ACTIVATION_FD,
+                                               &local_err);
+        if (server_ioc == NULL) {
+            error_report("Failed to use socket activation: %s",
+                         error_get_pretty(local_err));
+            exit(EXIT_FAILURE);
+        }
+    }
 
     if (qemu_init_main_loop(&local_err)) {
         error_report_err(local_err);
@@ -950,13 +1111,6 @@  int main(int argc, char **argv)
         exit(EXIT_FAILURE);
     }
 
-    server_ioc = qio_channel_socket_new();
-    if (qio_channel_socket_listen_sync(server_ioc, saddr, &local_err) < 0) {
-        object_unref(OBJECT(server_ioc));
-        error_report_err(local_err);
-        return 1;
-    }
-
     if (device) {
         int ret;