[Qemu-devel] [PATCH] Use qemu_eventfd for POSIX AIO

[Jan Kiszka <jan.kiszka@siemens.com>]

Move qemu_eventfd unmodified to oslib-posix and use it for signaling
POSIX AIO completions. If native eventfd suport is available, this
avoids multiple read accesses to drain multiple pending signals. As
before we use a pipe if eventfd is not supported.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 os-posix.c         |   32 --------------------------------
 oslib-posix.c      |   32 +++++++++++++++++++++++++++++++-
 posix-aio-compat.c |   12 ++++++++----
 3 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/os-posix.c b/os-posix.c
index dbf3b24..a918895 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -45,10 +45,6 @@
 #include <sys/syscall.h>
 #endif
 
-#ifdef CONFIG_EVENTFD
-#include <sys/eventfd.h>
-#endif
-
 static struct passwd *user_pwd;
 static const char *chroot_dir;
 static int daemonize;
@@ -333,34 +329,6 @@ void os_set_line_buffering(void)
     setvbuf(stdout, NULL, _IOLBF, 0);
 }
 
-/*
- * Creates an eventfd that looks like a pipe and has EFD_CLOEXEC set.
- */
-int qemu_eventfd(int fds[2])
-{
-#ifdef CONFIG_EVENTFD
-    int ret;
-
-    ret = eventfd(0, 0);
-    if (ret >= 0) {
-        fds[0] = ret;
-        qemu_set_cloexec(ret);
-        if ((fds[1] = dup(ret)) == -1) {
-            close(ret);
-            return -1;
-        }
-        qemu_set_cloexec(fds[1]);
-        return 0;
-    }
-
-    if (errno != ENOSYS) {
-        return -1;
-    }
-#endif
-
-    return qemu_pipe(fds);
-}
-
 int qemu_create_pidfile(const char *filename)
 {
     char buffer[128];
diff --git a/oslib-posix.c b/oslib-posix.c
index a304fb0..8ef7bd7 100644
--- a/oslib-posix.c
+++ b/oslib-posix.c
@@ -47,7 +47,9 @@ extern int daemon(int, int);
 #include "trace.h"
 #include "qemu_socket.h"
 
-
+#ifdef CONFIG_EVENTFD
+#include <sys/eventfd.h>
+#endif
 
 int qemu_daemon(int nochdir, int noclose)
 {
@@ -139,6 +141,34 @@ int qemu_pipe(int pipefd[2])
     return ret;
 }
 
+/*
+ * Creates an eventfd that looks like a pipe and has EFD_CLOEXEC set.
+ */
+int qemu_eventfd(int fds[2])
+{
+#ifdef CONFIG_EVENTFD
+    int ret;
+
+    ret = eventfd(0, 0);
+    if (ret >= 0) {
+        fds[0] = ret;
+        qemu_set_cloexec(ret);
+        if ((fds[1] = dup(ret)) == -1) {
+            close(ret);
+            return -1;
+        }
+        qemu_set_cloexec(fds[1]);
+        return 0;
+    }
+
+    if (errno != ENOSYS) {
+        return -1;
+    }
+#endif
+
+    return qemu_pipe(fds);
+}
+
 int qemu_utimensat(int dirfd, const char *path, const struct timespec *times,
                    int flags)
 {
diff --git a/posix-aio-compat.c b/posix-aio-compat.c
index d3c1174..2aa5ba3 100644
--- a/posix-aio-compat.c
+++ b/posix-aio-compat.c
@@ -521,7 +521,7 @@ static void posix_aio_read(void *opaque)
     PosixAioState *s = opaque;
     ssize_t len;
 
-    /* read all bytes from signal pipe */
+    /* read all bytes from eventfd or signal pipe */
     for (;;) {
         char bytes[16];
 
@@ -546,10 +546,14 @@ static PosixAioState *posix_aio_state;
 
 static void posix_aio_notify_event(void)
 {
-    char byte = 0;
+    /* Write 8 bytes to be compatible with eventfd.  */
+    static const uint64_t val = 1;
     ssize_t ret;
 
-    ret = write(posix_aio_state->wfd, &byte, sizeof(byte));
+    do {
+        ret = write(posix_aio_state->wfd, &val, sizeof(val));
+    } while (ret < 0 && errno == EINTR);
+
     if (ret < 0 && errno != EAGAIN)
         die("write()");
 }
@@ -665,7 +669,7 @@ int paio_init(void)
     s = g_malloc(sizeof(PosixAioState));
 
     s->first_aio = NULL;
-    if (qemu_pipe(fds) == -1) {
+    if (qemu_eventfd(fds) == -1) {
         fprintf(stderr, "failed to create pipe\n");
         return -1;
     }
-- 
1.7.3.4