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

# gpg: Signature made Mon 15 Mar 2021 08:42:25 GMT
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [marginal]
# 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:
  net: Do not fill legacy info_str for backends
  hmp: Use QAPI NetdevInfo in hmp_info_network
  net: Move NetClientState.info_str to dynamic allocations
  tests: Add tests for query-netdev command
  qapi: net: Add query-netdev command
  pvrdma: wean code off pvrdma_ring.h kernel header
  lan9118: switch to use qemu_receive_packet() for loopback
  cadence_gem: switch to use qemu_receive_packet() for loopback
  pcnet: switch to use qemu_receive_packet() for loopback
  rtl8139: switch to use qemu_receive_packet() for loopback
  tx_pkt: switch to use qemu_receive_packet_iov() for loopback
  sungem: switch to use qemu_receive_packet() for loopback
  msf2-mac: switch to use qemu_receive_packet() for loopback
  dp8393x: switch to use qemu_receive_packet() for loopback packet
  e1000: switch to use qemu_receive_packet() for loopback
  net: introduce qemu_receive_packet()
  e1000: fail early for evil descriptor
  net: validate that ids are well formed
  net: Fix build error when DEBUG_NET is on
  virtio-net: calculating proper msix vectors on init

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

# Conflicts:
#	hw/core/machine.c

17 files changed, 63 insertions, 42 deletions

diff --git a/hw/core/machine.c b/hw/core/machine.c
index 4c1a4a4c32..257a664ea2 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -40,6 +40,7 @@ GlobalProperty hw_compat_5_2[] = {
     { "ICH9-LPC", "smm-compat", "on"},
     { "PIIX4_PM", "smm-compat", "on"},
     { "virtio-blk-device", "report-discard-granularity", "off" },
+    { "virtio-net-pci", "vectors", "3"},
 };
 const size_t hw_compat_5_2_len = G_N_ELEMENTS(hw_compat_5_2);
 
diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c
index 9a4474a084..24b3a0ff66 100644
--- a/hw/net/cadence_gem.c
+++ b/hw/net/cadence_gem.c
@@ -1275,8 +1275,8 @@ static void gem_transmit(CadenceGEMState *s)
                 /* Send the packet somewhere */
                 if (s->phy_loop || (s->regs[GEM_NWCTRL] &
                                     GEM_NWCTRL_LOCALLOOP)) {
-                    gem_receive(qemu_get_queue(s->nic), s->tx_packet,
-                                total_bytes);
+                    qemu_receive_packet(qemu_get_queue(s->nic), s->tx_packet,
+                                        total_bytes);
                 } else {
                     qemu_send_packet(qemu_get_queue(s->nic), s->tx_packet,
                                      total_bytes);
diff --git a/hw/net/dp8393x.c b/hw/net/dp8393x.c
index 205c0decc5..533a8304d0 100644
--- a/hw/net/dp8393x.c
+++ b/hw/net/dp8393x.c
@@ -506,7 +506,7 @@ static void dp8393x_do_transmit_packets(dp8393xState *s)
             s->regs[SONIC_TCR] |= SONIC_TCR_CRSL;
             if (nc->info->can_receive(nc)) {
                 s->loopback_packet = 1;
-                nc->info->receive(nc, s->tx_buffer, tx_len);
+                qemu_receive_packet(nc, s->tx_buffer, tx_len);
             }
         } else {
             /* Transmit packet */
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index d8da2f6528..4f75b44cfc 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -546,7 +546,7 @@ e1000_send_packet(E1000State *s, const uint8_t *buf, int size)
 
     NetClientState *nc = qemu_get_queue(s->nic);
     if (s->phy_reg[PHY_CTRL] & MII_CR_LOOPBACK) {
-        nc->info->receive(nc, buf, size);
+        qemu_receive_packet(nc, buf, size);
     } else {
         qemu_send_packet(nc, buf, size);
     }
@@ -670,6 +670,9 @@ process_tx_desc(E1000State *s, struct e1000_tx_desc *dp)
         msh = tp->tso_props.hdr_len + tp->tso_props.mss;
         do {
             bytes = split_size;
+            if (tp->size >= msh) {
+                goto eop;
+            }
             if (tp->size + bytes > msh)
                 bytes = msh - tp->size;
 
