vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ*

IRQ setup uses the same semantics as the traditional vfio path, but we
need to share the corresponding file descriptors with the server as
necessary.

Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250625193012.2316242-10-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

3 files changed, 165 insertions, 0 deletions

diff --git a/hw/vfio-user/device.c b/hw/vfio-user/device.c
index 4ef6a2d..f01b392 100644
--- a/hw/vfio-user/device.c
+++ b/hw/vfio-user/device.c
@@ -121,6 +121,142 @@ static int vfio_user_device_io_get_region_info(VFIODevice *vbasedev,
     return 0;
 }
 
+static int vfio_user_device_io_get_irq_info(VFIODevice *vbasedev,
+                                            struct vfio_irq_info *info)
+{
+    VFIOUserProxy *proxy = vbasedev->proxy;
+    Error *local_err = NULL;
+    VFIOUserIRQInfo msg;
+
+    memset(&msg, 0, sizeof(msg));
+    vfio_user_request_msg(&msg.hdr, VFIO_USER_DEVICE_GET_IRQ_INFO,
+                          sizeof(msg), 0);
+    msg.argsz = info->argsz;
+    msg.index = info->index;
+
+    if (!vfio_user_send_wait(proxy, &msg.hdr, NULL, 0, &local_err)) {
+        error_prepend(&local_err, "%s: ", __func__);
+        error_report_err(local_err);
+        return -EFAULT;
+    }
+
+    if (msg.hdr.flags & VFIO_USER_ERROR) {
+        return -msg.hdr.error_reply;
+    }
+    trace_vfio_user_get_irq_info(msg.index, msg.flags, msg.count);
+
+    memcpy(info, &msg.argsz, sizeof(*info));
+    return 0;
+}
+
+static int irq_howmany(int *fdp, uint32_t cur, uint32_t max)
+{
+    int n = 0;
+
+    if (fdp[cur] != -1) {
+        do {
+            n++;
+        } while (n < max && fdp[cur + n] != -1);
+    } else {
+        do {
+            n++;
+        } while (n < max && fdp[cur + n] == -1);
+    }
+
+    return n;
+}
+
+static int vfio_user_device_io_set_irqs(VFIODevice *vbasedev,
+                                        struct vfio_irq_set *irq)
+{
+    VFIOUserProxy *proxy = vbasedev->proxy;
+    g_autofree VFIOUserIRQSet *msgp = NULL;
+    uint32_t size, nfds, send_fds, sent_fds, max;
+    Error *local_err = NULL;
+
+    if (irq->argsz < sizeof(*irq)) {
+        error_printf("vfio_user_set_irqs argsz too small\n");
+        return -EINVAL;
+    }
+
+    /*
+     * Handle simple case
+     */
+    if ((irq->flags & VFIO_IRQ_SET_DATA_EVENTFD) == 0) {
+        size = sizeof(VFIOUserHdr) + irq->argsz;
+        msgp = g_malloc0(size);
+
+        vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_SET_IRQS, size, 0);
+        msgp->argsz = irq->argsz;
+        msgp->flags = irq->flags;
+        msgp->index = irq->index;
+        msgp->start = irq->start;
+        msgp->count = irq->count;
+        trace_vfio_user_set_irqs(msgp->index, msgp->start, msgp->count,
+                                 msgp->flags);
+
+        if (!vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0, &local_err)) {
+            error_prepend(&local_err, "%s: ", __func__);
+            error_report_err(local_err);
+            return -EFAULT;
+        }
+
+        if (msgp->hdr.flags & VFIO_USER_ERROR) {
+            return -msgp->hdr.error_reply;
+        }
+
+        return 0;
+    }
+
+    /*
+     * Calculate the number of FDs to send
+     * and adjust argsz
+     */
+    nfds = (irq->argsz - sizeof(*irq)) / sizeof(int);
+    irq->argsz = sizeof(*irq);
+    msgp = g_malloc0(sizeof(*msgp));
+    /*
+     * Send in chunks if over max_send_fds
+     */
+    for (sent_fds = 0; nfds > sent_fds; sent_fds += send_fds) {
+        VFIOUserFDs *arg_fds, loop_fds;
+
+        /* must send all valid FDs or all invalid FDs in single msg */
+        max = nfds - sent_fds;
+        if (max > proxy->max_send_fds) {
+            max = proxy->max_send_fds;
+        }
+        send_fds = irq_howmany((int *)irq->data, sent_fds, max);
+
+        vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_SET_IRQS,
+                              sizeof(*msgp), 0);
+        msgp->argsz = irq->argsz;
+        msgp->flags = irq->flags;
+        msgp->index = irq->index;
+        msgp->start = irq->start + sent_fds;
+        msgp->count = send_fds;
+        trace_vfio_user_set_irqs(msgp->index, msgp->start, msgp->count,
+                                 msgp->flags);
+
+        loop_fds.send_fds = send_fds;
+        loop_fds.recv_fds = 0;
+        loop_fds.fds = (int *)irq->data + sent_fds;
+        arg_fds = loop_fds.fds[0] != -1 ? &loop_fds : NULL;
+
+        if (!vfio_user_send_wait(proxy, &msgp->hdr, arg_fds, 0, &local_err)) {
+            error_prepend(&local_err, "%s: ", __func__);
+            error_report_err(local_err);
+            return -EFAULT;
+        }
+
+        if (msgp->hdr.flags & VFIO_USER_ERROR) {
+            return -msgp->hdr.error_reply;
+        }
+    }
+
+    return 0;
+}
+
 static int vfio_user_device_io_region_read(VFIODevice *vbasedev, uint8_t index,
                                            off_t off, uint32_t count,
                                            void *data)
@@ -202,6 +338,8 @@ static int vfio_user_device_io_region_write(VFIODevice *vbasedev, uint8_t index,
  */
 VFIODeviceIOOps vfio_user_device_io_ops_sock = {
     .get_region_info = vfio_user_device_io_get_region_info,
+    .get_irq_info = vfio_user_device_io_get_irq_info,
+    .set_irqs = vfio_user_device_io_set_irqs,
     .region_read = vfio_user_device_io_region_read,
     .region_write = vfio_user_device_io_region_write,
 
