X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=main-loop.c;h=c3c9c28fbab786e0c50a5d1882d155680f0d46b9;hb=60aad298cb6de52f2716b2e82e1353ea9de95fd6;hp=e43c7c8e8d4355794540063da0f6be92c73e8bdc;hpb=5a34dbb55994ddb8e3f4cc465abbb85aa2e6dfaf;p=qemu.git

diff --git a/main-loop.c b/main-loop.c
index e43c7c8e8..c3c9c28fb 100644
--- a/main-loop.c
+++ b/main-loop.c
@@ -23,14 +23,15 @@
  */
 
 #include "qemu-common.h"
-#include "qemu-timer.h"
-#include "slirp/slirp.h"
-#include "main-loop.h"
-#include "qemu-aio.h"
+#include "qemu/timer.h"
+#include "qemu/sockets.h"	// struct in_addr needed for libslirp.h
+#include "slirp/libslirp.h"
+#include "qemu/main-loop.h"
+#include "block/aio.h"
 
 #ifndef _WIN32
 
-#include "compatfd.h"
+#include "qemu/compatfd.h"
 
 /* If we have signalfd, we mask out the signals we want to handle and then
  * use signalfd to listen for them.  We rely on whatever the current signal
@@ -109,6 +110,11 @@ static int qemu_signal_init(void)
 
 static AioContext *qemu_aio_context;
 
+AioContext *qemu_get_aio_context(void)
+{
+    return qemu_aio_context;
+}
+
 void qemu_notify_event(void)
 {
     if (!qemu_aio_context) {
@@ -117,20 +123,21 @@ void qemu_notify_event(void)
     aio_notify(qemu_aio_context);
 }
 
+static GArray *gpollfds;
+
 int qemu_init_main_loop(void)
 {
     int ret;
     GSource *src;
 
     init_clocks();
-    init_timer_alarm();
 
-    qemu_mutex_lock_iothread();
     ret = qemu_signal_init();
     if (ret) {
         return ret;
     }
 
+    gpollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
     qemu_aio_context = aio_context_new();
     src = aio_get_g_source(qemu_aio_context);
     g_source_attach(src, NULL);
@@ -138,100 +145,93 @@ int qemu_init_main_loop(void)
     return 0;
 }
 
-static fd_set rfds, wfds, xfds;
-static int nfds;
-static GPollFD poll_fds[1024 * 2]; /* this is probably overkill */
-static int n_poll_fds;
 static int max_priority;
 
 #ifndef _WIN32
-static void glib_select_fill(int *max_fd, fd_set *rfds, fd_set *wfds,
-                             fd_set *xfds, uint32_t *cur_timeout)
+static int glib_pollfds_idx;
+static int glib_n_poll_fds;
+
+static void glib_pollfds_fill(int64_t *cur_timeout)
 {
     GMainContext *context = g_main_context_default();
-    int i;
     int timeout = 0;
+    int64_t timeout_ns;
+    int n;
 
     g_main_context_prepare(context, &max_priority);
 
-    n_poll_fds = g_main_context_query(context, max_priority, &timeout,
-                                      poll_fds, ARRAY_SIZE(poll_fds));
-    g_assert(n_poll_fds <= ARRAY_SIZE(poll_fds));
-
-    for (i = 0; i < n_poll_fds; i++) {
-        GPollFD *p = &poll_fds[i];
-
-        if ((p->events & G_IO_IN)) {
-            FD_SET(p->fd, rfds);
-            *max_fd = MAX(*max_fd, p->fd);
-        }
-        if ((p->events & G_IO_OUT)) {
-            FD_SET(p->fd, wfds);
-            *max_fd = MAX(*max_fd, p->fd);
-        }
-        if ((p->events & G_IO_ERR)) {
-            FD_SET(p->fd, xfds);
-            *max_fd = MAX(*max_fd, p->fd);
-        }
+    glib_pollfds_idx = gpollfds->len;
+    n = glib_n_poll_fds;
+    do {
+        GPollFD *pfds;
+        glib_n_poll_fds = n;
+        g_array_set_size(gpollfds, glib_pollfds_idx + glib_n_poll_fds);
+        pfds = &g_array_index(gpollfds, GPollFD, glib_pollfds_idx);
+        n = g_main_context_query(context, max_priority, &timeout, pfds,
+                                 glib_n_poll_fds);
+    } while (n != glib_n_poll_fds);
+
+    if (timeout < 0) {
+        timeout_ns = -1;
+    } else {
+        timeout_ns = (int64_t)timeout * (int64_t)SCALE_MS;
     }
 
