dataplane: add virtio-blk data plane code

virtio-blk-data-plane is a subset implementation of virtio-blk.  It only
handles read, write, and flush requests.  It does this using a dedicated
thread that executes an epoll(2)-based event loop and processes I/O
using Linux AIO.

This approach performs very well but can be used for raw image files
only.  The number of IOPS achieved has been reported to be several times
higher than the existing virtio-blk implementation.

Eventually it should be possible to unify virtio-blk-data-plane with the
main body of QEMU code once the block layer and hardware emulation is
able to run outside the global mutex.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

5 files changed, 502 insertions, 1 deletions

diff --git a/hw/dataplane/Makefile.objs b/hw/dataplane/Makefile.objs
index abd408f1da..682aa9e7ee 100644
--- a/hw/dataplane/Makefile.objs
+++ b/hw/dataplane/Makefile.objs
@@ -1,3 +1,3 @@
 ifeq ($(CONFIG_VIRTIO), y)
-common-obj-$(CONFIG_VIRTIO_BLK_DATA_PLANE) += hostmem.o vring.o event-poll.o ioq.o
+common-obj-$(CONFIG_VIRTIO_BLK_DATA_PLANE) += hostmem.o vring.o event-poll.o ioq.o virtio-blk.o
 endif
diff --git a/hw/dataplane/virtio-blk.c b/hw/dataplane/virtio-blk.c
new file mode 100644
index 0000000000..4c4ad8422a
--- /dev/null
+++ b/hw/dataplane/virtio-blk.c
@@ -0,0 +1,465 @@
+/*
+ * Dedicated thread for virtio-blk I/O processing
+ *
+ * Copyright 2012 IBM, Corp.
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *   Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "trace.h"
+#include "qemu/iov.h"
+#include "event-poll.h"
+#include "qemu/thread.h"
+#include "vring.h"
+#include "ioq.h"
+#include "migration/migration.h"
+#include "hw/virtio-blk.h"
+#include "hw/dataplane/virtio-blk.h"
+
+enum {
+    SEG_MAX = 126,                  /* maximum number of I/O segments */
+    VRING_MAX = SEG_MAX + 2,        /* maximum number of vring descriptors */
+    REQ_MAX = VRING_MAX,            /* maximum number of requests in the vring,
+                                     * is VRING_MAX / 2 with traditional and
+                                     * VRING_MAX with indirect descriptors */
+};
+
+typedef struct {
+    struct iocb iocb;               /* Linux AIO control block */
+    QEMUIOVector *inhdr;            /* iovecs for virtio_blk_inhdr */
+    unsigned int head;              /* vring descriptor index */
+} VirtIOBlockRequest;
+
+struct VirtIOBlockDataPlane {
+    bool started;
+    QEMUBH *start_bh;
+    QemuThread thread;
+
+    VirtIOBlkConf *blk;
+    int fd;                         /* image file descriptor */
+
+    VirtIODevice *vdev;
+    Vring vring;                    /* virtqueue vring */
+    EventNotifier *guest_notifier;  /* irq */
+
+    EventPoll event_poll;           /* event poller */
+    EventHandler io_handler;        /* Linux AIO completion handler */
+    EventHandler notify_handler;    /* virtqueue notify handler */
+
+    IOQueue ioqueue;                /* Linux AIO queue (should really be per
+                                       dataplane thread) */
+    VirtIOBlockRequest requests[REQ_MAX]; /* pool of requests, managed by the
+                                             queue */
+
+    unsigned int num_reqs;
+
+    Error *migration_blocker;
+};
+
+/* Raise an interrupt to signal guest, if necessary */
+static void notify_guest(VirtIOBlockDataPlane *s)
+{
+    if (!vring_should_notify(s->vdev, &s->vring)) {
+        return;
+    }
+
+    event_notifier_set(s->guest_notifier);
+}
+
+static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
+{
+    VirtIOBlockDataPlane *s = opaque;
+    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
+    struct virtio_blk_inhdr hdr;
+    int len;
+
+    if (likely(ret >= 0)) {
+        hdr.status = VIRTIO_BLK_S_OK;
+        len = ret;
+    } else {
+        hdr.status = VIRTIO_BLK_S_IOERR;
+        len = 0;
+    }
+
+    trace_virtio_blk_data_plane_complete_request(s, req->head, ret);
+
+    qemu_iovec_from_buf(req->inhdr, 0, &hdr, sizeof(hdr));
+    qemu_iovec_destroy(req->inhdr);
+    g_slice_free(QEMUIOVector, req->inhdr);
+
+    /* According to the virtio specification len should be the number of bytes
+     * written to, but for virtio-blk it seems to be the number of bytes
+     * transferred plus the status bytes.