@@ -695,6 +698,7 @@ process_tx_desc(E1000State *s, struct e1000_tx_desc *dp)
         tp->size += split_size;
     }
 
+eop:
     if (!(txd_lower & E1000_TXD_CMD_EOP))
         return;
     if (!(tp->cptse && tp->size < tp->tso_props.hdr_len)) {
diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c
index abc796285a..6aff424cbe 100644
--- a/hw/net/lan9118.c
+++ b/hw/net/lan9118.c
@@ -680,7 +680,7 @@ static void do_tx_packet(lan9118_state *s)
     /* FIXME: Honor TX disable, and allow queueing of packets.  */
     if (s->phy_control & 0x4000)  {
         /* This assumes the receive routine doesn't touch the VLANClient.  */
-        lan9118_receive(qemu_get_queue(s->nic), s->txp->data, s->txp->len);
+        qemu_receive_packet(qemu_get_queue(s->nic), s->txp->data, s->txp->len);
     } else {
         qemu_send_packet(qemu_get_queue(s->nic), s->txp->data, s->txp->len);
     }
diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c
index 32ba9e8412..3e6206044f 100644
--- a/hw/net/msf2-emac.c
+++ b/hw/net/msf2-emac.c
@@ -158,7 +158,7 @@ static void msf2_dma_tx(MSF2EmacState *s)
          * R_CFG1 bit 0 is set.
          */
         if (s->regs[R_CFG1] & R_CFG1_LB_EN_MASK) {
-            nc->info->receive(nc, buf, size);
+            qemu_receive_packet(nc, buf, size);
         } else {
             qemu_send_packet(nc, buf, size);
         }
diff --git a/hw/net/net_tx_pkt.c b/hw/net/net_tx_pkt.c
index da262edc3e..1f9aa59eca 100644
--- a/hw/net/net_tx_pkt.c
+++ b/hw/net/net_tx_pkt.c
@@ -553,7 +553,7 @@ static inline void net_tx_pkt_sendv(struct NetTxPkt *pkt,
     NetClientState *nc, const struct iovec *iov, int iov_cnt)
 {
     if (pkt->is_loopback) {
-        nc->info->receive_iov(nc, iov, iov_cnt);
+        qemu_receive_packet_iov(nc, iov, iov_cnt);
     } else {
         qemu_sendv_packet(nc, iov, iov_cnt);
     }
diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
index f3f18d8598..dcd3fc4948 100644
--- a/hw/net/pcnet.c
+++ b/hw/net/pcnet.c
@@ -1250,7 +1250,7 @@ txagain:
             if (BCR_SWSTYLE(s) == 1)
                 add_crc = !GET_FIELD(tmd.status, TMDS, NOFCS);
             s->looptest = add_crc ? PCNET_LOOPTEST_CRC : PCNET_LOOPTEST_NOCRC;
-            pcnet_receive(qemu_get_queue(s->nic), s->buffer, s->xmit_pos);
+            qemu_receive_packet(qemu_get_queue(s->nic), s->buffer, s->xmit_pos);
             s->looptest = 0;
         } else {
             if (s->nic) {
diff --git a/hw/net/rtl8139.c b/hw/net/rtl8139.c
index 4675ac878e..90b4fc63ce 100644
--- a/hw/net/rtl8139.c
+++ b/hw/net/rtl8139.c
@@ -1795,7 +1795,7 @@ static void rtl8139_transfer_frame(RTL8139State *s, uint8_t *buf, int size,
         }
 
