xen: introduce an event channel for buffered io event notifications

Use the newly introduced HVM_PARAM_BUFIOREQ_EVTCHN to receive
notifications for buffered io events.
After the first notification is received leave the event channel masked
and setup a timer to process the rest of the batch.
Once we have completed processing the batch, unmask the event channel
and delete the timer.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>

xen-all.c

@@ -59,6 +59,9 @@ static inline ioreq_t *xen_vcpu_ioreq(shared_iopage_t *shared_page, int vcpu)
 }
 #  define FMT_ioreq_size "u"
 #endif
+#ifndef HVM_PARAM_BUFIOREQ_EVTCHN
+#define HVM_PARAM_BUFIOREQ_EVTCHN 26
+#endif
 
 #define BUFFER_IO_MAX_DELAY  100
 
@@ -77,6 +80,8 @@ typedef struct XenIOState {
     QEMUTimer *buffered_io_timer;
     /* the evtchn port for polling the notification, */
     evtchn_port_t *ioreq_local_port;
+    /* evtchn local port for buffered io */
+    evtchn_port_t bufioreq_local_port;
     /* the evtchn fd for polling */
     XenEvtchn xce_handle;
     /* which vcpu we are serving */
@@ -629,6 +634,12 @@ static ioreq_t *cpu_get_ioreq(XenIOState *state)
     evtchn_port_t port;
 
     port = xc_evtchn_pending(state->xce_handle);
+    if (port == state->bufioreq_local_port) {
+        qemu_mod_timer(state->buffered_io_timer,
+                BUFFER_IO_MAX_DELAY + qemu_get_clock_ms(rt_clock));
+        return NULL;
+    }
+
     if (port != -1) {
         for (i = 0; i < smp_cpus; i++) {
             if (state->ioreq_local_port[i] == port) {
@@ -777,16 +788,18 @@ static void handle_ioreq(ioreq_t *req)
     }
 }
 
-static void handle_buffered_iopage(XenIOState *state)
+static int handle_buffered_iopage(XenIOState *state)
 {
     buf_ioreq_t *buf_req = NULL;
     ioreq_t req;
     int qw;
 
     if (!state->buffered_io_page) {
-        return;
+        return 0;
     }
 
+    memset(&req, 0x00, sizeof(req));
+
     while (state->buffered_io_page->read_pointer != state->buffered_io_page->write_pointer) {
         buf_req = &state->buffered_io_page->buf_ioreq[
             state->buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM];
@@ -811,15 +824,21 @@ static void handle_buffered_iopage(XenIOState *state)
         xen_mb();
         state->buffered_io_page->read_pointer += qw ? 2 : 1;
     }
+
+    return req.count;
 }
 
 static void handle_buffered_io(void *opaque)
 {
     XenIOState *state = opaque;
 
-    handle_buffered_iopage(state);
-    qemu_mod_timer(state->buffered_io_timer,
-                   BUFFER_IO_MAX_DELAY + qemu_get_clock_ms(rt_clock));
+    if (handle_buffered_iopage(state)) {
+        qemu_mod_timer(state->buffered_io_timer,
+                BUFFER_IO_MAX_DELAY + qemu_get_clock_ms(rt_clock));
+    } else {
+        qemu_del_timer(state->buffered_io_timer);
+        xc_evtchn_unmask(state->xce_handle, state->bufioreq_local_port);
+    }
 }
 
 static void cpu_handle_ioreq(void *opaque)
@@ -949,7 +968,6 @@ static void xen_main_loop_prepare(XenIOState *state)
 
     state->buffered_io_timer = qemu_new_timer_ms(rt_clock, handle_buffered_io,
                                                  state);
-    qemu_mod_timer(state->buffered_io_timer, qemu_get_clock_ms(rt_clock));
 
     if (evtchn_fd != -1) {
         qemu_set_fd_handler(evtchn_fd, cpu_handle_ioreq, NULL, state);
@@ -1050,6 +1068,7 @@ int xen_hvm_init(void)
 {
     int i, rc;
     unsigned long ioreq_pfn;
+    unsigned long bufioreq_evtchn;
     XenIOState *state;
 
     state = g_malloc0(sizeof (XenIOState));
@@ -1102,6 +1121,20 @@ int xen_hvm_init(void)
         state->ioreq_local_port[i] = rc;
     }
 
+    rc = xc_get_hvm_param(xen_xc, xen_domid, HVM_PARAM_BUFIOREQ_EVTCHN,
+            &bufioreq_evtchn);
+    if (rc < 0) {
+        fprintf(stderr, "failed to get HVM_PARAM_BUFIOREQ_EVTCHN\n");
+        return -1;
+    }
+    rc = xc_evtchn_bind_interdomain(state->xce_handle, xen_domid,
+            (uint32_t)bufioreq_evtchn);
+    if (rc == -1) {
+        fprintf(stderr, "bind interdomain ioctl error %d\n", errno);
+        return -1;
+    }
+    state->bufioreq_local_port = rc;
+
     /* Init RAM management */
     xen_map_cache_init(xen_phys_offset_to_gaddr, state);
     xen_ram_init(ram_size);