vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO

Add support for getting region info for vfio-user. As vfio-user has one
fd per region, enable ->use_region_fds.

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/20250625193012.2316242-7-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

6 files changed, 103 insertions, 0 deletions

diff --git a/hw/vfio-user/device.c b/hw/vfio-user/device.c
index 4212fef..d90232a 100644
--- a/hw/vfio-user/device.c
+++ b/hw/vfio-user/device.c
@@ -53,3 +53,77 @@ bool vfio_user_get_device_info(VFIOUserProxy *proxy,
 
     return true;
 }
+
+static int vfio_user_get_region_info(VFIOUserProxy *proxy,
+                                     struct vfio_region_info *info,
+                                     VFIOUserFDs *fds)
+{
+    g_autofree VFIOUserRegionInfo *msgp = NULL;
+    Error *local_err = NULL;
+    uint32_t size;
+
+    /* data returned can be larger than vfio_region_info */
+    if (info->argsz < sizeof(*info)) {
+        error_printf("vfio_user_get_region_info argsz too small\n");
+        return -E2BIG;
+    }
+    if (fds != NULL && fds->send_fds != 0) {
+        error_printf("vfio_user_get_region_info can't send FDs\n");
+        return -EINVAL;
+    }
+
+    size = info->argsz + sizeof(VFIOUserHdr);
+    msgp = g_malloc0(size);
+
+    vfio_user_request_msg(&msgp->hdr, VFIO_USER_DEVICE_GET_REGION_INFO,
+                          sizeof(*msgp), 0);
+    msgp->argsz = info->argsz;
+    msgp->index = info->index;
+
+    if (!vfio_user_send_wait(proxy, &msgp->hdr, fds, size, &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;
+    }
+    trace_vfio_user_get_region_info(msgp->index, msgp->flags, msgp->size);
+
+    memcpy(info, &msgp->argsz, info->argsz);
+    return 0;
+}
+
+
+static int vfio_user_device_io_get_region_info(VFIODevice *vbasedev,
+                                               struct vfio_region_info *info,
+                                               int *fd)
+{
+    VFIOUserFDs fds = { 0, 1, fd};
+    int ret;
+
+    if (info->index > vbasedev->num_regions) {
+        return -EINVAL;
+    }
+
+    ret = vfio_user_get_region_info(vbasedev->proxy, info, &fds);
+    if (ret) {
+        return ret;
+    }
+
+    /* cap_offset in valid area */
+    if ((info->flags & VFIO_REGION_INFO_FLAG_CAPS) &&
+        (info->cap_offset < sizeof(*info) || info->cap_offset > info->argsz)) {
+        return -EINVAL;
+    }
+
+    return 0;
+}
+
+/*
+ * Socket-based io_ops
+ */
+VFIODeviceIOOps vfio_user_device_io_ops_sock = {
+    .get_region_info = vfio_user_device_io_get_region_info,
+};
diff --git a/hw/vfio-user/device.h b/hw/vfio-user/device.h
index ef3f71e..619c0f3 100644
--- a/hw/vfio-user/device.h
+++ b/hw/vfio-user/device.h
@@ -17,4 +17,6 @@
 bool vfio_user_get_device_info(VFIOUserProxy *proxy,
                                struct vfio_device_info *info, Error **errp);
 
+extern VFIODeviceIOOps vfio_user_device_io_ops_sock;
+
 #endif /* VFIO_USER_DEVICE_H */
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 61f525c..d704e3d 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -12,6 +12,7 @@
 
 #include "hw/qdev-properties.h"
 #include "hw/vfio/pci.h"
+#include "hw/vfio-user/device.h"
 #include "hw/vfio-user/proxy.h"
 
 #define TYPE_VFIO_USER_PCI "vfio-user-pci"
@@ -104,10 +105,20 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     }
 
     /*
+     * Use socket-based device I/O instead of vfio kernel driver.
+     */
+    vbasedev->io_ops = &vfio_user_device_io_ops_sock;
+
+    /*
      * vfio-user devices are effectively mdevs (don't use a host iommu).
      */
     vbasedev->mdev = true;
 
+    /*
+     * Enable per-region fds.
+     */
+    vbasedev->use_region_fds = true;
+
     as = pci_device_iommu_address_space(pdev);
     if (!vfio_device_attach_by_iommu_type(TYPE_VFIO_IOMMU_USER,
                                           vbasedev->name, vbasedev,
diff --git a/hw/vfio-user/protocol.h b/hw/vfio-user/protocol.h
index e0bba68..db88f5f 100644
--- a/hw/vfio-user/protocol.h
+++ b/hw/vfio-user/protocol.h
@@ -124,4 +124,18 @@ typedef struct {
     uint32_t num_irqs;
 } VFIOUserDeviceInfo;
 
+/*
+ * VFIO_USER_DEVICE_GET_REGION_INFO
+ * imported from struct vfio_region_info
+ */
+typedef struct {
+    VFIOUserHdr hdr;
+    uint32_t argsz;
+    uint32_t flags;
+    uint32_t index;
+    uint32_t cap_offset;
+    uint64_t size;
+    uint64_t offset;
+} VFIOUserRegionInfo;
+
 #endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio-user/proxy.h b/hw/vfio-user/proxy.h
index 837b02a..ba1c33a 100644
--- a/hw/vfio-user/proxy.h
+++ b/hw/vfio-user/proxy.h
@@ -15,6 +15,7 @@
 #include "qemu/queue.h"
 #include "qemu/sockets.h"
 #include "qemu/thread.h"
+#include "hw/vfio/vfio-device.h"
 #include "hw/vfio-user/protocol.h"
 
 typedef struct {
diff --git a/hw/vfio-user/trace-events b/hw/vfio-user/trace-events
index b7312d6..ef3f14c 100644
--- a/hw/vfio-user/trace-events
+++ b/hw/vfio-user/trace-events
@@ -9,3 +9,4 @@ vfio_user_recv_request(uint16_t cmd) " command 0x%x"
 vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
 vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"
 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