         DPRINTF("+++ transmit loopback mode\n");
-        rtl8139_do_receive(qemu_get_queue(s->nic), buf, size, do_interrupt);
+        qemu_receive_packet(qemu_get_queue(s->nic), buf, size);
 
         if (iov) {
             g_free(buf2);
diff --git a/hw/net/sungem.c b/hw/net/sungem.c
index 33c3722df6..3684a4d733 100644
--- a/hw/net/sungem.c
+++ b/hw/net/sungem.c
@@ -306,7 +306,7 @@ static void sungem_send_packet(SunGEMState *s, const uint8_t *buf,
     NetClientState *nc = qemu_get_queue(s->nic);
 
     if (s->macregs[MAC_XIFCFG >> 2] & MAC_XIFCFG_LBCK) {
-        nc->info->receive(nc, buf, size);
+        qemu_receive_packet(nc, buf, size);
     } else {
         qemu_send_packet(nc, buf, size);
     }
diff --git a/hw/net/xen_nic.c b/hw/net/xen_nic.c
index 5c815b4f0c..8431808ea0 100644
--- a/hw/net/xen_nic.c
+++ b/hw/net/xen_nic.c
@@ -296,9 +296,8 @@ static int net_init(struct XenLegacyDevice *xendev)
     netdev->nic = qemu_new_nic(&net_xen_info, &netdev->conf,
                                "xen", NULL, netdev);
 
-    snprintf(qemu_get_queue(netdev->nic)->info_str,
-             sizeof(qemu_get_queue(netdev->nic)->info_str),
-             "nic: xenbus vif macaddr=%s", netdev->mac);
+    qemu_get_queue(netdev->nic)->info_str = g_strdup_printf(
+        "nic: xenbus vif macaddr=%s", netdev->mac);
 
     /* fill info */
     xenstore_write_be_int(&netdev->xendev, "feature-rx-copy", 1);
diff --git a/hw/rdma/vmw/pvrdma.h b/hw/rdma/vmw/pvrdma.h
index 1d36a76f1e..d08965d3e2 100644
--- a/hw/rdma/vmw/pvrdma.h
+++ b/hw/rdma/vmw/pvrdma.h
@@ -26,7 +26,6 @@
 #include "../rdma_backend_defs.h"
 #include "../rdma_rm_defs.h"
 
-#include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h"
 #include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_dev_api.h"
 #include "pvrdma_dev_ring.h"
 #include "qom/object.h"
@@ -64,10 +63,10 @@ typedef struct DSRInfo {
     union pvrdma_cmd_req *req;
     union pvrdma_cmd_resp *rsp;
 
-    struct pvrdma_ring *async_ring_state;
+    PvrdmaRingState *async_ring_state;
     PvrdmaRing async;
 
-    struct pvrdma_ring *cq_ring_state;
+    PvrdmaRingState *cq_ring_state;
     PvrdmaRing cq;
 } DSRInfo;
 
diff --git a/hw/rdma/vmw/pvrdma_cmd.c b/hw/rdma/vmw/pvrdma_cmd.c
index 692125ac26..f59879e257 100644
--- a/hw/rdma/vmw/pvrdma_cmd.c
+++ b/hw/rdma/vmw/pvrdma_cmd.c
@@ -262,7 +262,7 @@ static int create_cq_ring(PCIDevice *pci_dev , PvrdmaRing **ring,
     r = g_malloc(sizeof(*r));
     *ring = r;
 
-    r->ring_state = (struct pvrdma_ring *)
+    r->ring_state = (PvrdmaRingState *)
         rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
 
     if (!r->ring_state) {
@@ -398,7 +398,7 @@ static int create_qp_rings(PCIDevice *pci_dev, uint64_t pdir_dma,
     *rings = sr;
 
     /* Create send ring */
-    sr->ring_state = (struct pvrdma_ring *)
+    sr->ring_state = (PvrdmaRingState *)
         rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
     if (!sr->ring_state) {
         rdma_error_report("Failed to map to QP ring state");
@@ -639,7 +639,7 @@ static int create_srq_ring(PCIDevice *pci_dev, PvrdmaRing **ring,
     r = g_malloc(sizeof(*r));
     *ring = r;
 
