Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging

# gpg: Signature made Tue 27 Sep 2016 11:05:56 BST
# gpg:                using RSA key 0xEF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* remotes/jasowang/tags/net-pull-request: (27 commits)
  imx_fec: fix error in qemu_send_packet argument
  mcf_fec: fix error in qemu_send_packet argument
  net: mcf: limit buffer descriptor count
  e1000e: Fix EIAC register implementation
  e1000e: Fix spurious RX TCP ACK interrupts
  e1000e: Fix OTHER interrupts processing for MSI-X
  e1000e: Fix PBACLR implementation
  e1000e: Fix CTRL_EXT.EIAME behavior
  e1000e: Flush receive queues on link up
  e1000e: Flush all receive queues on receive enable
  net: limit allocation in nc_sendv_compat
  tap: Allow specifying a bridge
  e1000: fix buliding complaint
  docs: Add documentation for COLO-proxy
  MAINTAINERS: add maintainer for COLO-proxy
  filter-rewriter: rewrite tcp packet to keep secondary connection
  filter-rewriter: track connection and parse packet
  filter-rewriter: introduce filter-rewriter initialization
  colo-compare: add TCP, UDP, ICMP packet comparison
  colo-compare: introduce packet comparison thread
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

7 files changed, 55 insertions, 19 deletions

diff --git a/hw/net/e1000e.c b/hw/net/e1000e.c
index bad43f474e..4994e1ca00 100644
--- a/hw/net/e1000e.c
+++ b/hw/net/e1000e.c
@@ -400,7 +400,7 @@ static void e1000e_write_config(PCIDevice *pci_dev, uint32_t address,
 
     if (range_covers_byte(address, len, PCI_COMMAND) &&
         (pci_dev->config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
-        qemu_flush_queued_packets(qemu_get_queue(s->nic));
+        e1000e_start_recv(&s->core);
     }
 }
 
diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index e0bd31c577..6505983c12 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -953,7 +953,7 @@ e1000e_has_rxbufs(E1000ECore *core, const E1000E_RingInfo *r,
                          core->rx_desc_buf_size;
 }
 
-static inline void
+void
 e1000e_start_recv(E1000ECore *core)
 {
     int i;
@@ -1710,7 +1710,8 @@ e1000e_receive_iov(E1000ECore *core, const struct iovec *iov, int iovcnt)
         }
 
         /* Perform ACK receive detection */
-        if (e1000e_is_tcp_ack(core, core->rx_pkt)) {
+        if  (!(core->mac[RFCTL] & E1000_RFCTL_ACK_DIS) &&
+             (e1000e_is_tcp_ack(core, core->rx_pkt))) {
             n |= E1000_ICS_ACK;
         }
 
@@ -1807,6 +1808,7 @@ e1000e_core_set_link_status(E1000ECore *core)
                                    core->autoneg_timer);
         } else {
             e1000x_update_regs_on_link_up(core->mac, core->phy[0]);
+            e1000e_start_recv(core);
         }
     }
 
@@ -2007,19 +2009,23 @@ e1000e_msix_notify_one(E1000ECore *core, uint32_t cause, uint32_t int_cfg)
     }
 
     if (core->mac[CTRL_EXT] & E1000_CTRL_EXT_EIAME) {
-        trace_e1000e_irq_ims_clear_eiame(core->mac[IAM], cause);
-        e1000e_clear_ims_bits(core, core->mac[IAM] & cause);
+        trace_e1000e_irq_iam_clear_eiame(core->mac[IAM], cause);
+        core->mac[IAM] &= ~cause;
     }
 
     trace_e1000e_irq_icr_clear_eiac(core->mac[ICR], core->mac[EIAC]);
 
-    if (core->mac[EIAC] & E1000_ICR_OTHER) {
-        effective_eiac = (core->mac[EIAC] & E1000_EIAC_MASK) |
-                         E1000_ICR_OTHER_CAUSES;
-    } else {
-        effective_eiac = core->mac[EIAC] & E1000_EIAC_MASK;
+    effective_eiac = core->mac[EIAC] & cause;
+
+    if (effective_eiac == E1000_ICR_OTHER) {
+        effective_eiac |= E1000_ICR_OTHER_CAUSES;
     }
+
     core->mac[ICR] &= ~effective_eiac;
+
+    if (!(core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
+        core->mac[IMS] &= ~effective_eiac;
+    }
 }
 
 static void
@@ -2130,7 +2136,7 @@ e1000e_update_interrupt_state(E1000ECore *core)
 
