Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix endless loop in nf_tables, from Phil Sutter.

 2) Fix cross namespace ip6_gre tunnel hash list corruption, from
    Olivier Matz.

 3) Don't be too strict in phy_start_aneg() otherwise we might not allow
    restarting auto negotiation. From Heiner Kallweit.

 4) Fix various KMSAN uninitialized value cases in tipc, from Ying Xue.

 5) Memory leak in act_tunnel_key, from Davide Caratti.

 6) Handle chip errata of mv88e6390 PHY, from Andrew Lunn.

 7) Remove linear SKB assumption in fou/fou6, from Eric Dumazet.

 8) Missing udplite rehash callbacks, from Alexey Kodanev.

 9) Log dirty pages properly in vhost, from Jason Wang.

10) Use consume_skb() in neigh_probe() as this is a normal free not a
    drop, from Yang Wei. Likewise in macvlan_process_broadcast().

11) Missing device_del() in mdiobus_register() error paths, from Thomas
    Petazzoni.

12) Fix checksum handling of short packets in mlx5, from Cong Wang.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (96 commits)
  bpf: in __bpf_redirect_no_mac pull mac only if present
  virtio_net: bulk free tx skbs
  net: phy: phy driver features are mandatory
  isdn: avm: Fix string plus integer warning from Clang
  net/mlx5e: Fix cb_ident duplicate in indirect block register
  net/mlx5e: Fix wrong (zero) TX drop counter indication for representor
  net/mlx5e: Fix wrong error code return on FEC query failure
  net/mlx5e: Force CHECKSUM_UNNECESSARY for short ethernet frames
  tools: bpftool: Cleanup license mess
  bpf: fix inner map masking to prevent oob under speculation
  bpf: pull in pkt_sched.h header for tooling to fix bpftool build
  selftests: forwarding: Add a test case for externally learned FDB entries
  selftests: mlxsw: Test FDB offload indication
  mlxsw: spectrum_switchdev: Do not treat static FDB entries as sticky
  net: bridge: Mark FDB entries that were added by user as such
  mlxsw: spectrum_fid: Update dummy FID index
  mlxsw: pci: Return error on PCI reset timeout
  mlxsw: pci: Increase PCI SW reset timeout
  mlxsw: pci: Ring CQ's doorbell before RDQ's
  MAINTAINERS: update email addresses of liquidio driver maintainers
  ...

3 files changed, 87 insertions, 16 deletions

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 36f3d0f49e60..bca86bf7189f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1236,7 +1236,8 @@ static void handle_rx(struct vhost_net *net)
 		if (nvq->done_idx > VHOST_NET_BATCH)
 			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
-			vhost_log_write(vq, vq_log, log, vhost_len);
+			vhost_log_write(vq, vq_log, log, vhost_len,
+					vq->iov, in);
 		total_len += vhost_len;
 		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index bac939af8dbb..15a216cdd507 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1737,13 +1737,87 @@ static int log_write(void __user *log_base,
 	return r;
 }
 
+static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
+{
+	struct vhost_umem *umem = vq->umem;
+	struct vhost_umem_node *u;
+	u64 start, end, l, min;
+	int r;
+	bool hit = false;
+
+	while (len) {
+		min = len;
+		/* More than one GPAs can be mapped into a single HVA. So
+		 * iterate all possible umems here to be safe.
+		 */
+		list_for_each_entry(u, &umem->umem_list, link) {
+			if (u->userspace_addr > hva - 1 + len ||
+			    u->userspace_addr - 1 + u->size < hva)
+				continue;
+			start = max(u->userspace_addr, hva);
+			end = min(u->userspace_addr - 1 + u->size,
+				  hva - 1 + len);
+			l = end - start + 1;
+			r = log_write(vq->log_base,
+				      u->start + start - u->userspace_addr,
+				      l);
+			if (r < 0)
+				return r;
+			hit = true;
+			min = min(l, min);
+		}
+
+		if (!hit)
+			return -EFAULT;
+
+		len -= min;
+		hva += min;
+	}
+
+	return 0;
+}
+
+static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
+{
+	struct iovec iov[64];
+	int i, ret;
+
+	if (!vq->iotlb)
+		return log_write(vq->log_base, vq->log_addr + used_offset, len);
+
+	ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
+			     len, iov, 64, VHOST_ACCESS_WO);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ret; i++) {
+		ret = log_write_hva(vq,	(uintptr_t)iov[i].iov_base,
+				    iov[i].iov_len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len)
+		    unsigned int log_num, u64 len, struct iovec *iov, int count)
 {
 	int i, r;
 
 	/* Make sure data written is seen before log. */
 	smp_wmb();
+
+	if (vq->iotlb) {
+		for (i = 0; i < count; i++) {
+			r = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
+					  iov[i].iov_len);
+			if (r < 0)
+				return r;
+		}
+		return 0;
+	}
+
 	for (i = 0; i < log_num; ++i) {
 		u64 l = min(log[i].len, len);
 		r = log_write(vq->log_base, log[i].addr, l);
@@ -1773,9 +1847,8 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 		smp_wmb();
 		/* Log used flag write. */
 		used = &vq->used->flags;
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof vq->used->flags);
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof vq->used->flags);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -1793,9 +1866,8 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 		smp_wmb();
 		/* Log avail event write */
 		used = vhost_avail_event(vq);
-		log_write(vq->log_base, vq->log_addr +
-			  (used - (void __user *)vq->used),
-			  sizeof *vhost_avail_event(vq));
+		log_used(vq, (used - (void __user *)vq->used),
+			 sizeof *vhost_avail_event(vq));
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
@@ -2195,10 +2267,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 		/* Make sure data is seen before log. */
 		smp_wmb();
 		/* Log used ring entry write. */
-		log_write(vq->log_base,
-			  vq->log_addr +
-			   ((void __user *)used - (void __user *)vq->used),
-			  count * sizeof *used);
+		log_used(vq, ((void __user *)used - (void __user *)vq->used),
+			 count * sizeof *used);
 	}
 	old = vq->last_used_idx;
 	new = (vq->last_used_idx += count);
@@ -2240,9 +2310,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		/* Make sure used idx is seen before log. */
 		smp_wmb();
 		/* Log used index update. */
-		log_write(vq->log_base,
-			  vq->log_addr + offsetof(struct vring_used, idx),
-			  sizeof vq->used->idx);
+		log_used(vq, offsetof(struct vring_used, idx),
+			 sizeof vq->used->idx);
 		if (vq->log_ctx)
 			eventfd_signal(vq->log_ctx, 1);
 	}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 466ef7542291..1b675dad5e05 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -205,7 +205,8 @@ bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
 bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
-		    unsigned int log_num, u64 len);
+		    unsigned int log_num, u64 len,
+		    struct iovec *iov, int count);
 int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
 
 struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);