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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

1 files changed, 135 insertions, 38 deletions

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index a902838f9fcc..8e0ffa800a71 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -73,6 +73,21 @@ struct xsk_nl_info {
 	int fd;
 };
 
+/* Up until and including Linux 5.3 */
+struct xdp_ring_offset_v1 {
+	__u64 producer;
+	__u64 consumer;
+	__u64 desc;
+};
+
+/* Up until and including Linux 5.3 */
+struct xdp_mmap_offsets_v1 {
+	struct xdp_ring_offset_v1 rx;
+	struct xdp_ring_offset_v1 tx;
+	struct xdp_ring_offset_v1 fr;
+	struct xdp_ring_offset_v1 cr;
+};
+
 int xsk_umem__fd(const struct xsk_umem *umem)
 {
 	return umem ? umem->fd : -EINVAL;
@@ -133,6 +148,58 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 	return 0;
 }
 
+static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off)
+{
+	struct xdp_mmap_offsets_v1 off_v1;
+
+	/* getsockopt on a kernel <= 5.3 has no flags fields.
+	 * Copy over the offsets to the correct places in the >=5.4 format
+	 * and put the flags where they would have been on that kernel.
+	 */
+	memcpy(&off_v1, off, sizeof(off_v1));
+
+	off->rx.producer = off_v1.rx.producer;
+	off->rx.consumer = off_v1.rx.consumer;
+	off->rx.desc = off_v1.rx.desc;
+	off->rx.flags = off_v1.rx.consumer + sizeof(__u32);
+
+	off->tx.producer = off_v1.tx.producer;
+	off->tx.consumer = off_v1.tx.consumer;
+	off->tx.desc = off_v1.tx.desc;
+	off->tx.flags = off_v1.tx.consumer + sizeof(__u32);
+
+	off->fr.producer = off_v1.fr.producer;
+	off->fr.consumer = off_v1.fr.consumer;
+	off->fr.desc = off_v1.fr.desc;
+	off->fr.flags = off_v1.fr.consumer + sizeof(__u32);
+
+	off->cr.producer = off_v1.cr.producer;
+	off->cr.consumer = off_v1.cr.consumer;
+	off->cr.desc = off_v1.cr.desc;
+	off->cr.flags = off_v1.cr.consumer + sizeof(__u32);
+}
+
+static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
+{
+	socklen_t optlen;
+	int err;
+
+	optlen = sizeof(*off);
+	err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen);
+	if (err)
+		return err;
+
+	if (optlen == sizeof(*off))
+		return 0;
+
+	if (optlen == sizeof(struct xdp_mmap_offsets_v1)) {
+		xsk_mmap_offsets_v1(off);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
 int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -141,7 +208,6 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	struct xdp_mmap_offsets off;
 	struct xdp_umem_reg mr;
 	struct xsk_umem *umem;
-	socklen_t optlen;
 	void *map;
 	int err;
 
@@ -163,6 +229,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	umem->umem_area = umem_area;
 	xsk_set_umem_config(&umem->config, usr_config);
 
+	memset(&mr, 0, sizeof(mr));
 	mr.addr = (uintptr_t)umem_area;
 	mr.len = size;
 	mr.chunk_size = umem->config.frame_size;
@@ -189,8 +256,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 		goto out_socket;
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(umem->fd, &off);
 	if (err) {
 		err = -errno;
 		goto out_socket;
@@ -273,33 +339,55 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	/* This is the C-program:
 	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
 	 * {
-	 *     int index = ctx->rx_queue_index;
+	 *     int ret, index = ctx->rx_queue_index;
 	 *
 	 *     // A set entry here means that the correspnding queue_id
 	 *     // has an active AF_XDP socket bound to it.
+	 *     ret = bpf_redirect_map(&xsks_map, index, XDP_PASS);
+	 *     if (ret > 0)
+	 *         return ret;
+	 *
+	 *     // Fallback for pre-5.3 kernels, not supporting default
+	 *     // action in the flags parameter.
 	 *     if (bpf_map_lookup_elem(&xsks_map, &index))
 	 *         return bpf_redirect_map(&xsks_map, index, 0);
-	 *
 	 *     return XDP_PASS;
 	 * }
 	 */
 	struct bpf_insn prog[] = {
-		/* r1 = *(u32 *)(r1 + 16) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 16),
-		/* *(u32 *)(r10 - 4) = r1 */
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4),
+		/* r2 = *(u32 *)(r1 + 16) */
+		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
+		/* *(u32 *)(r10 - 4) = r2 */
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4),
+		/* r1 = xskmap[] */
+		BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
+		/* r3 = XDP_PASS */
+		BPF_MOV64_IMM(BPF_REG_3, 2),
+		/* call bpf_redirect_map */
+		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+		/* if w0 != 0 goto pc+13 */
+		BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13),
+		/* r2 = r10 */
 		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		/* r2 += -4 */
 		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+		/* r1 = xskmap[] */
 		BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
+		/* call bpf_map_lookup_elem */
 		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+		/* r1 = r0 */
 		BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-		BPF_MOV32_IMM(BPF_REG_0, 2),
-		/* if r1 == 0 goto +5 */
+		/* r0 = XDP_PASS */
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		/* if r1 == 0 goto pc+5 */
 		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
 		/* r2 = *(u32 *)(r10 - 4) */
-		BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
 		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4),
-		BPF_MOV32_IMM(BPF_REG_3, 0),
+		/* r1 = xskmap[] */
+		BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd),
+		/* r3 = 0 */
+		BPF_MOV64_IMM(BPF_REG_3, 0),
+		/* call bpf_redirect_map */
 		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
 		/* The jumps are to this instruction */
 		BPF_EXIT_INSN(),
@@ -310,7 +398,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 				   "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
 				   log_buf_size);
 	if (prog_fd < 0) {
-		pr_warning("BPF log buffer:\n%s", log_buf);
+		pr_warn("BPF log buffer:\n%s", log_buf);
 		return prog_fd;
 	}
 