-    r->ring_state = (struct pvrdma_ring *)
+    r->ring_state = (PvrdmaRingState *)
             rdma_pci_dma_map(pci_dev, tbl[0], TARGET_PAGE_SIZE);
     if (!r->ring_state) {
         rdma_error_report("Failed to map tp SRQ ring state");
diff --git a/hw/rdma/vmw/pvrdma_dev_ring.c b/hw/rdma/vmw/pvrdma_dev_ring.c
index f0bcde74b0..074ac59b84 100644
--- a/hw/rdma/vmw/pvrdma_dev_ring.c
+++ b/hw/rdma/vmw/pvrdma_dev_ring.c
@@ -22,11 +22,10 @@
 #include "trace.h"
 
 #include "../rdma_utils.h"
-#include "standard-headers/drivers/infiniband/hw/vmw_pvrdma/pvrdma_ring.h"
 #include "pvrdma_dev_ring.h"
 
 int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev,
-                     struct pvrdma_ring *ring_state, uint32_t max_elems,
+                     PvrdmaRingState *ring_state, uint32_t max_elems,
                      size_t elem_sz, dma_addr_t *tbl, uint32_t npages)
 {
     int i;
@@ -73,48 +72,54 @@ out:
 
 void *pvrdma_ring_next_elem_read(PvrdmaRing *ring)
 {
-    int e;
-    unsigned int idx = 0, offset;
+    unsigned int idx, offset;
+    const uint32_t tail = qatomic_read(&ring->ring_state->prod_tail);
+    const uint32_t head = qatomic_read(&ring->ring_state->cons_head);
 
-    e = pvrdma_idx_ring_has_data(ring->ring_state, ring->max_elems, &idx);
-    if (e <= 0) {
+    if (tail & ~((ring->max_elems << 1) - 1) ||
+        head & ~((ring->max_elems << 1) - 1) ||
+        tail == head) {
         trace_pvrdma_ring_next_elem_read_no_data(ring->name);
         return NULL;
     }
 
+    idx = head & (ring->max_elems - 1);
     offset = idx * ring->elem_sz;
     return ring->pages[offset / TARGET_PAGE_SIZE] + (offset % TARGET_PAGE_SIZE);
 }
 
 void pvrdma_ring_read_inc(PvrdmaRing *ring)
 {
-    pvrdma_idx_ring_inc(&ring->ring_state->cons_head, ring->max_elems);
+    uint32_t idx = qatomic_read(&ring->ring_state->cons_head);
+
+    idx = (idx + 1) & ((ring->max_elems << 1) - 1);
+    qatomic_set(&ring->ring_state->cons_head, idx);
 }
 
 void *pvrdma_ring_next_elem_write(PvrdmaRing *ring)
 {
-    int idx;
-    unsigned int offset, tail;
+    unsigned int idx, offset;
+    const uint32_t tail = qatomic_read(&ring->ring_state->prod_tail);
+    const uint32_t head = qatomic_read(&ring->ring_state->cons_head);
 
-    idx = pvrdma_idx_ring_has_space(ring->ring_state, ring->max_elems, &tail);
-    if (idx <= 0) {
+    if (tail & ~((ring->max_elems << 1) - 1) ||
+        head & ~((ring->max_elems << 1) - 1) ||
+        tail == (head ^ ring->max_elems)) {
         rdma_error_report("CQ is full");
         return NULL;
     }
 
-    idx = pvrdma_idx(&ring->ring_state->prod_tail, ring->max_elems);
-    if (idx < 0 || tail != idx) {
-        rdma_error_report("Invalid idx %d", idx);
-        return NULL;
-    }
-
+    idx = tail & (ring->max_elems - 1);
     offset = idx * ring->elem_sz;
     return ring->pages[offset / TARGET_PAGE_SIZE] + (offset % TARGET_PAGE_SIZE);
 }
 
 void pvrdma_ring_write_inc(PvrdmaRing *ring)
 {
-    pvrdma_idx_ring_inc(&ring->ring_state->prod_tail, ring->max_elems);
+    uint32_t idx = qatomic_read(&ring->ring_state->prod_tail);
+
+    idx = (idx + 1) & ((ring->max_elems << 1) - 1);
+    qatomic_set(&ring->ring_state->prod_tail, idx);
 }
 
 void pvrdma_ring_free(PvrdmaRing *ring)
diff --git a/hw/rdma/vmw/pvrdma_dev_ring.h b/hw/rdma/vmw/pvrdma_dev_ring.h
index 5f2a0cf9b9..d231588ce0 100644
--- a/hw/rdma/vmw/pvrdma_dev_ring.h
+++ b/hw/rdma/vmw/pvrdma_dev_ring.h
@@ -19,18 +19,23 @@
 
