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

Pull networking fixes from David Miller:

 1) Fix cfg80211 deadlock, from Johannes Berg.

 2) RXRPC fails to send norigications, from David Howells.

 3) MPTCP RM_ADDR parsing has an off by one pointer error, fix from
    Geliang Tang.

 4) Fix crash when using MSG_PEEK with sockmap, from Anny Hu.

 5) The ucc_geth driver needs __netdev_watchdog_up exported, from
    Valentin Longchamp.

 6) Fix hashtable memory leak in dccp, from Wang Hai.

 7) Fix how nexthops are marked as FDB nexthops, from David Ahern.

 8) Fix mptcp races between shutdown and recvmsg, from Paolo Abeni.

 9) Fix crashes in tipc_disc_rcv(), from Tuong Lien.

10) Fix link speed reporting in iavf driver, from Brett Creeley.

11) When a channel is used for XSK and then reused again later for XSK,
    we forget to clear out the relevant data structures in mlx5 which
    causes all kinds of problems. Fix from Maxim Mikityanskiy.

12) Fix memory leak in genetlink, from Cong Wang.

13) Disallow sockmap attachments to UDP sockets, it simply won't work.
    From Lorenz Bauer.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (83 commits)
  net: ethernet: ti: ale: fix allmulti for nu type ale
  net: ethernet: ti: am65-cpsw-nuss: fix ale parameters init
  net: atm: Remove the error message according to the atomic context
  bpf: Undo internal BPF_PROBE_MEM in BPF insns dump
  libbpf: Support pre-initializing .bss global variables
  tools/bpftool: Fix skeleton codegen
  bpf: Fix memlock accounting for sock_hash
  bpf: sockmap: Don't attach programs to UDP sockets
  bpf: tcp: Recv() should return 0 when the peer socket is closed
  ibmvnic: Flush existing work items before device removal
  genetlink: clean up family attributes allocations
  net: ipa: header pad field only valid for AP->modem endpoint
  net: ipa: program upper nibbles of sequencer type
  net: ipa: fix modem LAN RX endpoint id
  net: ipa: program metadata mask differently
  ionic: add pcie_print_link_status
  rxrpc: Fix race between incoming ACK parser and retransmitter
  net/mlx5: E-Switch, Fix some error pointer dereferences
  net/mlx5: Don't fail driver on failure to create debugfs
  net/mlx5e: CT: Fix ipv6 nat header rewrite actions
  ...

1 files changed, 63 insertions, 7 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27716e4932bc..810cc164f795 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1742,14 +1742,48 @@ int tcp_mmap(struct file *file, struct socket *sock,
 }
 EXPORT_SYMBOL(tcp_mmap);
 
+static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma,
+					struct page **pages,
+					unsigned long pages_to_map,
+					unsigned long *insert_addr,
+					u32 *length_with_pending,
+					u32 *seq,
+					struct tcp_zerocopy_receive *zc)
+{
+	unsigned long pages_remaining = pages_to_map;
+	int bytes_mapped;
+	int ret;
+
+	ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining);
+	bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining);
+	/* Even if vm_insert_pages fails, it may have partially succeeded in
+	 * mapping (some but not all of the pages).
+	 */
+	*seq += bytes_mapped;
+	*insert_addr += bytes_mapped;
+	if (ret) {
+		/* But if vm_insert_pages did fail, we have to unroll some state
+		 * we speculatively touched before.
+		 */
+		const int bytes_not_mapped = PAGE_SIZE * pages_remaining;
+		*length_with_pending -= bytes_not_mapped;
+		zc->recv_skip_hint += bytes_not_mapped;
+	}
+	return ret;
+}
+
 static int tcp_zerocopy_receive(struct sock *sk,
 				struct tcp_zerocopy_receive *zc)
 {
 	unsigned long address = (unsigned long)zc->address;
 	u32 length = 0, seq, offset, zap_len;
+	#define PAGE_BATCH_SIZE 8
+	struct page *pages[PAGE_BATCH_SIZE];
 	const skb_frag_t *frags = NULL;
 	struct vm_area_struct *vma;
 	struct sk_buff *skb = NULL;
+	unsigned long pg_idx = 0;
+	unsigned long curr_addr;
 	struct tcp_sock *tp;
 	int inq;
 	int ret;
@@ -1762,6 +1796,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	sock_rps_record_flow(sk);
 
+	tp = tcp_sk(sk);
+
 	mmap_read_lock(current->mm);
 
 	vma = find_vma(current->mm, address);
@@ -1771,7 +1807,6 @@ static int tcp_zerocopy_receive(struct sock *sk,
 	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
-	tp = tcp_sk(sk);
 	seq = tp->copied_seq;
 	inq = tcp_inq(sk);
 	zc->length = min_t(u32, zc->length, inq);
@@ -1783,8 +1818,20 @@ static int tcp_zerocopy_receive(struct sock *sk,
 		zc->recv_skip_hint = zc->length;
 	}
 	ret = 0;
+	curr_addr = address;
 	while (length + PAGE_SIZE <= zc->length) {
 		if (zc->recv_skip_hint < PAGE_SIZE) {
+			/* If we're here, finish the current batch. */
+			if (pg_idx) {
+				ret = tcp_zerocopy_vm_insert_batch(vma, pages,
+								   pg_idx,
+								   &curr_addr,
+								   &length,
+								   &seq, zc);
+				if (ret)
+					goto out;
+				pg_idx = 0;
+			}
 			if (skb) {
 				if (zc->recv_skip_hint > 0)
 					break;
@@ -1793,7 +1840,6 @@ static int tcp_zerocopy_receive(struct sock *sk,
 			} else {
 				skb = tcp_recv_skb(sk, seq, &offset);
 			}
-
 			zc->recv_skip_hint = skb->len - offset;
 			offset -= skb_headlen(skb);
 			if ((int)offset < 0 || skb_has_frag_list(skb))
@@ -1817,14 +1863,24 @@ static int tcp_zerocopy_receive(struct sock *sk,
 			zc->recv_skip_hint -= remaining;
 			break;
 		}
-		ret = vm_insert_page(vma, address + length,
-				     skb_frag_page(frags));
-		if (ret)
-			break;
+		pages[pg_idx] = skb_frag_page(frags);
+		pg_idx++;
 		length += PAGE_SIZE;
-		seq += PAGE_SIZE;
 		zc->recv_skip_hint -= PAGE_SIZE;
 		frags++;
+		if (pg_idx == PAGE_BATCH_SIZE) {
+			ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
+							   &curr_addr, &length,
+							   &seq, zc);
+			if (ret)
+				goto out;
+			pg_idx = 0;
+		}
+	}
+	if (pg_idx) {
+		ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
+						   &curr_addr, &length, &seq,
+						   zc);
 	}
 out:
 	mmap_read_unlock(current->mm);