+     */
+    vring_push(&s->vring, req->head, len + sizeof(hdr));
+
+    s->num_reqs--;
+}
+
+static void complete_request_early(VirtIOBlockDataPlane *s, unsigned int head,
+                                   QEMUIOVector *inhdr, unsigned char status)
+{
+    struct virtio_blk_inhdr hdr = {
+        .status = status,
+    };
+
+    qemu_iovec_from_buf(inhdr, 0, &hdr, sizeof(hdr));
+    qemu_iovec_destroy(inhdr);
+    g_slice_free(QEMUIOVector, inhdr);
+
+    vring_push(&s->vring, head, sizeof(hdr));
+    notify_guest(s);
+}
+
+/* Get disk serial number */
+static void do_get_id_cmd(VirtIOBlockDataPlane *s,
+                          struct iovec *iov, unsigned int iov_cnt,
+                          unsigned int head, QEMUIOVector *inhdr)
+{
+    char id[VIRTIO_BLK_ID_BYTES];
+
+    /* Serial number not NUL-terminated when shorter than buffer */
+    strncpy(id, s->blk->serial ? s->blk->serial : "", sizeof(id));
+    iov_from_buf(iov, iov_cnt, 0, id, sizeof(id));
+    complete_request_early(s, head, inhdr, VIRTIO_BLK_S_OK);
+}
+
+static int process_request(IOQueue *ioq, struct iovec iov[],
+                           unsigned int out_num, unsigned int in_num,
+                           unsigned int head)
+{
+    VirtIOBlockDataPlane *s = container_of(ioq, VirtIOBlockDataPlane, ioqueue);
+    struct iovec *in_iov = &iov[out_num];
+    struct virtio_blk_outhdr outhdr;
+    QEMUIOVector *inhdr;
+    size_t in_size;
+    struct iocb *iocb;
+
+    /* Copy in outhdr */
+    if (unlikely(iov_to_buf(iov, out_num, 0, &outhdr,
+                            sizeof(outhdr)) != sizeof(outhdr))) {
+        error_report("virtio-blk request outhdr too short");
+        return -EFAULT;
+    }
+    iov_discard_front(&iov, &out_num, sizeof(outhdr));
+
+    /* Grab inhdr for later */
+    in_size = iov_size(in_iov, in_num);
+    if (in_size < sizeof(struct virtio_blk_inhdr)) {
+        error_report("virtio_blk request inhdr too short");
+        return -EFAULT;
+    }
+    inhdr = g_slice_new(QEMUIOVector);
+    qemu_iovec_init(inhdr, 1);
+    qemu_iovec_concat_iov(inhdr, in_iov, in_num,
+            in_size - sizeof(struct virtio_blk_inhdr),
+            sizeof(struct virtio_blk_inhdr));
+    iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
+
+    /* TODO Linux sets the barrier bit even when not advertised! */
+    outhdr.type &= ~VIRTIO_BLK_T_BARRIER;
+
+    switch (outhdr.type) {
+    case VIRTIO_BLK_T_IN:
+        iocb = ioq_rdwr(ioq, true, in_iov, in_num, outhdr.sector * 512);
+        break;
+
+    case VIRTIO_BLK_T_OUT:
+        iocb = ioq_rdwr(ioq, false, iov, out_num, outhdr.sector * 512);
+        break;
+
+    case VIRTIO_BLK_T_SCSI_CMD:
+        /* TODO support SCSI commands */
+        complete_request_early(s, head, inhdr, VIRTIO_BLK_S_UNSUPP);
+        return 0;
+
+    case VIRTIO_BLK_T_FLUSH:
+        /* TODO fdsync not supported by Linux AIO, do it synchronously here! */
+        if (qemu_fdatasync(s->fd) < 0) {
+            complete_request_early(s, head, inhdr, VIRTIO_BLK_S_IOERR);
+        } else {
+            complete_request_early(s, head, inhdr, VIRTIO_BLK_S_OK);
+        }
+        return 0;
+
+    case VIRTIO_BLK_T_GET_ID:
+        do_get_id_cmd(s, in_iov, in_num, head, inhdr);
+        return 0;
+
+    default:
+        error_report("virtio-blk unsupported request type %#x", outhdr.type);
+        qemu_iovec_destroy(inhdr);
+        g_slice_free(QEMUIOVector, inhdr);
+        return -EFAULT;
+    }
+
+    /* Fill in virtio block metadata needed for completion */
