Merge tag 'net-pull-request' of https://github.com/jasowang/qemu into staging

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmXwPUAACgkQ7wSWWzmN
# YhFnIwgAgctDniJwlRxXB01eVlzXz7IulHnpSby07XEJxENSpGB8ufaeE4eK5gJy
# NVK6C2+1EU2vRxm4oIdcvtN4C4/jtRbYYjiSTx7eE4FmSkqshSnR5XCV72LDqG3i
# WbzInjMvYfysmcMXLfrWgxOnVew9WqEzlpEWlc7FfNKnkzBVf+JDztfqCUx0XM7H
# qefw4ImjqQw993QxJpipXC7aEGUyouB0RIBB71FkCa9ihlh9x7W68evbOI/jTn5q
# HWuStgS02sKHjRFliMbdbMY77FNUz4Yroo/GKSvGt64atxkQSJqPNAV+/9n18LNy
# QAH5eK6cXFPOIAaYpADU5kHDVVAFiw==
# =iBdx
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 12 Mar 2024 11:32:16 GMT
# gpg:                using RSA key 215D46F48246689EC77F3562EF04965B398D6211
# 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

* tag 'net-pull-request' of https://github.com/jasowang/qemu:
  ebpf: Updated eBPF program and skeleton.
  qmp: Added new command to retrieve eBPF blob.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added eBPF initialization by fds.
  ebpf: Added eBPF map update through mmap.
  Avoid unaligned fetch in ladr_match()
  e1000e: fix link state on resume
  igb: fix link state on resume

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

6 files changed, 63 insertions, 108 deletions

diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index e324c02..3ae2a18 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -123,14 +123,6 @@ e1000e_intmgr_timer_resume(E1000IntrDelayTimer *timer)
     }
 }
 
-static void
-e1000e_intmgr_timer_pause(E1000IntrDelayTimer *timer)
-{
-    if (timer->running) {
-        timer_del(timer->timer);
-    }
-}
-
 static inline void
 e1000e_intrmgr_stop_timer(E1000IntrDelayTimer *timer)
 {
@@ -399,24 +391,6 @@ e1000e_intrmgr_resume(E1000ECore *core)
 }
 
 static void
-e1000e_intrmgr_pause(E1000ECore *core)
-{
-    int i;
-
-    e1000e_intmgr_timer_pause(&core->radv);
-    e1000e_intmgr_timer_pause(&core->rdtr);
-    e1000e_intmgr_timer_pause(&core->raid);
-    e1000e_intmgr_timer_pause(&core->tidv);
-    e1000e_intmgr_timer_pause(&core->tadv);
-
-    e1000e_intmgr_timer_pause(&core->itr);
-
-    for (i = 0; i < E1000E_MSIX_VEC_NUM; i++) {
-        e1000e_intmgr_timer_pause(&core->eitr[i]);
-    }
-}
-
-static void
 e1000e_intrmgr_reset(E1000ECore *core)
 {
     int i;
@@ -3334,12 +3308,6 @@ e1000e_core_read(E1000ECore *core, hwaddr addr, unsigned size)
     return 0;
 }
 
-static inline void
-e1000e_autoneg_pause(E1000ECore *core)
-{
-    timer_del(core->autoneg_timer);
-}
-
 static void
 e1000e_autoneg_resume(E1000ECore *core)
 {
@@ -3351,22 +3319,6 @@ e1000e_autoneg_resume(E1000ECore *core)
     }
 }
 
-static void
-e1000e_vm_state_change(void *opaque, bool running, RunState state)
-{
-    E1000ECore *core = opaque;
-
-    if (running) {
-        trace_e1000e_vm_state_running();
-        e1000e_intrmgr_resume(core);
-        e1000e_autoneg_resume(core);
-    } else {
-        trace_e1000e_vm_state_stopped();
-        e1000e_autoneg_pause(core);
-        e1000e_intrmgr_pause(core);
-    }
-}
-
 void
 e1000e_core_pci_realize(E1000ECore     *core,
                         const uint16_t *eeprom_templ,
@@ -3379,9 +3331,6 @@ e1000e_core_pci_realize(E1000ECore     *core,
                                        e1000e_autoneg_timer, core);
     e1000e_intrmgr_pci_realize(core);
 