-    if (timeout >= 0 && timeout < *cur_timeout) {
-        *cur_timeout = timeout;
-    }
+    *cur_timeout = qemu_soonest_timeout(timeout_ns, *cur_timeout);
 }
 
-static void glib_select_poll(fd_set *rfds, fd_set *wfds, fd_set *xfds,
-                             bool err)
+static void glib_pollfds_poll(void)
 {
     GMainContext *context = g_main_context_default();
+    GPollFD *pfds = &g_array_index(gpollfds, GPollFD, glib_pollfds_idx);
 
-    if (!err) {
-        int i;
-
-        for (i = 0; i < n_poll_fds; i++) {
-            GPollFD *p = &poll_fds[i];
-
-            if ((p->events & G_IO_IN) && FD_ISSET(p->fd, rfds)) {
-                p->revents |= G_IO_IN;
-            }
-            if ((p->events & G_IO_OUT) && FD_ISSET(p->fd, wfds)) {
-                p->revents |= G_IO_OUT;
-            }
-            if ((p->events & G_IO_ERR) && FD_ISSET(p->fd, xfds)) {
-                p->revents |= G_IO_ERR;
-            }
-        }
-    }
-
-    if (g_main_context_check(context, max_priority, poll_fds, n_poll_fds)) {
+    if (g_main_context_check(context, max_priority, pfds, glib_n_poll_fds)) {
         g_main_context_dispatch(context);
     }
 }
 
-static int os_host_main_loop_wait(uint32_t timeout)
+#define MAX_MAIN_LOOP_SPIN (1000)
+
+static int os_host_main_loop_wait(int64_t timeout)
 {
-    struct timeval tv, *tvarg = NULL;
     int ret;
+    static int spin_counter;
 
-    glib_select_fill(&nfds, &rfds, &wfds, &xfds, &timeout);
+    glib_pollfds_fill(&timeout);
 
-    if (timeout < UINT32_MAX) {
-        tvarg = &tv;
-        tv.tv_sec = timeout / 1000;
-        tv.tv_usec = (timeout % 1000) * 1000;
+    /* If the I/O thread is very busy or we are incorrectly busy waiting in
+     * the I/O thread, this can lead to starvation of the BQL such that the
+     * VCPU threads never run.  To make sure we can detect the later case,
+     * print a message to the screen.  If we run into this condition, create
+     * a fake timeout in order to give the VCPU threads a chance to run.
+     */
+    if (!timeout && (spin_counter > MAX_MAIN_LOOP_SPIN)) {
+        static bool notified;
+
+        if (!notified) {
+            fprintf(stderr,
+                    "main-loop: WARNING: I/O thread spun for %d iterations\n",
+                    MAX_MAIN_LOOP_SPIN);
+            notified = true;
+        }
+
+        timeout = SCALE_MS;
     }
 
-    if (timeout > 0) {
+    if (timeout) {
+        spin_counter = 0;
         qemu_mutex_unlock_iothread();
+    } else {
+        spin_counter++;
     }
 
-    ret = select(nfds + 1, &rfds, &wfds, &xfds, tvarg);
+    ret = qemu_poll_ns((GPollFD *)gpollfds->data, gpollfds->len, timeout);
 
-    if (timeout > 0) {
+    if (timeout) {
         qemu_mutex_lock_iothread();
     }
 