+    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
+    req->head = head;
+    req->inhdr = inhdr;
+    return 0;
+}
+
+static void handle_notify(EventHandler *handler)
+{
+    VirtIOBlockDataPlane *s = container_of(handler, VirtIOBlockDataPlane,
+                                           notify_handler);
+
+    /* There is one array of iovecs into which all new requests are extracted
+     * from the vring.  Requests are read from the vring and the translated
+     * descriptors are written to the iovecs array.  The iovecs do not have to
+     * persist across handle_notify() calls because the kernel copies the
+     * iovecs on io_submit().
+     *
+     * Handling io_submit() EAGAIN may require storing the requests across
+     * handle_notify() calls until the kernel has sufficient resources to
+     * accept more I/O.  This is not implemented yet.
+     */
+    struct iovec iovec[VRING_MAX];
+    struct iovec *end = &iovec[VRING_MAX];
+    struct iovec *iov = iovec;
+
+    /* When a request is read from the vring, the index of the first descriptor
+     * (aka head) is returned so that the completed request can be pushed onto
+     * the vring later.
+     *
+     * The number of hypervisor read-only iovecs is out_num.  The number of
+     * hypervisor write-only iovecs is in_num.
+     */
+    int head;
+    unsigned int out_num = 0, in_num = 0;
+    unsigned int num_queued;
+
+    for (;;) {
+        /* Disable guest->host notifies to avoid unnecessary vmexits */
+        vring_disable_notification(s->vdev, &s->vring);
+
+        for (;;) {
+            head = vring_pop(s->vdev, &s->vring, iov, end, &out_num, &in_num);
+            if (head < 0) {
+                break; /* no more requests */
+            }
+
+            trace_virtio_blk_data_plane_process_request(s, out_num, in_num,
+                                                        head);
+
+            if (process_request(&s->ioqueue, iov, out_num, in_num, head) < 0) {
+                vring_set_broken(&s->vring);
+                break;
+            }
+            iov += out_num + in_num;
+        }
+
+        if (likely(head == -EAGAIN)) { /* vring emptied */
+            /* Re-enable guest->host notifies and stop processing the vring.
+             * But if the guest has snuck in more descriptors, keep processing.
+             */
+            if (vring_enable_notification(s->vdev, &s->vring)) {
+                break;
+            }
+        } else { /* head == -ENOBUFS or fatal error, iovecs[] is depleted */
+            /* Since there are no iovecs[] left, stop processing for now.  Do
+             * not re-enable guest->host notifies since the I/O completion
+             * handler knows to check for more vring descriptors anyway.
+             */
+            break;
+        }
+    }
+
+    num_queued = ioq_num_queued(&s->ioqueue);
+    if (num_queued > 0) {
+        s->num_reqs += num_queued;
+
+        int rc = ioq_submit(&s->ioqueue);
+        if (unlikely(rc < 0)) {
+            fprintf(stderr, "ioq_submit failed %d\n", rc);
+            exit(1);
+        }
+    }
+}
+
+static void handle_io(EventHandler *handler)
+{
+    VirtIOBlockDataPlane *s = container_of(handler, VirtIOBlockDataPlane,
+                                           io_handler);
+
+    if (ioq_run_completion(&s->ioqueue, complete_request, s) > 0) {
+        notify_guest(s);
+    }
+
+    /* If there were more requests than iovecs, the vring will not be empty yet
+     * so check again.  There should now be enough resources to process more
+     * requests.