-    core->vmstate =
-        qemu_add_vm_change_state_handler(e1000e_vm_state_change, core);
-
     for (i = 0; i < E1000E_NUM_QUEUES; i++) {
         net_tx_pkt_init(&core->tx[i].tx_pkt, E1000E_MAX_TX_FRAGS);
     }
@@ -3405,8 +3354,6 @@ e1000e_core_pci_uninit(E1000ECore *core)
 
     e1000e_intrmgr_pci_unint(core);
 
-    qemu_del_vm_change_state_handler(core->vmstate);
-
     for (i = 0; i < E1000E_NUM_QUEUES; i++) {
         net_tx_pkt_uninit(core->tx[i].tx_pkt);
     }
@@ -3576,5 +3523,12 @@ e1000e_core_post_load(E1000ECore *core)
      */
     nc->link_down = (core->mac[STATUS] & E1000_STATUS_LU) == 0;
 
+    /*
+     * we need to restart intrmgr timers, as an older version of
+     * QEMU can have stopped them before migration
+     */
+    e1000e_intrmgr_resume(core);
+    e1000e_autoneg_resume(core);
+
     return 0;
 }
diff --git a/hw/net/e1000e_core.h b/hw/net/e1000e_core.h
index 66b025c..01510ca 100644
--- a/hw/net/e1000e_core.h
+++ b/hw/net/e1000e_core.h
@@ -98,8 +98,6 @@ struct E1000Core {
 
     E1000IntrDelayTimer eitr[E1000E_MSIX_VEC_NUM];
 
-    VMChangeStateEntry *vmstate;
-
     uint32_t itr_guest_value;
     uint32_t eitr_guest_value[E1000E_MSIX_VEC_NUM];
 
diff --git a/hw/net/igb_core.c b/hw/net/igb_core.c
index 2a7a11a..bcd5f6c 100644
--- a/hw/net/igb_core.c
+++ b/hw/net/igb_core.c
@@ -161,14 +161,6 @@ igb_intmgr_timer_resume(IGBIntrDelayTimer *timer)
 }
 
 static void
-igb_intmgr_timer_pause(IGBIntrDelayTimer *timer)
-{
-    if (timer->running) {
-        timer_del(timer->timer);
-    }
-}
-
-static void
 igb_intrmgr_on_msix_throttling_timer(void *opaque)
 {
     IGBIntrDelayTimer *timer = opaque;
@@ -213,16 +205,6 @@ igb_intrmgr_resume(IGBCore *core)
 }
 
 static void
-igb_intrmgr_pause(IGBCore *core)
-{
-    int i;
-
-    for (i = 0; i < IGB_INTR_NUM; i++) {
-        igb_intmgr_timer_pause(&core->eitr[i]);
-    }
-}
-
-static void
 igb_intrmgr_reset(IGBCore *core)
 {
     int i;
@@ -4290,12 +4272,6 @@ igb_core_read(IGBCore *core, hwaddr addr, unsigned size)
     return 0;
 }
 
-static inline void
-igb_autoneg_pause(IGBCore *core)
-{
-    timer_del(core->autoneg_timer);
-}
-
 static void
 igb_autoneg_resume(IGBCore *core)
 {
@@ -4307,22 +4283,6 @@ igb_autoneg_resume(IGBCore *core)
     }
 }
 
-static void
-igb_vm_state_change(void *opaque, bool running, RunState state)
-{
-    IGBCore *core = opaque;
-
-    if (running) {
-        trace_e1000e_vm_state_running();
-        igb_intrmgr_resume(core);
-        igb_autoneg_resume(core);
-    } else {
-        trace_e1000e_vm_state_stopped();
-        igb_autoneg_pause(core);
-        igb_intrmgr_pause(core);
-    }
-}
-
 void
 igb_core_pci_realize(IGBCore        *core,
                      const uint16_t *eeprom_templ,
@@ -4335,8 +4295,6 @@ igb_core_pci_realize(IGBCore        *core,
                                        igb_autoneg_timer, core);
     igb_intrmgr_pci_realize(core);
 
-    core->vmstate = qemu_add_vm_change_state_handler(igb_vm_state_change, core);
-
     for (i = 0; i < IGB_NUM_QUEUES; i++) {
         net_tx_pkt_init(&core->tx[i].tx_pkt, E1000E_MAX_TX_FRAGS);
     }
@@ -4360,8 +4318,6 @@ igb_core_pci_uninit(IGBCore *core)
 
     igb_intrmgr_pci_unint(core);
 
