block: Enable qemu_open/close to work with fd sets

When qemu_open is passed a filename of the "/dev/fdset/nnn"
format (where nnn is the fdset ID), an fd with matching access
mode flags will be searched for within the specified monitor
fd set.  If the fd is found, a dup of the fd will be returned
from qemu_open.

Signed-off-by: Corey Bryant <coreyb@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

9 files changed, 251 insertions, 5 deletions

diff --git a/Makefile b/Makefile
index d736ea5311..6a65f8f2fa 100644
--- a/Makefile
+++ b/Makefile
@@ -148,9 +148,6 @@ install-libcacard: libcacard.la
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" install-libcacard,)
 endif
 
-vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o libcacard/vscclient.o
-	$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS),"  LINK  $@")
-
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
@@ -166,6 +163,9 @@ qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
 
 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
 
+vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) $(tools-obj-y) qemu-timer-common.o libcacard/vscclient.o
+	$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS),"  LINK  $@")
+
 fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o oslib-posix.o $(trace-obj-y)
 fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
 
diff --git a/cutils.c b/cutils.c
index ee4614d378..8ef648f4b9 100644
--- a/cutils.c
+++ b/cutils.c
@@ -383,6 +383,11 @@ int qemu_parse_fd(const char *param)
     return fd;
 }
 
+int qemu_parse_fdset(const char *param)
+{
+    return qemu_parse_fd(param);
+}
+
 /* round down to the nearest power of 2*/
 int64_t pow2floor(int64_t value)
 {
diff --git a/monitor.c b/monitor.c
index 8d813d5121..a4a29b9cd7 100644
--- a/monitor.c
+++ b/monitor.c
@@ -154,6 +154,7 @@ typedef struct MonFdset MonFdset;
 struct MonFdset {
     int64_t id;
     QLIST_HEAD(, MonFdsetFd) fds;
+    QLIST_HEAD(, MonFdsetFd) dup_fds;
     QLIST_ENTRY(MonFdset) next;
 };
 
@@ -2398,7 +2399,7 @@ static void monitor_fdset_cleanup(MonFdset *mon_fdset)
         }
     }
 
-    if (QLIST_EMPTY(&mon_fdset->fds)) {
+    if (QLIST_EMPTY(&mon_fdset->fds) && QLIST_EMPTY(&mon_fdset->dup_fds)) {
         QLIST_REMOVE(mon_fdset, next);
         g_free(mon_fdset);
     }
@@ -2555,6 +2556,89 @@ FdsetInfoList *qmp_query_fdsets(Error **errp)
     return fdset_list;
 }
 
+int monitor_fdset_get_fd(int64_t fdset_id, int flags)
+{
+    MonFdset *mon_fdset;
+    MonFdsetFd *mon_fdset_fd;
+    int mon_fd_flags;
+
+#ifndef _WIN32
+    QLIST_FOREACH(mon_fdset, &mon_fdsets, next) {
+        if (mon_fdset->id != fdset_id) {
+            continue;
+        }
+        QLIST_FOREACH(mon_fdset_fd, &mon_fdset->fds, next) {
+            mon_fd_flags = fcntl(mon_fdset_fd->fd, F_GETFL);
+            if (mon_fd_flags == -1) {
+                return -1;
+            }
+
+            if ((flags & O_ACCMODE) == (mon_fd_flags & O_ACCMODE)) {
+                return mon_fdset_fd->fd;
+            }
+        }
+        errno = EACCES;
+        return -1;
+    }
+#endif
+
+    errno = ENOENT;
+    return -1;
+}
+
+int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd)
+{
+    MonFdset *mon_fdset;
+    MonFdsetFd *mon_fdset_fd_dup;
+
+    QLIST_FOREACH(mon_fdset, &mon_fdsets, next) {
+        if (mon_fdset->id != fdset_id) {
+            continue;
+        }
+        QLIST_FOREACH(mon_fdset_fd_dup, &mon_fdset->dup_fds, next) {
+            if (mon_fdset_fd_dup->fd == dup_fd) {
+                return -1;
+            }
+        }
+        mon_fdset_fd_dup = g_malloc0(sizeof(*mon_fdset_fd_dup));
+        mon_fdset_fd_dup->fd = dup_fd;
+        QLIST_INSERT_HEAD(&mon_fdset->dup_fds, mon_fdset_fd_dup, next);
+        return 0;
+    }
+    return -1;
+}
+
+static int monitor_fdset_dup_fd_find_remove(int dup_fd, bool remove)
+{
+    MonFdset *mon_fdset;
+    MonFdsetFd *mon_fdset_fd_dup;
+
+    QLIST_FOREACH(mon_fdset, &mon_fdsets, next) {
+        QLIST_FOREACH(mon_fdset_fd_dup, &mon_fdset->dup_fds, next) {
+            if (mon_fdset_fd_dup->fd == dup_fd) {
+                if (remove) {
+                    QLIST_REMOVE(mon_fdset_fd_dup, next);
+                    if (QLIST_EMPTY(&mon_fdset->dup_fds)) {
+                        monitor_fdset_cleanup(mon_fdset);
+                    }
+                }
+                return mon_fdset->id;
+            }
+        }
+    }
+    return -1;
+}
+
+int monitor_fdset_dup_fd_find(int dup_fd)
+{
+    return monitor_fdset_dup_fd_find_remove(dup_fd, false);
+}
+
+int monitor_fdset_dup_fd_remove(int dup_fd)
+{
+    return monitor_fdset_dup_fd_find_remove(dup_fd, true);
+}
+
 /* mon_cmds and info_cmds would be sorted at runtime */
 static mon_cmd_t mon_cmds[] = {
 #include "hmp-commands.h"
diff --git a/monitor.h b/monitor.h
index 4ef9a046f8..47d556b9d1 100644
--- a/monitor.h
+++ b/monitor.h
@@ -87,4 +87,9 @@ int qmp_qom_set(Monitor *mon, const QDict *qdict, QObject **ret);
 
