qemu-kvm: vhost net port

new file mode 100644
index 0000000..165a484
@@ -0,0 +1,130 @@
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+	unsigned int index;
+	unsigned int num;
+};
+
+struct vhost_vring_file {
+	unsigned int index;
+	int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+	unsigned int index;
+	/* Option flags. */
+	unsigned int flags;
+	/* Flag values: */
+	/* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+	/* Start of array of descriptors (virtually contiguous) */
+	__u64 desc_user_addr;
+	/* Used structure address. Must be 32 bit aligned */
+	__u64 used_user_addr;
+	/* Available structure address. Must be 16 bit aligned */
+	__u64 avail_user_addr;
+	/* Logging support. */
+	/* Log writes to used structure, at offset calculated from specified
+	 * address. Address must be 32 bit aligned. */
+	__u64 log_guest_addr;
+};
+
+struct vhost_memory_region {
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr;
+	__u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+	__u32 nregions;
+	__u32 padding;
+	struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility.  Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES	_IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES	_IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor.  This
+ * must be called before any other vhost command.  Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit.  Pass fd -1 to unbind from the socket and the transmit
+ * device.  This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+#endif

index 7b05462..1a15662 100644
@@ -1200,5 +1200,24 @@ int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
 }
 #endif
 
+#if defined(KVM_IRQFD)
+int kvm_set_irqfd(int gsi, int fd, bool assigned)
+{
+    struct kvm_irqfd irqfd = {
+        .fd = fd,
+        .gsi = gsi,
+        .flags = assigned ? 0 : KVM_IRQFD_FLAG_DEASSIGN,
+    };
+    int r;
+    if (!kvm_enabled() || !kvm_irqchip_in_kernel())
+        return -ENOSYS;
+
+    r = kvm_vm_ioctl(kvm_state, KVM_IRQFD, &irqfd);
+    if (r < 0)
+        return r;
+    return 0;
+}
+#endif
+
 #undef PAGE_SIZE
 #include "qemu-kvm.c"

index 0951380..72dcaca 100644
@@ -180,4 +180,14 @@ int kvm_set_ioeventfd_pio_word(int fd, uint16_t adr, uint16_t val, bool assign)
 }
 #endif
 
+#if defined(KVM_IRQFD) && defined(CONFIG_KVM)
+int kvm_set_irqfd(int gsi, int fd, bool assigned);
+#else
+static inline
+int kvm_set_irqfd(int gsi, int fd, bool assigned)
+{
+    return -ENOSYS;
+}
+#endif
+
 #endif

index faee0b2..3ec8805 100644
@@ -317,6 +317,13 @@ static void msix_mmio_writel(void *opaque, target_phys_addr_t addr,
     if (kvm_enabled() && kvm_irqchip_in_kernel()) {
         kvm_msix_update(dev, vector, was_masked, msix_is_masked(dev, vector));
     }
+    if (was_masked != msix_is_masked(dev, vector) &&
+        dev->msix_mask_notifier && dev->msix_mask_notifier_opaque[vector]) {
+        int r = dev->msix_mask_notifier(dev, vector,
+					dev->msix_mask_notifier_opaque[vector],
+					msix_is_masked(dev, vector));
+        assert(r >= 0);
+    }
     msix_handle_mask_update(dev, vector);
 }
 

@@ -355,10 +362,18 @@ void msix_mmio_map(PCIDevice *d, int region_num,
 
 static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
 {
-    int vector;
+    int vector, r;
     for (vector = 0; vector < nentries; ++vector) {
         unsigned offset = vector * MSIX_ENTRY_SIZE + MSIX_VECTOR_CTRL;
+        int was_masked = msix_is_masked(dev, vector);
         dev->msix_table_page[offset] |= MSIX_VECTOR_MASK;
+        if (was_masked != msix_is_masked(dev, vector) &&
+            dev->msix_mask_notifier && dev->msix_mask_notifier_opaque[vector]) {
+            r = dev->msix_mask_notifier(dev, vector,
+                                        dev->msix_mask_notifier_opaque[vector],
+                                        msix_is_masked(dev, vector));
+            assert(r >= 0);
+        }
     }
 }
 

@@ -381,6 +396,9 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
                                             sizeof *dev->msix_irq_entries);
     }
 #endif
+    dev->msix_mask_notifier_opaque =
+        qemu_mallocz(nentries * sizeof *dev->msix_mask_notifier_opaque);
+    dev->msix_mask_notifier = NULL;
     dev->msix_entry_used = qemu_mallocz(MSIX_MAX_ENTRIES *
                                         sizeof *dev->msix_entry_used);
 