-    qemu_del_vm_change_state_handler(core->vmstate);
-
     for (i = 0; i < IGB_NUM_QUEUES; i++) {
         net_tx_pkt_uninit(core->tx[i].tx_pkt);
     }
@@ -4586,5 +4542,12 @@ igb_core_post_load(IGBCore *core)
      */
     nc->link_down = (core->mac[STATUS] & E1000_STATUS_LU) == 0;
 
+    /*
+     * we need to restart intrmgr timers, as an older version of
+     * QEMU can have stopped them before migration
+     */
+    igb_intrmgr_resume(core);
+    igb_autoneg_resume(core);
+
     return 0;
 }
diff --git a/hw/net/igb_core.h b/hw/net/igb_core.h
index bf8c46f..d70b54e 100644
--- a/hw/net/igb_core.h
+++ b/hw/net/igb_core.h
@@ -90,8 +90,6 @@ struct IGBCore {
 
     IGBIntrDelayTimer eitr[IGB_INTR_NUM];
 
-    VMChangeStateEntry *vmstate;
-
     uint32_t eitr_guest_value[IGB_INTR_NUM];
 
     uint8_t permanent_mac[ETH_ALEN];
diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
index 494eab8..ad675ab 100644
--- a/hw/net/pcnet.c
+++ b/hw/net/pcnet.c
@@ -632,7 +632,7 @@ static inline int ladr_match(PCNetState *s, const uint8_t *buf, int size)
 {
     struct qemu_ether_header *hdr = (void *)buf;
     if ((*(hdr->ether_dhost)&0x01) &&
-        ((uint64_t *)&s->csr[8])[0] != 0LL) {
+        (s->csr[8] | s->csr[9] | s->csr[10] | s->csr[11]) != 0) {
         uint8_t ladr[8] = {
             s->csr[8] & 0xff, s->csr[8] >> 8,
             s->csr[9] & 0xff, s->csr[9] >> 8,
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index a3c711b..403a693 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1328,14 +1329,53 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
     virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-    if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-        /* backend doesn't support steering ebpf */
-        return false;
+    int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+    int ret = true;
+    int i = 0;
+
+    ERRP_GUARD();
+
+    if (n->nr_ebpf_rss_fds != EBPF_RSS_MAX_FDS) {
+        error_setg(errp,
+                  "Expected %d file descriptors but got %d",
+                  EBPF_RSS_MAX_FDS, n->nr_ebpf_rss_fds);
+       return false;
+   }
+
+    for (i = 0; i < n->nr_ebpf_rss_fds; i++) {
+        fds[i] = monitor_fd_param(monitor_cur(), n->ebpf_rss_fds[i], errp);
+        if (*errp) {
+            ret = false;
+            goto exit;
+        }
+    }
+
+    ret = ebpf_rss_load_fds(&n->ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+    if (!ret || *errp) {
+        for (i = 0; i < n->nr_ebpf_rss_fds && fds[i] != -1; i++) {
+            close(fds[i]);
+        }
     }
 
-    return ebpf_rss_load(&n->ebpf_rss);
+    return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+    bool ret = false;
+
+    if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+        if (!(n->ebpf_rss_fds
+                && virtio_net_load_ebpf_fds(n, errp))) {
+            ret = ebpf_rss_load(&n->ebpf_rss);
+        }
+    }
+
+    return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3768,7 +3808,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     net_rx_pkt_init(&n->rx_pkt);
 
     if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-        virtio_net_load_ebpf(n);
+        virtio_net_load_ebpf(n, errp);
     }
 }
 
@@ -3930,6 +3970,8 @@ static Property virtio_net_properties[] = {
                     VIRTIO_NET_F_RSS, false),
     DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
                     VIRTIO_NET_F_HASH_REPORT, false),
+    DEFINE_PROP_ARRAY("ebpf-rss-fds", VirtIONet, nr_ebpf_rss_fds,
+                      ebpf_rss_fds, qdev_prop_string, char*),
     DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
                     VIRTIO_NET_F_RSC_EXT, false),
     DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,