 int qmp_qom_get(Monitor *mon, const QDict *qdict, QObject **ret);
 
+int monitor_fdset_get_fd(int64_t fdset_id, int flags);
+int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd);
+int monitor_fdset_dup_fd_remove(int dup_fd);
+int monitor_fdset_dup_fd_find(int dup_fd);
+
 #endif /* !MONITOR_H */
diff --git a/osdep.c b/osdep.c
index 7f876aecd0..5b78ceebef 100644
--- a/osdep.c
+++ b/osdep.c
@@ -48,6 +48,7 @@ extern int madvise(caddr_t, size_t, int);
 #include "qemu-common.h"
 #include "trace.h"
 #include "qemu_socket.h"
+#include "monitor.h"
 
 static bool fips_enabled = false;
 
@@ -78,6 +79,66 @@ int qemu_madvise(void *addr, size_t len, int advice)
 #endif
 }
 
+#ifndef _WIN32
+/*
+ * Dups an fd and sets the flags
+ */
+static int qemu_dup_flags(int fd, int flags)
+{
+    int ret;
+    int serrno;
+    int dup_flags;
+    int setfl_flags;
+
+#ifdef F_DUPFD_CLOEXEC
+    ret = fcntl(fd, F_DUPFD_CLOEXEC, 0);
+#else
+    ret = dup(fd);
+    if (ret != -1) {
+        qemu_set_cloexec(ret);
+    }
+#endif
+    if (ret == -1) {
+        goto fail;
+    }
+
+    dup_flags = fcntl(ret, F_GETFL);
+    if (dup_flags == -1) {
+        goto fail;
+    }
+
+    if ((flags & O_SYNC) != (dup_flags & O_SYNC)) {
+        errno = EINVAL;
+        goto fail;
+    }
+
+    /* Set/unset flags that we can with fcntl */
+    setfl_flags = O_APPEND | O_ASYNC | O_DIRECT | O_NOATIME | O_NONBLOCK;
+    dup_flags &= ~setfl_flags;
+    dup_flags |= (flags & setfl_flags);
+    if (fcntl(ret, F_SETFL, dup_flags) == -1) {
+        goto fail;
+    }
+
+    /* Truncate the file in the cases that open() would truncate it */
+    if (flags & O_TRUNC ||
+            ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))) {
+        if (ftruncate(ret, 0) == -1) {
+            goto fail;
+        }
+    }
+
+    return ret;
+
+fail:
+    serrno = errno;
+    if (ret != -1) {
+        close(ret);
+    }
+    errno = serrno;
+    return -1;
+}
+#endif
 
