hw/rdma: Make distinction between device init and start modes

There are certain operations that are well considered as part of device
configuration while others are needed only when "start" command is
triggered by the guest driver. An example of device initialization step
is msix_init and example of "device start" stage is the creation of a CQ
completion handler thread.

Driver expects such distinction - implement it.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Message-Id: <20180805153518.2983-2-yuval.shaia@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>

hw/rdma/rdma_backend.c

@@ -35,6 +35,7 @@
 #define VENDOR_ERR_MR_SMALL         0x208
 
 #define THR_NAME_LEN 16
+#define THR_POLL_TO  5000
 
 typedef struct BackendCtx {
     uint64_t req_id;
@@ -91,35 +92,82 @@ static void *comp_handler_thread(void *arg)
     int rc;
     struct ibv_cq *ev_cq;
     void *ev_ctx;
+    int flags;
+    GPollFD pfds[1];
+
+    /* Change to non-blocking mode */
+    flags = fcntl(backend_dev->channel->fd, F_GETFL);
+    rc = fcntl(backend_dev->channel->fd, F_SETFL, flags | O_NONBLOCK);
+    if (rc < 0) {
+        pr_dbg("Fail to change to non-blocking mode\n");
+        return NULL;
+    }
 
     pr_dbg("Starting\n");
 
+    pfds[0].fd = backend_dev->channel->fd;
+    pfds[0].events = G_IO_IN | G_IO_HUP | G_IO_ERR;
+
+    backend_dev->comp_thread.is_running = true;
+
     while (backend_dev->comp_thread.run) {
-        pr_dbg("Waiting for completion on channel %p\n", backend_dev->channel);
+        do {
-        rc = ibv_get_cq_event(backend_dev->channel, &ev_cq, &ev_ctx);
+            rc = qemu_poll_ns(pfds, 1, THR_POLL_TO * (int64_t)SCALE_MS);
-        pr_dbg("ibv_get_cq_event=%d\n", rc);
+        } while (!rc && backend_dev->comp_thread.run);
-        if (unlikely(rc)) {
+
-            pr_dbg("---> ibv_get_cq_event (%d)\n", rc);
+        if (backend_dev->comp_thread.run) {
-            continue;
+            pr_dbg("Waiting for completion on channel %p\n", backend_dev->channel);
+            rc = ibv_get_cq_event(backend_dev->channel, &ev_cq, &ev_ctx);
+            pr_dbg("ibv_get_cq_event=%d\n", rc);
+            if (unlikely(rc)) {
+                pr_dbg("---> ibv_get_cq_event (%d)\n", rc);
+                continue;
+            }
+
+            rc = ibv_req_notify_cq(ev_cq, 0);
+            if (unlikely(rc)) {
+                pr_dbg("Error %d from ibv_req_notify_cq\n", rc);
+            }
+
+            poll_cq(backend_dev->rdma_dev_res, ev_cq);
+
+            ibv_ack_cq_events(ev_cq, 1);
         }
-
-        rc = ibv_req_notify_cq(ev_cq, 0);
-        if (unlikely(rc)) {
-            pr_dbg("Error %d from ibv_req_notify_cq\n", rc);
-        }
-
-        poll_cq(backend_dev->rdma_dev_res, ev_cq);
-
-        ibv_ack_cq_events(ev_cq, 1);
     }
 
     pr_dbg("Going down\n");
 
     /* TODO: Post cqe for all remaining buffs that were posted */
 
+    backend_dev->comp_thread.is_running = false;
+
+    qemu_thread_exit(0);
+
     return NULL;
 }
 
+static void stop_comp_thread(RdmaBackendDev *backend_dev)
+{
+    backend_dev->comp_thread.run = false;
+    while (backend_dev->comp_thread.is_running) {
+        pr_dbg("Waiting for thread to complete\n");
+        sleep(THR_POLL_TO / SCALE_US / 2);
+    }
+}
+
+static void start_comp_thread(RdmaBackendDev *backend_dev)
+{
+    char thread_name[THR_NAME_LEN] = {0};
+
+    stop_comp_thread(backend_dev);
+
+    snprintf(thread_name, sizeof(thread_name), "rdma_comp_%s",
+             ibv_get_device_name(backend_dev->ib_dev));
+    backend_dev->comp_thread.run = true;
+    qemu_thread_create(&backend_dev->comp_thread.thread, thread_name,
+                       comp_handler_thread, backend_dev, QEMU_THREAD_DETACHED);
+}
+
 void rdma_backend_register_comp_handler(void (*handler)(int status,
                                         unsigned int vendor_err, void *ctx))
 {
@@ -706,7 +754,6 @@ int rdma_backend_init(RdmaBackendDev *backend_dev,
     int i;
     int ret = 0;
     int num_ibv_devices;
-    char thread_name[THR_NAME_LEN] = {0};
     struct ibv_device **dev_list;
     struct ibv_port_attr port_attr;
 
