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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-04-28

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Introduce BPF socket local storage map so that BPF programs can store
   private data they associate with a socket (instead of e.g. separate hash
   table), from Martin.

2) Add support for bpftool to dump BTF types. This is done through a new
   `bpftool btf dump` sub-command, from Andrii.

3) Enable BPF-based flow dissector for skb-less eth_get_headlen() calls which
   was currently not supported since skb was used to lookup netns, from Stanislav.

4) Add an opt-in interface for tracepoints to expose a writable context
   for attached BPF programs, used here for NBD sockets, from Matt.

5) BPF xadd related arm64 JIT fixes and scalability improvements, from Daniel.

6) Change the skb->protocol for bpf_skb_adjust_room() helper in order to
   support tunnels such as sit. Add selftests as well, from Willem.

7) Various smaller misc fixes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

15 files changed, 31 insertions, 14 deletions

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 6c2dd268e603..053958a8a2ba 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -44,6 +44,9 @@
 #include <linux/nbd-netlink.h>
 #include <net/genetlink.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/nbd.h>
+
 static DEFINE_IDR(nbd_index_idr);
 static DEFINE_MUTEX(nbd_index_mutex);
 static int nbd_total_devices = 0;
@@ -510,6 +513,10 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	if (sent) {
 		if (sent >= sizeof(request)) {
 			skip = sent - sizeof(request);
+
+			/* initialize handle for tracing purposes */
+			handle = nbd_cmd_handle(cmd);
+
 			goto send_pages;
 		}
 		iov_iter_advance(&from, sent);
@@ -526,11 +533,14 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	handle = nbd_cmd_handle(cmd);
 	memcpy(request.handle, &handle, sizeof(handle));
 
+	trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd));
+
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
+	trace_nbd_header_sent(req, handle);
 	if (result <= 0) {
 		if (was_interrupted(result)) {
 			/* If we havne't sent anything we can just return BUSY,
@@ -603,6 +613,7 @@ send_pages:
 		bio = next;
 	}
 out:
+	trace_nbd_payload_sent(req, handle);
 	nsock->pending = NULL;
 	nsock->sent = 0;
 	return 0;
@@ -650,6 +661,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 			tag, req);
 		return ERR_PTR(-ENOENT);
 	}
+	trace_nbd_header_received(req, handle);
 	cmd = blk_mq_rq_to_pdu(req);
 
 	mutex_lock(&cmd->lock);
@@ -703,6 +715,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		}
 	}
 out:
+	trace_nbd_payload_received(req, handle);
 	mutex_unlock(&cmd->lock);
 	return ret ? ERR_PTR(ret) : cmd;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index c64e2fb5a4f1..350e385528fd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 
 			hdr_len = buff->len;
 			if (hdr_len > AQ_CFG_RX_HDR_SIZE)
-				hdr_len = eth_get_headlen(aq_buf_vaddr(&buff->rxdata),
+				hdr_len = eth_get_headlen(skb->dev,
+							  aq_buf_vaddr(&buff->rxdata),
 							  AQ_CFG_RX_HDR_SIZE);
 
 			memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6528a597367b..526f36dcb204 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 			     DMA_ATTR_WEAK_ORDERING);
 
 	if (unlikely(!payload))
-		payload = eth_get_headlen(data_ptr, len);
+		payload = eth_get_headlen(bp->dev, data_ptr, len);
 
 	skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
 	if (!skb) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 297b95c1b3c1..65b985acae38 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	} else {
 		ring->stats.seg_pkt_cnt++;
 
-		pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE);
+		pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE);
 		memcpy(__skb_put(skb, pull_len), va,
 		       ALIGN(pull_len, sizeof(long)));
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b0f31eb481ea..96272e632afc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2588,7 +2588,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 	ring->stats.seg_pkt_cnt++;
 	u64_stats_update_end(&ring->syncp);
 
-	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+	ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE);
 	__skb_put(skb, ring->pull_len);
 	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
 			    desc_cb);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 2325cee76211..b4d970e44163 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 	/* we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
+	pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1a95223c9f99..e1931701cd7e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > I40E_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  I40E_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index b64187753ad6..cf8be63a8a4f 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1315,7 +1315,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IAVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 79043fec0187..259f118c7d8b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -699,7 +699,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > ICE_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, ICE_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index acbb5b4f333d..9b8a4bb25327 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8051,7 +8051,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGB_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f79728381e8a..e58a6e0dc4d9 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1199,7 +1199,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGC_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGC_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 60cec3540dd7..7b903206b534 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1800,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	 * we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
+	pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 49e23afa05a2..d189ed247665 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IXGBEVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  IXGBEVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 40f3f98aa279..7b61126fcec9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -163,7 +163,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	case MLX5_INLINE_MODE_NONE:
 		return 0;
 	case MLX5_INLINE_MODE_TCP_UDP:
-		hlen = eth_get_headlen(skb->data, skb_headlen(skb));
+		hlen = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb));
 		if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb))
 			hlen += VLAN_HLEN;
 		break;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 24d0220b9ba0..9d72f8c76c15 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1965,7 +1965,8 @@ drop:
 
 	if (frags) {
 		/* Exercise flow dissector code path. */
-		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
+		u32 headlen = eth_get_headlen(tun->dev, skb->data,
+					      skb_headlen(skb));
 
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);