 /*
  * Opens a file with FD_CLOEXEC set
@@ -87,6 +148,41 @@ int qemu_open(const char *name, int flags, ...)
     int ret;
     int mode = 0;
 
+#ifndef _WIN32
+    const char *fdset_id_str;
+
+    /* Attempt dup of fd from fd set */
+    if (strstart(name, "/dev/fdset/", &fdset_id_str)) {
+        int64_t fdset_id;
+        int fd, dupfd;
+
+        fdset_id = qemu_parse_fdset(fdset_id_str);
+        if (fdset_id == -1) {
+            errno = EINVAL;
+            return -1;
+        }
+
+        fd = monitor_fdset_get_fd(fdset_id, flags);
+        if (fd == -1) {
+            return -1;
+        }
+
+        dupfd = qemu_dup_flags(fd, flags);
+        if (dupfd == -1) {
+            return -1;
+        }
+
+        ret = monitor_fdset_dup_fd_add(fdset_id, dupfd);
+        if (ret == -1) {
+            close(dupfd);
+            errno = EINVAL;
+            return -1;
+        }
+
+        return dupfd;
+    }
+#endif
+
     if (flags & O_CREAT) {
         va_list ap;
 
@@ -109,6 +205,21 @@ int qemu_open(const char *name, int flags, ...)
 
 int qemu_close(int fd)
 {
+    int64_t fdset_id;
+
+    /* Close fd that was dup'd from an fdset */
+    fdset_id = monitor_fdset_dup_fd_find(fd);
+    if (fdset_id != -1) {
+        int ret;
+
+        ret = close(fd);
+        if (ret == 0) {
+            monitor_fdset_dup_fd_remove(fd);
+        }
+
+        return ret;
+    }
+
     return close(fd);
 }
 
diff --git a/qemu-common.h b/qemu-common.h
index b388c5cd70..e5c2bcd204 100644
--- a/qemu-common.h
+++ b/qemu-common.h
@@ -167,6 +167,7 @@ int qemu_fls(int i);
 int qemu_fdatasync(int fd);
 int fcntl_setfl(int fd, int flag);
 int qemu_parse_fd(const char *param);
+int qemu_parse_fdset(const char *param);
 
 /*
  * strtosz() suffixes used to specify the default treatment of an
diff --git a/qemu-tool.c b/qemu-tool.c
index 64b5e88bc7..18205babab 100644
--- a/qemu-tool.c
+++ b/qemu-tool.c
@@ -62,6 +62,26 @@ void monitor_protocol_event(MonitorEvent event, QObject *data)
 {
 }
 
+int monitor_fdset_get_fd(int64_t fdset_id, int flags)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_remove(int dup_fd)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_find(int dup_fd)
+{
+    return -1;
+}
+
 int64_t cpu_get_clock(void)
 {
     return qemu_get_clock_ns(rt_clock);
diff --git a/qemu-user.c b/qemu-user.c
index 08ccb0fe8e..13fb9ae77b 100644
--- a/qemu-user.c
+++ b/qemu-user.c
@@ -35,3 +35,23 @@ void monitor_vprintf(Monitor *mon, const char *fmt, va_list ap)
 void monitor_set_error(Monitor *mon, QError *qerror)
 {
 }
+
+int monitor_fdset_get_fd(int64_t fdset_id, int flags)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_remove(int dup_fd)
+{
+    return -1;
+}
+
+int monitor_fdset_dup_fd_find(int dup_fd)
+{
+    return -1;
+}
diff --git a/tests/Makefile b/tests/Makefile
index f3f4159c25..26a67ce6f5 100644
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -81,7 +81,7 @@ TARGETS=$(patsubst %-softmmu,%, $(filter %-softmmu,$(TARGET_DIRS)))
 QTEST_TARGETS=$(foreach TARGET,$(TARGETS), $(if $(check-qtest-$(TARGET)-y), $(TARGET),))
 check-qtest-$(CONFIG_POSIX)=$(foreach TARGET,$(TARGETS), $(check-qtest-$(TARGET)-y))
 
-qtest-obj-y = tests/libqtest.o $(oslib-obj-y)
+qtest-obj-y = tests/libqtest.o $(oslib-obj-y) $(tools-obj-y)
 $(check-qtest-y): $(qtest-obj-y)
 
 .PHONY: check-help