-    glib_select_poll(&rfds, &wfds, &xfds, (ret < 0));
+    glib_pollfds_poll();
     return ret;
 }
 #else
@@ -325,14 +325,68 @@ void qemu_fd_register(int fd)
                    FD_CONNECT | FD_WRITE | FD_OOB);
 }
 
-static int os_host_main_loop_wait(uint32_t timeout)
+static int pollfds_fill(GArray *pollfds, fd_set *rfds, fd_set *wfds,
+                        fd_set *xfds)
+{
+    int nfds = -1;
+    int i;
+
+    for (i = 0; i < pollfds->len; i++) {
+        GPollFD *pfd = &g_array_index(pollfds, GPollFD, i);
+        int fd = pfd->fd;
+        int events = pfd->events;
+        if (events & G_IO_IN) {
+            FD_SET(fd, rfds);
+            nfds = MAX(nfds, fd);
+        }
+        if (events & G_IO_OUT) {
+            FD_SET(fd, wfds);
+            nfds = MAX(nfds, fd);
+        }
+        if (events & G_IO_PRI) {
+            FD_SET(fd, xfds);
+            nfds = MAX(nfds, fd);
+        }
+    }
+    return nfds;
+}
+
+static void pollfds_poll(GArray *pollfds, int nfds, fd_set *rfds,
+                         fd_set *wfds, fd_set *xfds)
+{
+    int i;
+
+    for (i = 0; i < pollfds->len; i++) {
+        GPollFD *pfd = &g_array_index(pollfds, GPollFD, i);
+        int fd = pfd->fd;
+        int revents = 0;
+
+        if (FD_ISSET(fd, rfds)) {
+            revents |= G_IO_IN;
+        }
+        if (FD_ISSET(fd, wfds)) {
+            revents |= G_IO_OUT;
+        }
+        if (FD_ISSET(fd, xfds)) {
+            revents |= G_IO_PRI;
+        }
+        pfd->revents = revents & pfd->events;
+    }
+}
+
+static int os_host_main_loop_wait(int64_t timeout)
 {
     GMainContext *context = g_main_context_default();
-    int ret, i;
+    GPollFD poll_fds[1024 * 2]; /* this is probably overkill */
+    int select_ret = 0;
+    int g_poll_ret, ret, i, n_poll_fds;
     PollingEntry *pe;
     WaitObjects *w = &wait_objects;
     gint poll_timeout;
+    int64_t poll_timeout_ns;
     static struct timeval tv0;
+    fd_set rfds, wfds, xfds;
+    int nfds;
 
     /* XXX: need to suppress polling by better using win32 events */
     ret = 0;
@@ -343,11 +397,18 @@ static int os_host_main_loop_wait(uint32_t timeout)
         return ret;
     }
 
+    FD_ZERO(&rfds);
+    FD_ZERO(&wfds);
+    FD_ZERO(&xfds);
+    nfds = pollfds_fill(gpollfds, &rfds, &wfds, &xfds);
     if (nfds >= 0) {
-        ret = select(nfds + 1, &rfds, &wfds, &xfds, &tv0);
-        if (ret != 0) {
+        select_ret = select(nfds + 1, &rfds, &wfds, &xfds, &tv0);
+        if (select_ret != 0) {
             timeout = 0;
         }
+        if (select_ret > 0) {
+            pollfds_poll(gpollfds, nfds, &rfds, &wfds, &xfds);
+        }
     }
 
     g_main_context_prepare(context, &max_priority);
@@ -360,14 +421,19 @@ static int os_host_main_loop_wait(uint32_t timeout)
         poll_fds[n_poll_fds + i].events = G_IO_IN;
     }
 
-    if (poll_timeout < 0 || timeout < poll_timeout) {
-        poll_timeout = timeout;
+    if (poll_timeout < 0) {
+        poll_timeout_ns = -1;
+    } else {
+        poll_timeout_ns = (int64_t)poll_timeout * (int64_t)SCALE_MS;
     }
 