 #define MAX_RING_NAME_SZ 32
 
+typedef struct PvrdmaRingState {
+    int prod_tail; /* producer tail */
+    int cons_head; /* consumer head */
+} PvrdmaRingState;
+
 typedef struct PvrdmaRing {
     char name[MAX_RING_NAME_SZ];
     PCIDevice *dev;
     uint32_t max_elems;
     size_t elem_sz;
-    struct pvrdma_ring *ring_state; /* used only for unmap */
+    PvrdmaRingState *ring_state; /* used only for unmap */
     int npages;
     void **pages;
 } PvrdmaRing;
 
 int pvrdma_ring_init(PvrdmaRing *ring, const char *name, PCIDevice *dev,
-                     struct pvrdma_ring *ring_state, uint32_t max_elems,
+                     PvrdmaRingState *ring_state, uint32_t max_elems,
                      size_t elem_sz, dma_addr_t *tbl, uint32_t npages);
 void *pvrdma_ring_next_elem_read(PvrdmaRing *ring);
 void pvrdma_ring_read_inc(PvrdmaRing *ring);
diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c
index 8593570332..84ae8024fc 100644
--- a/hw/rdma/vmw/pvrdma_main.c
+++ b/hw/rdma/vmw/pvrdma_main.c
@@ -85,7 +85,7 @@ static void free_dev_ring(PCIDevice *pci_dev, PvrdmaRing *ring,
     rdma_pci_dma_unmap(pci_dev, ring_state, TARGET_PAGE_SIZE);
 }
 
-static int init_dev_ring(PvrdmaRing *ring, struct pvrdma_ring **ring_state,
+static int init_dev_ring(PvrdmaRing *ring, PvrdmaRingState **ring_state,
                          const char *name, PCIDevice *pci_dev,
                          dma_addr_t dir_addr, uint32_t num_pages)
 {
@@ -114,7 +114,7 @@ static int init_dev_ring(PvrdmaRing *ring, struct pvrdma_ring **ring_state,
     /* RX ring is the second */
     (*ring_state)++;
     rc = pvrdma_ring_init(ring, name, pci_dev,
-                          (struct pvrdma_ring *)*ring_state,
+                          (PvrdmaRingState *)*ring_state,
                           (num_pages - 1) * TARGET_PAGE_SIZE /
                           sizeof(struct pvrdma_cqne),
                           sizeof(struct pvrdma_cqne),
diff --git a/hw/virtio/virtio-net-pci.c b/hw/virtio/virtio-net-pci.c
index 292d13d278..aa0b3caecb 100644
--- a/hw/virtio/virtio-net-pci.c
+++ b/hw/virtio/virtio-net-pci.c
@@ -41,7 +41,8 @@ struct VirtIONetPCI {
 static Property virtio_net_properties[] = {
     DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags,
                     VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true),
-    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3),
+    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors,
+                       DEV_NVECTORS_UNSPECIFIED),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -50,6 +51,13 @@ static void virtio_net_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
     DeviceState *qdev = DEVICE(vpci_dev);
     VirtIONetPCI *dev = VIRTIO_NET_PCI(vpci_dev);
     DeviceState *vdev = DEVICE(&dev->vdev);
+    VirtIONet *net = VIRTIO_NET(vdev);
+
+    if (vpci_dev->nvectors == DEV_NVECTORS_UNSPECIFIED) {
+        vpci_dev->nvectors = 2 * MAX(net->nic_conf.peers.queues, 1)
+            + 1 /* Config interrupt */
+            + 1 /* Control vq */;
+    }
 
     virtio_net_set_netclient_name(&dev->vdev, qdev->id,
                                   object_get_typename(OBJECT(qdev)));