     /* Set ICR[OTHER] for MSI-X */
     if (is_msix) {
-        if (core->mac[ICR] & core->mac[IMS] & E1000_ICR_OTHER_CAUSES) {
+        if (core->mac[ICR] & E1000_ICR_OTHER_CAUSES) {
             core->mac[ICR] |= E1000_ICR_OTHER;
             trace_e1000e_irq_add_msi_other(core->mac[ICR]);
         }
@@ -2168,7 +2174,7 @@ e1000e_update_interrupt_state(E1000ECore *core)
     }
 }
 
-static inline void
+static void
 e1000e_set_interrupt_cause(E1000ECore *core, uint32_t val)
 {
     trace_e1000e_irq_set_cause_entry(val, core->mac[ICR]);
@@ -2187,6 +2193,8 @@ e1000e_autoneg_timer(void *opaque)
     E1000ECore *core = opaque;
     if (!qemu_get_queue(core->owner_nic)->link_down) {
         e1000x_update_regs_on_autoneg_done(core->mac, core->phy[0]);
+        e1000e_start_recv(core);
+
         e1000e_update_flowctl_status(core);
         /* signal link status change to the guest */
         e1000e_set_interrupt_cause(core, E1000_ICR_LSC);
@@ -2344,7 +2352,7 @@ e1000e_set_pbaclr(E1000ECore *core, int index, uint32_t val)
 
     core->mac[PBACLR] = val & E1000_PBACLR_VALID_MASK;
 
-    if (msix_enabled(core->owner)) {
+    if (!msix_enabled(core->owner)) {
         return;
     }
 
diff --git a/hw/net/e1000e_core.h b/hw/net/e1000e_core.h
index 5f413a9e08..1ff6978ca1 100644
--- a/hw/net/e1000e_core.h
+++ b/hw/net/e1000e_core.h
@@ -144,3 +144,6 @@ e1000e_receive(E1000ECore *core, const uint8_t *buf, size_t size);
 
 ssize_t
 e1000e_receive_iov(E1000ECore *core, const struct iovec *iov, int iovcnt);
+
+void
+e1000e_start_recv(E1000ECore *core);
diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c
index 1c415ab3b1..50c75642c6 100644
--- a/hw/net/imx_fec.c
+++ b/hw/net/imx_fec.c
@@ -429,7 +429,7 @@ static void imx_fec_do_tx(IMXFECState *s)
         frame_size += len;
         if (bd.flags & ENET_BD_L) {
             /* Last buffer in frame.  */
-            qemu_send_packet(qemu_get_queue(s->nic), frame, len);
+            qemu_send_packet(qemu_get_queue(s->nic), frame, frame_size);
             ptr = frame;
             frame_size = 0;
             s->regs[ENET_EIR] |= ENET_INT_TXF;
diff --git a/hw/net/mcf_fec.c b/hw/net/mcf_fec.c
index 0ee8ad9d66..dc61bac2fc 100644
--- a/hw/net/mcf_fec.c
+++ b/hw/net/mcf_fec.c
@@ -23,6 +23,7 @@ do { printf("mcf_fec: " fmt , ## __VA_ARGS__); } while (0)
 #define DPRINTF(fmt, ...) do {} while(0)
 #endif
 
+#define FEC_MAX_DESC 1024
 #define FEC_MAX_FRAME_SIZE 2032
 
 typedef struct {
@@ -149,7 +150,7 @@ static void mcf_fec_do_tx(mcf_fec_state *s)
     uint32_t addr;
     mcf_fec_bd bd;
     int frame_size;
-    int len;
+    int len, descnt = 0;
     uint8_t frame[FEC_MAX_FRAME_SIZE];
     uint8_t *ptr;
 