@@ -800,11 +847,8 @@ int rdma_backend_init(RdmaBackendDev *backend_dev,
     pr_dbg("interface_id=0x%" PRIx64 "\n",
            be64_to_cpu(backend_dev->gid.global.interface_id));
 
-    snprintf(thread_name, sizeof(thread_name), "rdma_comp_%s",
+    backend_dev->comp_thread.run = false;
-             ibv_get_device_name(backend_dev->ib_dev));
+    backend_dev->comp_thread.is_running = false;
-    backend_dev->comp_thread.run = true;
-    qemu_thread_create(&backend_dev->comp_thread.thread, thread_name,
-                       comp_handler_thread, backend_dev, QEMU_THREAD_DETACHED);
 
     ah_cache_init();
 
@@ -823,8 +867,22 @@ out:
     return ret;
 }
 
+
+void rdma_backend_start(RdmaBackendDev *backend_dev)
+{
+    pr_dbg("Starting rdma_backend\n");
+    start_comp_thread(backend_dev);
+}
+
+void rdma_backend_stop(RdmaBackendDev *backend_dev)
+{
+    pr_dbg("Stopping rdma_backend\n");
+    stop_comp_thread(backend_dev);
+}
+
 void rdma_backend_fini(RdmaBackendDev *backend_dev)
 {
+    rdma_backend_stop(backend_dev);
     g_hash_table_destroy(ah_hash);
     ibv_destroy_comp_channel(backend_dev->channel);
     ibv_close_device(backend_dev->context);

hw/rdma/rdma_backend.h

@@ -52,6 +52,8 @@ int rdma_backend_init(RdmaBackendDev *backend_dev,
                       uint8_t backend_gid_idx, struct ibv_device_attr *dev_attr,
                       Error **errp);
 void rdma_backend_fini(RdmaBackendDev *backend_dev);
+void rdma_backend_start(RdmaBackendDev *backend_dev);
+void rdma_backend_stop(RdmaBackendDev *backend_dev);
 void rdma_backend_register_comp_handler(void (*handler)(int status,
                                         unsigned int vendor_err, void *ctx));
 void rdma_backend_unregister_comp_handler(void);

hw/rdma/rdma_backend_defs.h

@@ -24,7 +24,8 @@ typedef struct RdmaDeviceResources RdmaDeviceResources;
 typedef struct RdmaBackendThread {
     QemuThread thread;
     QemuMutex mutex;
-    bool run;
+    bool run; /* Set by thread manager to let thread know it should exit */
+    bool is_running; /* Set by the thread to report its status */
 } RdmaBackendThread;
 
 typedef struct RdmaBackendDev {

hw/rdma/vmw/pvrdma_main.c

@@ -286,8 +286,78 @@ static void init_ports(PVRDMADev *dev, Error **errp)
     }
 }
 