@@ -443,6 +461,8 @@ int msix_uninit(PCIDevice *dev)
     dev->msix_entry_used = NULL;
     qemu_free(dev->msix_irq_entries);
     dev->msix_irq_entries = NULL;
+    qemu_free(dev->msix_mask_notifier_opaque);
+    dev->msix_mask_notifier_opaque = NULL;
     dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
     return 0;
 }

@@ -586,3 +606,17 @@ void msix_unuse_all_vectors(PCIDevice *dev)
         return;
     msix_free_irq_entries(dev);
 }
+
+int msix_set_mask_notifier(PCIDevice *dev, unsigned vector, void *opaque)
+{
+    int r = 0;
+    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])
+        return 0;
+
+    if (dev->msix_mask_notifier)
+        r = dev->msix_mask_notifier(dev, vector, opaque,
+                                    msix_is_masked(dev, vector));
+    if (r >= 0)
+        dev->msix_mask_notifier_opaque[vector] = opaque;
+    return r;
+}

index a9f7993..f167231 100644
@@ -33,4 +33,5 @@ void msix_reset(PCIDevice *dev);
 
 extern int msix_supported;
 
+int msix_set_mask_notifier(PCIDevice *dev, unsigned vector, void *opaque);
 #endif

index 1eab8f2..100104c 100644
@@ -136,6 +136,9 @@ enum {
 #define PCI_CAPABILITY_CONFIG_MSI_LENGTH 0x10
 #define PCI_CAPABILITY_CONFIG_MSIX_LENGTH 0x10
 
+typedef int (*msix_mask_notifier_func)(PCIDevice *, unsigned vector,
+				       void *opaque, int masked);
+
 struct PCIDevice {
     DeviceState qdev;
     /* PCI config space */

@@ -201,6 +204,9 @@ struct PCIDevice {
 
     struct kvm_irq_routing_entry *msix_irq_entries;
 
+    void **msix_mask_notifier_opaque;
+    msix_mask_notifier_func msix_mask_notifier;
+
     /* Device capability configuration space */
     struct {
         int supported;

index 4255d98..f8d8022 100644
@@ -402,6 +402,27 @@ static void virtio_pci_guest_notifier_read(void *opaque)
     }
 }
 
+static int virtio_pci_mask_notifier(PCIDevice *dev, unsigned vector,
+                                    void *opaque, int masked)
+{
+    VirtQueue *vq = opaque;
+    EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
+    int r = kvm_set_irqfd(dev->msix_irq_entries[vector].gsi,
+                          event_notifier_get_fd(notifier),
+                          !masked);
+    if (r < 0) {
+        return (r == -ENOSYS) ? 0 : r;
+    }
+    if (masked) {
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            virtio_pci_guest_notifier_read, NULL, vq);
+    } else {
+        qemu_set_fd_handler(event_notifier_get_fd(notifier),
+                            NULL, NULL, NULL);
+    }
+    return 0;
+}
+
 static int virtio_pci_set_guest_notifier(void *opaque, int n, bool assign)
 {
     VirtIOPCIProxy *proxy = opaque;

@@ -415,7 +436,11 @@ static int virtio_pci_set_guest_notifier(void *opaque, int n, bool assign)
         }
         qemu_set_fd_handler(event_notifier_get_fd(notifier),
                             virtio_pci_guest_notifier_read, NULL, vq);
+        msix_set_mask_notifier(&proxy->pci_dev,
+                               virtio_queue_vector(proxy->vdev, n), vq);
     } else {
+        msix_set_mask_notifier(&proxy->pci_dev,
+                               virtio_queue_vector(proxy->vdev, n), NULL);
         qemu_set_fd_handler(event_notifier_get_fd(notifier),
                             NULL, NULL, NULL);
         event_notifier_cleanup(notifier);

@@ -500,6 +525,8 @@ static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,
 
     proxy->pci_dev.config_write = virtio_write_config;
 
+    proxy->pci_dev.msix_mask_notifier = virtio_pci_mask_notifier;
+
     size = VIRTIO_PCI_REGION_SIZE(&proxy->pci_dev) + vdev->config_len;
     if (size & (size-1))
         size = 1 << qemu_fls(size);