@@ -157,7 +158,7 @@ static void mcf_fec_do_tx(mcf_fec_state *s)
     ptr = frame;
     frame_size = 0;
     addr = s->tx_descriptor;
-    while (1) {
+    while (descnt++ < FEC_MAX_DESC) {
         mcf_fec_read_bd(&bd, addr);
         DPRINTF("tx_bd %x flags %04x len %d data %08x\n",
                 addr, bd.flags, bd.length, bd.data);
@@ -176,7 +177,7 @@ static void mcf_fec_do_tx(mcf_fec_state *s)
         if (bd.flags & FEC_BD_L) {
             /* Last buffer in frame.  */
             DPRINTF("Sending packet\n");
-            qemu_send_packet(qemu_get_queue(s->nic), frame, len);
+            qemu_send_packet(qemu_get_queue(s->nic), frame, frame_size);
             ptr = frame;
             frame_size = 0;
             s->eir |= FEC_INT_TXF;
diff --git a/hw/net/trace-events b/hw/net/trace-events
index 47ab14ac71..1a5c909939 100644
--- a/hw/net/trace-events
+++ b/hw/net/trace-events
@@ -223,7 +223,7 @@ e1000e_irq_icr_read_entry(uint32_t icr) "Starting ICR read. Current ICR: 0x%x"
 e1000e_irq_icr_read_exit(uint32_t icr) "Ending ICR read. Current ICR: 0x%x"
 e1000e_irq_icr_clear_zero_ims(void) "Clearing ICR on read due to zero IMS"
 e1000e_irq_icr_clear_iame(void) "Clearing ICR on read due to IAME"
-e1000e_irq_ims_clear_eiame(uint32_t iam, uint32_t cause) "Clearing IMS due to EIAME, IAM: 0x%X, cause: 0x%X"
+e1000e_irq_iam_clear_eiame(uint32_t iam, uint32_t cause) "Clearing IMS due to EIAME, IAM: 0x%X, cause: 0x%X"
 e1000e_irq_icr_clear_eiac(uint32_t icr, uint32_t eiac) "Clearing ICR bits due to EIAC, ICR: 0x%X, EIAC: 0x%X"
 e1000e_irq_ims_clear_set_imc(uint32_t val) "Clearing IMS bits due to IMC write 0x%x"
 e1000e_irq_fire_delayed_interrupts(void) "Firing delayed interrupts"
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 01f1351554..6b8ae2c1fa 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -31,6 +31,11 @@
 #define MAC_TABLE_ENTRIES    64
 #define MAX_VLAN    (1 << 12)   /* Per 802.1Q definition */
 
+/* previously fixed value */
+#define VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE 256
+/* for now, only allow larger queues; with virtio-1, guest can downsize */
+#define VIRTIO_NET_RX_QUEUE_MIN_SIZE VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE
+
 /*
  * Calculate the number of bytes up to and including the given 'field' of
  * 'container'.
@@ -1412,7 +1417,8 @@ static void virtio_net_add_queue(VirtIONet *n, int index)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(n);
 
-    n->vqs[index].rx_vq = virtio_add_queue(vdev, 256, virtio_net_handle_rx);
+    n->vqs[index].rx_vq = virtio_add_queue(vdev, n->net_conf.rx_queue_size,
+                                           virtio_net_handle_rx);
     if (n->net_conf.tx && !strcmp(n->net_conf.tx, "timer")) {
         n->vqs[index].tx_vq =
             virtio_add_queue(vdev, 256, virtio_net_handle_tx_timer);
@@ -1720,6 +1726,22 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     virtio_net_set_config_size(n, n->host_features);
     virtio_init(vdev, "virtio-net", VIRTIO_ID_NET, n->config_size);
 
+    /*
+     * We set a lower limit on RX queue size to what it always was.
+     * Guests that want a smaller ring can always resize it without
+     * help from us (using virtio 1 and up).
+     */
+    if (n->net_conf.rx_queue_size < VIRTIO_NET_RX_QUEUE_MIN_SIZE ||
+        n->net_conf.rx_queue_size > VIRTQUEUE_MAX_SIZE ||
+        (n->net_conf.rx_queue_size & (n->net_conf.rx_queue_size - 1))) {
+        error_setg(errp, "Invalid rx_queue_size (= %" PRIu16 "), "
+                   "must be a power of 2 between %d and %d.",
+                   n->net_conf.rx_queue_size, VIRTIO_NET_RX_QUEUE_MIN_SIZE,
+                   VIRTQUEUE_MAX_SIZE);
+        virtio_cleanup(vdev);
+        return;
+    }
+
     n->max_queues = MAX(n->nic_conf.peers.queues, 1);
     if (n->max_queues * 2 + 1 > VIRTIO_QUEUE_MAX) {
         error_setg(errp, "Invalid number of queues (= %" PRIu32 "), "
@@ -1880,6 +1902,8 @@ static Property virtio_net_properties[] = {
                        TX_TIMER_INTERVAL),
     DEFINE_PROP_INT32("x-txburst", VirtIONet, net_conf.txburst, TX_BURST),
     DEFINE_PROP_STRING("tx", VirtIONet, net_conf.tx),
+    DEFINE_PROP_UINT16("rx_queue_size", VirtIONet, net_conf.rx_queue_size,
+                       VIRTIO_NET_RX_QUEUE_DEFAULT_SIZE),
     DEFINE_PROP_END_OF_LIST(),
 };