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index 0cd32ad..48144b2 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -139,6 +139,31 @@ typedef struct {
 } VFIOUserRegionInfo;
 
 /*
+ * VFIO_USER_DEVICE_GET_IRQ_INFO
+ * imported from struct vfio_irq_info
+ */
+typedef struct {
+    VFIOUserHdr hdr;
+    uint32_t argsz;
+    uint32_t flags;
+    uint32_t index;
+    uint32_t count;
+} VFIOUserIRQInfo;
+
+/*
+ * VFIO_USER_DEVICE_SET_IRQS
+ * imported from struct vfio_irq_set
+ */
+typedef struct {
+    VFIOUserHdr hdr;
+    uint32_t argsz;
+    uint32_t flags;
+    uint32_t index;
+    uint32_t start;
+    uint32_t count;
+} VFIOUserIRQSet;
+
+/*
  * VFIO_USER_REGION_READ
  * VFIO_USER_REGION_WRITE
  */
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index 733313c..aa8f3c3 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -11,3 +11,5 @@ vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d m
 vfio_user_get_info(uint32_t nregions, uint32_t nirqs) " #regions %d #irqs %d"
 vfio_user_get_region_info(uint32_t index, uint32_t flags, uint64_t size) " index %d flags 0x%x size 0x%"PRIx64
 vfio_user_region_rw(uint32_t region, uint64_t off, uint32_t count) " region %d offset 0x%"PRIx64" count %d"
+vfio_user_get_irq_info(uint32_t index, uint32_t flags, uint32_t count) " index %d flags 0x%x count %d"
+vfio_user_set_irqs(uint32_t index, uint32_t start, uint32_t count, uint32_t flags) " index %d start %d count %d flags 0x%x"