@@ -343,13 +431,18 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		goto out;
 	}
 
-	if (err || channels.max_combined == 0)
+	if (err) {
 		/* If the device says it has no channels, then all traffic
 		 * is sent to a single stream, so max queues = 1.
 		 */
 		ret = 1;
-	else
-		ret = channels.max_combined;
+	} else {
+		/* Take the max of rx, tx, combined. Drivers return
+		 * the number of channels in different ways.
+		 */
+		ret = max(channels.max_rx, channels.max_tx);
+		ret = max(ret, (int)channels.max_combined);
+	}
 
 out:
 	close(fd);
@@ -465,6 +558,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	} else {
 		xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+		if (xsk->prog_fd < 0)
+			return -errno;
 		err = xsk_lookup_bpf_maps(xsk);
 		if (err) {
 			close(xsk->prog_fd);
@@ -472,7 +567,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	}
 
-	err = xsk_set_bpf_maps(xsk);
+	if (xsk->rx)
+		err = xsk_set_bpf_maps(xsk);
 	if (err) {
 		xsk_delete_bpf_maps(xsk);
 		close(xsk->prog_fd);
@@ -491,21 +587,26 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
-	socklen_t optlen;
 	int err;
 
-	if (!umem || !xsk_ptr || !rx || !tx)
+	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
 
-	if (umem->refcount) {
-		pr_warning("Error: shared umems not supported by libbpf.\n");
-		return -EBUSY;
-	}
-
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
 		return -ENOMEM;
 
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_xsk_alloc;
+
+	if (umem->refcount &&
+	    !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
+		pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n");
+		err = -EBUSY;
+		goto out_xsk_alloc;
+	}
+
 	if (umem->refcount++ > 0) {
 		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
 		if (xsk->fd < 0) {
@@ -527,10 +628,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
 	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
-	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
-	if (err)
-		goto out_socket;
-
 	if (rx) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
 				 &xsk->config.rx_size,
@@ -550,8 +647,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		}
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
 	if (err) {
 		err = -errno;
 		goto out_socket;
@@ -599,7 +695,12 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	sxdp.sxdp_family = PF_XDP;
 	sxdp.sxdp_ifindex = xsk->ifindex;
 	sxdp.sxdp_queue_id = xsk->queue_id;
-	sxdp.sxdp_flags = xsk->config.bind_flags;
+	if (umem->refcount > 1) {
+		sxdp.sxdp_flags = XDP_SHARED_UMEM;
+		sxdp.sxdp_shared_umem_fd = umem->fd;
+	} else {
+		sxdp.sxdp_flags = xsk->config.bind_flags;
+	}
 
 	err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp));
 	if (err) {
@@ -637,7 +738,6 @@ out_xsk_alloc:
 int xsk_umem__delete(struct xsk_umem *umem)
 {
 	struct xdp_mmap_offsets off;
-	socklen_t optlen;
 	int err;
 
 	if (!umem)
@@ -646,8 +746,7 @@ int xsk_umem__delete(struct xsk_umem *umem)
 	if (umem->refcount)
 		return -EBUSY;
 
-	optlen = sizeof(off);
-	err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(umem->fd, &off);
 	if (!err) {
 		munmap(umem->fill->ring - off.fr.desc,
 		       off.fr.desc + umem->config.fill_size * sizeof(__u64));
@@ -665,7 +764,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 {
 	size_t desc_sz = sizeof(struct xdp_desc);
 	struct xdp_mmap_offsets off;
-	socklen_t optlen;
 	int err;
 
 	if (!xsk)
@@ -676,8 +774,7 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 		close(xsk->prog_fd);
 	}
 
-	optlen = sizeof(off);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
 	if (!err) {
 		if (xsk->rx) {
 			munmap(xsk->rx->ring - off.rx.desc,