+     */
+    if (unlikely(vring_more_avail(&s->vring))) {
+        handle_notify(&s->notify_handler);
+    }
+}
+
+static void *data_plane_thread(void *opaque)
+{
+    VirtIOBlockDataPlane *s = opaque;
+
+    do {
+        event_poll(&s->event_poll);
+    } while (s->started || s->num_reqs > 0);
+    return NULL;
+}
+
+static void start_data_plane_bh(void *opaque)
+{
+    VirtIOBlockDataPlane *s = opaque;
+
+    qemu_bh_delete(s->start_bh);
+    s->start_bh = NULL;
+    qemu_thread_create(&s->thread, data_plane_thread,
+                       s, QEMU_THREAD_JOINABLE);
+}
+
+bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
+                                  VirtIOBlockDataPlane **dataplane)
+{
+    VirtIOBlockDataPlane *s;
+    int fd;
+
+    *dataplane = NULL;
+
+    if (!blk->data_plane) {
+        return true;
+    }
+
+    if (blk->scsi) {
+        error_report("device is incompatible with x-data-plane, use scsi=off");
+        return false;
+    }
+
+    if (blk->config_wce) {
+        error_report("device is incompatible with x-data-plane, "
+                     "use config-wce=off");
+        return false;
+    }
+
+    fd = raw_get_aio_fd(blk->conf.bs);
+    if (fd < 0) {
+        error_report("drive is incompatible with x-data-plane, "
+                     "use format=raw,cache=none,aio=native");
+        return false;
+    }
+
+    s = g_new0(VirtIOBlockDataPlane, 1);
+    s->vdev = vdev;
+    s->fd = fd;
+    s->blk = blk;
+
+    /* Prevent block operations that conflict with data plane thread */
+    bdrv_set_in_use(blk->conf.bs, 1);
+
+    error_setg(&s->migration_blocker,
+            "x-data-plane does not support migration");
+    migrate_add_blocker(s->migration_blocker);
+
+    *dataplane = s;
+    return true;
+}
+
+void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
+{
+    if (!s) {
+        return;
+    }
+
+    virtio_blk_data_plane_stop(s);
+    migrate_del_blocker(s->migration_blocker);
+    error_free(s->migration_blocker);
+    bdrv_set_in_use(s->blk->conf.bs, 0);
+    g_free(s);
+}
+
+void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
+{
+    VirtQueue *vq;
+    int i;
+
+    if (s->started) {
+        return;
+    }
+
+    vq = virtio_get_queue(s->vdev, 0);
+    if (!vring_setup(&s->vring, s->vdev, 0)) {
+        return;
+    }
+
+    event_poll_init(&s->event_poll);
+
+    /* Set up guest notifier (irq) */
+    if (s->vdev->binding->set_guest_notifiers(s->vdev->binding_opaque,
+                                              true) != 0) {
+        fprintf(stderr, "virtio-blk failed to set guest notifier, "
+                "ensure -enable-kvm is set\n");
+        exit(1);
+    }
+    s->guest_notifier = virtio_queue_get_guest_notifier(vq);
+
+    /* Set up virtqueue notify */
+    if (s->vdev->binding->set_host_notifier(s->vdev->binding_opaque,
+                                            0, true) != 0) {
+        fprintf(stderr, "virtio-blk failed to set host notifier\n");
+        exit(1);
+    }
+    event_poll_add(&s->event_poll, &s->notify_handler,
+                   virtio_queue_get_host_notifier(vq),
+                   handle_notify);
+
+    /* Set up ioqueue */
+    ioq_init(&s->ioqueue, s->fd, REQ_MAX);
+    for (i = 0; i < ARRAY_SIZE(s->requests); i++) {
+        ioq_put_iocb(&s->ioqueue, &s->requests[i].iocb);
