[PATCH 20/77] virtiofsd: add --rlimit-nofile=NUM option

[Michael Roth <mdroth@linux.vnet.ibm.com>]

From: Stefan Hajnoczi <stefanha@redhat.com>

Make it possible to specify the RLIMIT_NOFILE on the command-line.
Users running multiple virtiofsd processes should allocate a certain
number to each process so that the system-wide limit can never be
exhausted.

When this option is set to 0 the rlimit is left at its current value.
This is useful when a management tool wants to configure the rlimit
itself.

The default behavior remains unchanged: try to set the limit to
1,000,000 file descriptors if the current rlimit is lower.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20200501140644.220940-2-stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 6dbb716877728ce4eb51619885ef6ef4ada9565f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
 tools/virtiofsd/fuse_lowlevel.h  |  1 +
 tools/virtiofsd/helper.c         | 23 +++++++++++++++++++++++
 tools/virtiofsd/passthrough_ll.c | 22 ++++++++--------------
 3 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/tools/virtiofsd/fuse_lowlevel.h b/tools/virtiofsd/fuse_lowlevel.h
index 8f6d705b5c..562fd5241e 100644
--- a/tools/virtiofsd/fuse_lowlevel.h
+++ b/tools/virtiofsd/fuse_lowlevel.h
@@ -1777,6 +1777,7 @@ struct fuse_cmdline_opts {
     int syslog;
     int log_level;
     unsigned int max_idle_threads;
+    unsigned long rlimit_nofile;
 };
 
 /**
diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c
index 819c2bc13c..dc59f38af0 100644
--- a/tools/virtiofsd/helper.c
+++ b/tools/virtiofsd/helper.c
@@ -23,6 +23,8 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/param.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include <unistd.h>
 
 #define FUSE_HELPER_OPT(t, p)                       \
@@ -53,6 +55,7 @@ static const struct fuse_opt fuse_helper_opts[] = {
     FUSE_HELPER_OPT("subtype=", nodefault_subtype),
     FUSE_OPT_KEY("subtype=", FUSE_OPT_KEY_KEEP),
     FUSE_HELPER_OPT("max_idle_threads=%u", max_idle_threads),
+    FUSE_HELPER_OPT("--rlimit-nofile=%lu", rlimit_nofile),
     FUSE_HELPER_OPT("--syslog", syslog),
     FUSE_HELPER_OPT_VALUE("log_level=debug", log_level, FUSE_LOG_DEBUG),
     FUSE_HELPER_OPT_VALUE("log_level=info", log_level, FUSE_LOG_INFO),
@@ -171,6 +174,9 @@ void fuse_cmdline_help(void)
            "                               default: no_writeback\n"
            "    -o xattr|no_xattr          enable/disable xattr\n"
            "                               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"
            );
 }
 
@@ -191,11 +197,28 @@ static int fuse_helper_opt_proc(void *data, const char *arg, int key,
     }
 }
 
+static unsigned long get_default_rlimit_nofile(void)
+{
+    rlim_t max_fds = 1000000; /* our default RLIMIT_NOFILE target */
+    struct rlimit rlim;
+
+    if (getrlimit(RLIMIT_NOFILE, &rlim) < 0) {
+        fuse_log(FUSE_LOG_ERR, "getrlimit(RLIMIT_NOFILE): %m\n");
+        exit(1);
+    }
+
+    if (rlim.rlim_cur >= max_fds) {
+        return 0; /* we have more fds available than required! */
+    }
+    return max_fds;
+}
+
 int fuse_parse_cmdline(struct fuse_args *args, struct fuse_cmdline_opts *opts)
 {
     memset(opts, 0, sizeof(struct fuse_cmdline_opts));
 
     opts->max_idle_threads = 10;
+    opts->rlimit_nofile = get_default_rlimit_nofile();
     opts->foreground = 1;
 
     if (fuse_opt_parse(args, opts, fuse_helper_opts, fuse_helper_opt_proc) ==
diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
index 4c35c95b25..f7b9c1d20c 100644
--- a/tools/virtiofsd/passthrough_ll.c
+++ b/tools/virtiofsd/passthrough_ll.c
@@ -2707,24 +2707,18 @@ static void setup_sandbox(struct lo_data *lo, struct fuse_session *se,
     setup_seccomp(enable_syslog);
 }
 
-/* Raise the maximum number of open file descriptors */
-static void setup_nofile_rlimit(void)
+/* Set the maximum number of open file descriptors */
+static void setup_nofile_rlimit(unsigned long rlimit_nofile)
 {
-    const rlim_t max_fds = 1000000;
-    struct rlimit rlim;
-
-    if (getrlimit(RLIMIT_NOFILE, &rlim) < 0) {
-        fuse_log(FUSE_LOG_ERR, "getrlimit(RLIMIT_NOFILE): %m\n");
-        exit(1);
-    }
+    struct rlimit rlim = {
+        .rlim_cur = rlimit_nofile,
+        .rlim_max = rlimit_nofile,
+    };
 
-    if (rlim.rlim_cur >= max_fds) {
+    if (rlimit_nofile == 0) {
         return; /* nothing to do */
     }
 
-    rlim.rlim_cur = max_fds;
-    rlim.rlim_max = max_fds;
-
     if (setrlimit(RLIMIT_NOFILE, &rlim) < 0) {
         /* Ignore SELinux denials */
         if (errno == EPERM) {
@@ -2977,7 +2971,7 @@ int main(int argc, char *argv[])
 
     fuse_daemonize(opts.foreground);
 
-    setup_nofile_rlimit();
+    setup_nofile_rlimit(opts.rlimit_nofile);
 
     /* Must be before sandbox since it wants /proc */
     setup_capng();
-- 
2.17.1