+static void uninit_msix(PCIDevice *pdev, int used_vectors)
+{
+    PVRDMADev *dev = PVRDMA_DEV(pdev);
+    int i;
+
+    for (i = 0; i < used_vectors; i++) {
+        msix_vector_unuse(pdev, i);
+    }
+
+    msix_uninit(pdev, &dev->msix, &dev->msix);
+}
+
+static int init_msix(PCIDevice *pdev, Error **errp)
+{
+    PVRDMADev *dev = PVRDMA_DEV(pdev);
+    int i;
+    int rc;
+
+    rc = msix_init(pdev, RDMA_MAX_INTRS, &dev->msix, RDMA_MSIX_BAR_IDX,
+                   RDMA_MSIX_TABLE, &dev->msix, RDMA_MSIX_BAR_IDX,
+                   RDMA_MSIX_PBA, 0, NULL);
+
+    if (rc < 0) {
+        error_setg(errp, "Failed to initialize MSI-X");
+        return rc;
+    }
+
+    for (i = 0; i < RDMA_MAX_INTRS; i++) {
+        rc = msix_vector_use(PCI_DEVICE(dev), i);
+        if (rc < 0) {
+            error_setg(errp, "Fail mark MSI-X vector %d", i);
+            uninit_msix(pdev, i);
+            return rc;
+        }
+    }
+
+    return 0;
+}
+
+static void pvrdma_fini(PCIDevice *pdev)
+{
+    PVRDMADev *dev = PVRDMA_DEV(pdev);
+
+    pr_dbg("Closing device %s %x.%x\n", pdev->name, PCI_SLOT(pdev->devfn),
+           PCI_FUNC(pdev->devfn));
+
+    pvrdma_qp_ops_fini();
+
+    rdma_rm_fini(&dev->rdma_dev_res);
+
+    rdma_backend_fini(&dev->backend_dev);
+
+    free_dsr(dev);
+
+    if (msix_enabled(pdev)) {
+        uninit_msix(pdev, RDMA_MAX_INTRS);
+    }
+}
+
+static void pvrdma_stop(PVRDMADev *dev)
+{
+    rdma_backend_stop(&dev->backend_dev);
+}
+
+static void pvrdma_start(PVRDMADev *dev)
+{
+    rdma_backend_start(&dev->backend_dev);
+}
+
 static void activate_device(PVRDMADev *dev)
 {
+    pvrdma_start(dev);
     set_reg_val(dev, PVRDMA_REG_ERR, 0);
     pr_dbg("Device activated\n");
 }
@@ -300,7 +370,10 @@ static int unquiesce_device(PVRDMADev *dev)
 
 static int reset_device(PVRDMADev *dev)
 {
+    pvrdma_stop(dev);
+
     pr_dbg("Device reset complete\n");
+
     return 0;
 }
 
@@ -469,45 +542,6 @@ static void init_regs(PCIDevice *pdev)
     set_reg_val(dev, PVRDMA_REG_ERR, 0xFFFF);
 }
 
-static void uninit_msix(PCIDevice *pdev, int used_vectors)
-{
-    PVRDMADev *dev = PVRDMA_DEV(pdev);
-    int i;
-
-    for (i = 0; i < used_vectors; i++) {
-        msix_vector_unuse(pdev, i);
-    }
-
-    msix_uninit(pdev, &dev->msix, &dev->msix);
-}
-
-static int init_msix(PCIDevice *pdev, Error **errp)
-{
-    PVRDMADev *dev = PVRDMA_DEV(pdev);
-    int i;
-    int rc;
-
-    rc = msix_init(pdev, RDMA_MAX_INTRS, &dev->msix, RDMA_MSIX_BAR_IDX,
-                   RDMA_MSIX_TABLE, &dev->msix, RDMA_MSIX_BAR_IDX,
-                   RDMA_MSIX_PBA, 0, NULL);
-
-    if (rc < 0) {
-        error_setg(errp, "Failed to initialize MSI-X");
-        return rc;
-    }
-
-    for (i = 0; i < RDMA_MAX_INTRS; i++) {
-        rc = msix_vector_use(PCI_DEVICE(dev), i);
-        if (rc < 0) {
-            error_setg(errp, "Fail mark MSI-X vercor %d", i);
-            uninit_msix(pdev, i);
-            return rc;
-        }
-    }
-
-    return 0;
-}
-
 static void init_dev_caps(PVRDMADev *dev)
 {
     size_t pg_tbl_bytes = TARGET_PAGE_SIZE *
@@ -602,22 +636,7 @@ out:
 
 static void pvrdma_exit(PCIDevice *pdev)
 {
-    PVRDMADev *dev = PVRDMA_DEV(pdev);
+    pvrdma_fini(pdev);
-
-    pr_dbg("Closing device %s %x.%x\n", pdev->name, PCI_SLOT(pdev->devfn),
-           PCI_FUNC(pdev->devfn));
-
-    pvrdma_qp_ops_fini();
-
-    rdma_rm_fini(&dev->rdma_dev_res);
-
-    rdma_backend_fini(&dev->backend_dev);
-
-    free_dsr(dev);
-
-    if (msix_enabled(pdev)) {
-        uninit_msix(pdev, RDMA_MAX_INTRS);
-    }
 }
 
 static void pvrdma_class_init(ObjectClass *klass, void *data)