+    }
+    event_poll_add(&s->event_poll, &s->io_handler,
+                   ioq_get_notifier(&s->ioqueue), handle_io);
+
+    s->started = true;
+    trace_virtio_blk_data_plane_start(s);
+
+    /* Kick right away to begin processing requests already in vring */
+    event_notifier_set(virtio_queue_get_host_notifier(vq));
+
+    /* Spawn thread in BH so it inherits iothread cpusets */
+    s->start_bh = qemu_bh_new(start_data_plane_bh, s);
+    qemu_bh_schedule(s->start_bh);
+}
+
+void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
+{
+    if (!s->started) {
+        return;
+    }
+    s->started = false;
+    trace_virtio_blk_data_plane_stop(s);
+
+    /* Stop thread or cancel pending thread creation BH */
+    if (s->start_bh) {
+        qemu_bh_delete(s->start_bh);
+        s->start_bh = NULL;
+    } else {
+        event_poll_notify(&s->event_poll);
+        qemu_thread_join(&s->thread);
+    }
+
+    ioq_cleanup(&s->ioqueue);
+
+    s->vdev->binding->set_host_notifier(s->vdev->binding_opaque, 0, false);
+
+    event_poll_cleanup(&s->event_poll);
+
+    /* Clean up guest notifier (irq) */
+    s->vdev->binding->set_guest_notifiers(s->vdev->binding_opaque, false);
+
+    vring_teardown(&s->vring);
+}
diff --git a/hw/dataplane/virtio-blk.h b/hw/dataplane/virtio-blk.h
new file mode 100644
index 0000000000..1e8fdfe418
--- /dev/null
+++ b/hw/dataplane/virtio-blk.h
@@ -0,0 +1,29 @@
+/*
+ * Dedicated thread for virtio-blk I/O processing
+ *
+ * Copyright 2012 IBM, Corp.
+ * Copyright 2012 Red Hat, Inc. and/or its affiliates
+ *
+ * Authors:
+ *   Stefan Hajnoczi <stefanha@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef HW_DATAPLANE_VIRTIO_BLK_H
+#define HW_DATAPLANE_VIRTIO_BLK_H
+
+#include "hw/virtio.h"
+
+typedef struct VirtIOBlockDataPlane VirtIOBlockDataPlane;
+
+bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
+                                  VirtIOBlockDataPlane **dataplane);
+void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_drain(VirtIOBlockDataPlane *s);
+
+#endif /* HW_DATAPLANE_VIRTIO_BLK_H */
diff --git a/hw/virtio-blk.h b/hw/virtio-blk.h
index 454f445d61..43ca492080 100644
--- a/hw/virtio-blk.h
+++ b/hw/virtio-blk.h
@@ -105,6 +105,7 @@ struct VirtIOBlkConf
     char *serial;
     uint32_t scsi;
     uint32_t config_wce;
+    uint32_t data_plane;
 };
 
 #define DEFINE_VIRTIO_BLK_FEATURES(_state, _field) \
diff --git a/trace-events b/trace-events
index 167d776eff..4023a4c094 100644
--- a/trace-events
+++ b/trace-events
@@ -98,6 +98,12 @@ virtio_blk_rw_complete(void *req, int ret) "req %p ret %d"
 virtio_blk_handle_write(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
 virtio_blk_handle_read(void *req, uint64_t sector, size_t nsectors) "req %p sector %"PRIu64" nsectors %zu"
 
+# hw/dataplane/virtio-blk.c
+virtio_blk_data_plane_start(void *s) "dataplane %p"
+virtio_blk_data_plane_stop(void *s) "dataplane %p"
+virtio_blk_data_plane_process_request(void *s, unsigned int out_num, unsigned int in_num, unsigned int head) "dataplane %p out_num %u in_num %u head %u"
+virtio_blk_data_plane_complete_request(void *s, unsigned int head, int ret) "dataplane %p head %u ret %d"
+
 # hw/dataplane/vring.c
 vring_setup(uint64_t physical, void *desc, void *avail, void *used) "vring physical %#"PRIx64" desc %p avail %p used %p"