virtiofsd: stay below fs.file-max sysctl value (CVE-2020-10717)

The system-wide fs.file-max sysctl value determines how many files can
be open.  It defaults to a value calculated based on the machine's RAM
size.  Previously virtiofsd would try to set RLIMIT_NOFILE to 1,000,000
and this allowed the FUSE client to exhaust the number of open files
system-wide on Linux hosts with less than 10 GB of RAM!

Take fs.file-max into account when choosing the default RLIMIT_NOFILE
value.

Fixes: CVE-2020-10717
Reported-by: Yuval Avrahami <yavrahami@paloaltonetworks.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20200501140644.220940-3-stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

1 files changed, 25 insertions, 1 deletions

diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c
index dc59f38af0..00a1ef666a 100644
--- a/tools/virtiofsd/helper.c
+++ b/tools/virtiofsd/helper.c
@@ -176,7 +176,8 @@ void fuse_cmdline_help(void)
            "                               default: no_xattr\n"
            "    --rlimit-nofile=<num>      set maximum number of file descriptors\n"
            "                               (0 leaves rlimit unchanged)\n"
-           "                               default: 1,000,000 if the current rlimit is lower\n"
+           "                               default: min(1000000, fs.file-max - 16384)\n"
+           "                                        if the current rlimit is lower\n"
            );
 }
 
@@ -199,9 +200,32 @@ static int fuse_helper_opt_proc(void *data, const char *arg, int key,
 
 static unsigned long get_default_rlimit_nofile(void)
 {
+    g_autofree gchar *file_max_str = NULL;
+    const rlim_t reserved_fds = 16384; /* leave at least this many fds free */
     rlim_t max_fds = 1000000; /* our default RLIMIT_NOFILE target */
+    rlim_t file_max;
     struct rlimit rlim;
 
+    /*
+     * Reduce max_fds below the system-wide maximum, if necessary.  This
+     * ensures there are fds available for other processes so we don't
+     * cause resource exhaustion.
+     */
+    if (!g_file_get_contents("/proc/sys/fs/file-max", &file_max_str,
+                             NULL, NULL)) {
+        fuse_log(FUSE_LOG_ERR, "can't read /proc/sys/fs/file-max\n");
+        exit(1);
+    }
+    file_max = g_ascii_strtoull(file_max_str, NULL, 10);
+    if (file_max < 2 * reserved_fds) {
+        fuse_log(FUSE_LOG_ERR,
+                 "The fs.file-max sysctl is too low (%lu) to allow a "
+                 "reasonable number of open files.\n",
+                 (unsigned long)file_max);
+        exit(1);
+    }
+    max_fds = MIN(file_max - reserved_fds, max_fds);
+
     if (getrlimit(RLIMIT_NOFILE, &rlim) < 0) {
         fuse_log(FUSE_LOG_ERR, "getrlimit(RLIMIT_NOFILE): %m\n");
         exit(1);