+    poll_timeout_ns = qemu_soonest_timeout(poll_timeout_ns, timeout);
+
     qemu_mutex_unlock_iothread();
-    ret = g_poll(poll_fds, n_poll_fds + w->num, poll_timeout);
+    g_poll_ret = qemu_poll_ns(poll_fds, n_poll_fds + w->num, poll_timeout_ns);
+
     qemu_mutex_lock_iothread();
-    if (ret > 0) {
+    if (g_poll_ret > 0) {
         for (i = 0; i < w->num; i++) {
             w->revents[i] = poll_fds[n_poll_fds + i].revents;
         }
@@ -382,12 +448,7 @@ static int os_host_main_loop_wait(uint32_t timeout)
         g_main_context_dispatch(context);
     }
 
-    /* If an edge-triggered socket event occurred, select will return a
-     * positive result on the next iteration.  We do not need to do anything
-     * here.
-     */
-
-    return ret;
+    return select_ret || g_poll_ret;
 }
 #endif
 
@@ -395,30 +456,37 @@ int main_loop_wait(int nonblocking)
 {
     int ret;
     uint32_t timeout = UINT32_MAX;
+    int64_t timeout_ns;
 
     if (nonblocking) {
         timeout = 0;
     }
 
     /* poll any events */
+    g_array_set_size(gpollfds, 0); /* reset for new iteration */
     /* XXX: separate device handlers from system ones */
-    nfds = -1;
-    FD_ZERO(&rfds);
-    FD_ZERO(&wfds);
-    FD_ZERO(&xfds);
-
 #ifdef CONFIG_SLIRP
-    slirp_update_timeout(&timeout);
-    slirp_select_fill(&nfds, &rfds, &wfds, &xfds);
+    slirp_pollfds_fill(gpollfds, &timeout);
 #endif
-    qemu_iohandler_fill(&nfds, &rfds, &wfds, &xfds);
-    ret = os_host_main_loop_wait(timeout);
-    qemu_iohandler_poll(&rfds, &wfds, &xfds, ret);
+    qemu_iohandler_fill(gpollfds);
+
+    if (timeout == UINT32_MAX) {
+        timeout_ns = -1;
+    } else {
+        timeout_ns = (uint64_t)timeout * (int64_t)(SCALE_MS);
+    }
+
+    timeout_ns = qemu_soonest_timeout(timeout_ns,
+                                      timerlistgroup_deadline_ns(
+                                          &main_loop_tlg));
+
+    ret = os_host_main_loop_wait(timeout_ns);
+    qemu_iohandler_poll(gpollfds, ret);
 #ifdef CONFIG_SLIRP
-    slirp_select_poll(&rfds, &wfds, &xfds, (ret < 0));
+    slirp_pollfds_poll(gpollfds, (ret < 0));
 #endif
 
-    qemu_run_all_timers();
+    qemu_clock_run_all_timers();
 
     return ret;
 }
@@ -430,11 +498,6 @@ QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
     return aio_bh_new(qemu_aio_context, cb, opaque);
 }
 
-void qemu_aio_flush(void)
-{
-    aio_flush(qemu_aio_context);
-}
-
 bool qemu_aio_wait(void)
 {
     return aio_poll(qemu_aio_context, true);
@@ -444,17 +507,14 @@ bool qemu_aio_wait(void)
 void qemu_aio_set_fd_handler(int fd,
                              IOHandler *io_read,
                              IOHandler *io_write,
-                             AioFlushHandler *io_flush,
                              void *opaque)
 {
-    aio_set_fd_handler(qemu_aio_context, fd, io_read, io_write, io_flush,
-                       opaque);
+    aio_set_fd_handler(qemu_aio_context, fd, io_read, io_write, opaque);
 }
 #endif
 
 void qemu_aio_set_event_notifier(EventNotifier *notifier,
-                                 EventNotifierHandler *io_read,
-                                 AioFlushEventNotifierHandler *io_flush)
+                                 EventNotifierHandler *io_read)
 {
-    aio_set_event_notifier(qemu_aio_context, notifier, io_read, io_flush);
+    aio_set_event_notifier(qemu_aio_context, notifier, io_read);
 }