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 <[email protected]>

MAINTAINERS

@@ -10742,6 +10742,7 @@ L:	[email protected]
 L:	[email protected]
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
+F:	include/trace/events/nbd.h
 F:	include/uapi/linux/nbd.h
 
 NETWORK DROP MONITOR

arch/arm64/include/asm/insn.h

@@ -277,6 +277,7 @@ __AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
 __AARCH64_INSN_FUNCS(prfm,	0x3FC00000, 0x39800000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
+__AARCH64_INSN_FUNCS(ldadd,	0x3F20FC00, 0xB8200000)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
 __AARCH64_INSN_FUNCS(ldr_lit,	0xBF000000, 0x18000000)
 __AARCH64_INSN_FUNCS(ldrsw_lit,	0xFF000000, 0x98000000)
@@ -394,6 +395,13 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 				   enum aarch64_insn_register state,
 				   enum aarch64_insn_size_type size,
 				   enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result,
+			   enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size);
+u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size);
 u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 				 enum aarch64_insn_register src,
 				 int imm, enum aarch64_insn_variant variant,

arch/arm64/kernel/insn.c

@@ -734,6 +734,46 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
 					    state);
 }
 
+u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result,
+			   enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size)
+{
+	u32 insn = aarch64_insn_get_ldadd_value();
+
+	switch (size) {
+	case AARCH64_INSN_SIZE_32:
+	case AARCH64_INSN_SIZE_64:
+		break;
+	default:
+		pr_err("%s: unimplemented size encoding %d\n", __func__, size);
+		return AARCH64_BREAK_FAULT;
+	}
+
+	insn = aarch64_insn_encode_ldst_size(size, insn);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+					    result);
+
+	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+					    address);
+
+	return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+					    value);
+}
+
+u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address,
+			   enum aarch64_insn_register value,
+			   enum aarch64_insn_size_type size)
+{
+	/*
+	 * STADD is simply encoded as an alias for LDADD with XZR as
+	 * the destination register.
+	 */
+	return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address,
+				      value, size);
+}
+
 static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type,
 					enum aarch64_insn_prfm_target target,
 					enum aarch64_insn_prfm_policy policy,

arch/arm64/net/bpf_jit.h

@@ -100,11 +100,9 @@
 #define A64_STXR(sf, Rt, Rn, Rs) \
 	A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
 
-/* Prefetch */
-#define A64_PRFM(Rn, type, target, policy) \
-	aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
-				  AARCH64_INSN_PRFM_TARGET_##target, \
-				  AARCH64_INSN_PRFM_POLICY_##policy)
+/* LSE atomics */
+#define A64_STADD(sf, Rn, Rs) \
+	aarch64_insn_gen_stadd(Rn, Rs, A64_SIZE(sf))
 
 /* Add/subtract (immediate) */
 #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \

arch/arm64/net/bpf_jit_comp.c

@@ -365,7 +365,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64 ||
 			  BPF_CLASS(code) == BPF_JMP;
 	const bool isdw = BPF_SIZE(code) == BPF_DW;
-	u8 jmp_cond;
+	u8 jmp_cond, reg;
 	s32 jmp_offset;
 
 #define check_imm(bits, imm) do {				\
@@ -756,19 +756,28 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		}
 		break;
+
 	/* STX XADD: lock *(u32 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_W:
 	/* STX XADD: lock *(u64 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_DW:
-		emit_a64_mov_i(1, tmp, off, ctx);
-		emit(A64_ADD(1, tmp, tmp, dst), ctx);
-		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
-		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
-		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
-		emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx);
-		jmp_offset = -3;
-		check_imm19(jmp_offset);
-		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+		if (!off) {
+			reg = dst;
+		} else {
+			emit_a64_mov_i(1, tmp, off, ctx);
+			emit(A64_ADD(1, tmp, tmp, dst), ctx);
+			reg = tmp;
+		}
+		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) {
+			emit(A64_STADD(isdw, reg, src), ctx);
+		} else {
+			emit(A64_LDXR(isdw, tmp2, reg), ctx);
+			emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
+			emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx);
+			jmp_offset = -3;
+			check_imm19(jmp_offset);
+			emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
+		}
 		break;
 
 	default:

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 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		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;
 }

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),

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) {

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)));
 

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);

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)));

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,

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)));

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)));

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)));

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)));

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)));

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,

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;

drivers/net/tun.c

@@ -1965,7 +1965,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	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);

include/linux/bpf.h

@@ -184,6 +184,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
 	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
+	ARG_PTR_TO_MAP_VALUE_OR_NULL,	/* pointer to stack used as map value or NULL */
 
 	/* the following constraints used to prototype bpf_memcmp() and other
 	 * functions that access data on eBPF program stack
@@ -204,6 +205,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
+	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
 };
 
 /* type of values returned from helper functions */
@@ -272,6 +274,7 @@ enum bpf_reg_type {
 	PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
 	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
+	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -361,6 +364,7 @@ struct bpf_prog_aux {
 	u32 used_map_cnt;
 	u32 max_ctx_offset;
 	u32 max_pkt_offset;
+	u32 max_tp_access;
 	u32 stack_depth;
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */

include/linux/bpf_types.h

@@ -25,6 +25,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
 BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
@@ -60,6 +61,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 #ifdef CONFIG_NET
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 #if defined(CONFIG_BPF_STREAM_PARSER)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)

include/linux/etherdevice.h

@@ -33,7 +33,7 @@ struct device;
 int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
 unsigned char *arch_get_platform_mac_address(void);
 int nvmem_get_mac_address(struct device *dev, void *addrbuf);
-u32 eth_get_headlen(void *data, unsigned int max_len);
+u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len);
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;