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

Pull networking fixes from David Miller:

 1) Fix error path in netdevsim, from Jakub Kicinski.

 2) Default values listed in tcp_wmem and tcp_rmem documentation were
    inaccurate, from Tonghao Zhang.

 3) Fix route leaks in SCTP, both for ipv4 and ipv6. From Alexey Kodanev
    and Tommi Rantala.

 4) Fix "MASK < Y" meant to be "MASK << Y" in xgbe driver, from Wolfram
    Sang.

 5) Use after free in u32_destroy_key(), from Paolo Abeni.

 6) Fix two TX issues in be2net driver, from Suredh Reddy.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (25 commits)
  be2net: Handle transmit completion errors in Lancer
  be2net: Fix HW stall issue in Lancer
  RDS: IB: Fix null pointer issue
  nfp: fix kdoc warnings on nested structures
  sample/bpf: fix erspan metadata
  net: erspan: fix erspan config overwrite
  net: erspan: fix metadata extraction
  cls_u32: fix use after free in u32_destroy_key()
  net: amd-xgbe: fix comparison to bitshift when dealing with a mask
  net: phy: Handle not having GPIO enabled in the kernel
  ibmvnic: fix empty firmware version and errors cleanup
  sctp: fix dst refcnt leak in sctp_v4_get_dst
  sctp: fix dst refcnt leak in sctp_v6_get_dst()
  dwc-xlgmac: remove Jie Deng as co-maintainer
  doc: Change the min default value of tcp_wmem/tcp_rmem.
  samples/bpf: use bpf_set_link_xdp_fd
  libbpf: add missing SPDX-License-Identifier
  libbpf: add error reporting in XDP
  libbpf: add function to setup XDP
  tools: add netlink.h and if_link.h in tools uapi
  ...

Documentation/bpf/bpf_devel_QA.txt

@@ -516,4 +516,35 @@ A: LLVM has a -mcpu selector for the BPF back end in order to allow the
    By the way, the BPF kernel selftests run with -mcpu=probe for better
    test coverage.
 
+Q: In some cases clang flag "-target bpf" is used but in other cases the
+   default clang target, which matches the underlying architecture, is used.
+   What is the difference and when I should use which?
+
+A: Although LLVM IR generation and optimization try to stay architecture
+   independent, "-target <arch>" still has some impact on generated code:
+
+     - BPF program may recursively include header file(s) with file scope
+       inline assembly codes. The default target can handle this well,
+       while bpf target may fail if bpf backend assembler does not
+       understand these assembly codes, which is true in most cases.
+
+     - When compiled without -g, additional elf sections, e.g.,
+       .eh_frame and .rela.eh_frame, may be present in the object file
+       with default target, but not with bpf target.
+
+     - The default target may turn a C switch statement into a switch table
+       lookup and jump operation. Since the switch table is placed
+       in the global readonly section, the bpf program will fail to load.
+       The bpf target does not support switch table optimization.
+       The clang option "-fno-jump-tables" can be used to disable
+       switch table generation.
+
+   You should use default target when:
+
+     - Your program includes a header file, e.g., ptrace.h, which eventually
+       pulls in some header files containing file scope host assembly codes.
+     - You can add "-fno-jump-tables" to work around the switch table issue.
+
+   Otherwise, you can use bpf target.
+
 Happy BPF hacking!

Documentation/networking/ip-sysctl.txt

@@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	min: Minimal size of receive buffer used by TCP sockets.
 	It is guaranteed to each TCP socket, even under moderate memory
 	pressure.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of receive buffer used by TCP sockets.
 	This value overrides net.core.rmem_default used by other protocols.
@@ -667,7 +667,7 @@ tcp_window_scaling - BOOLEAN
 tcp_wmem - vector of 3 INTEGERs: min, default, max
 	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.
-	Default: 1 page
+	Default: 4K
 
 	default: initial size of send buffer used by TCP sockets.  This
 	value overrides net.core.wmem_default used by other protocols.

MAINTAINERS

@@ -13326,7 +13326,6 @@ F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
 SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
-M:	Jie Deng <jiedeng@synopsys.com>
 M:	Jose Abreu <Jose.Abreu@synopsys.com>
 L:	netdev@vger.kernel.org
 S:	Supported

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

@@ -595,7 +595,7 @@ static void xgbe_isr_task(unsigned long data)
 
 		reissue_mask = 1 << 0;
 		if (!pdata->per_channel_irq)
-			reissue_mask |= 0xffff < 4;
+			reissue_mask |= 0xffff << 4;
 
 		XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask);
 	}

drivers/net/ethernet/emulex/benet/be.h

@@ -248,6 +248,7 @@ struct be_tx_stats {
 	u32 tx_spoof_check_err;
 	u32 tx_qinq_err;
 	u32 tx_internal_parity_err;
+	u32 tx_sge_err;
 	struct u64_stats_sync sync;
 	struct u64_stats_sync sync_compl;
 };
@@ -944,8 +945,10 @@ static inline bool is_ipv6_ext_hdr(struct sk_buff *skb)
 #define BE_ERROR_EEH		1
 #define BE_ERROR_UE		BIT(1)
 #define BE_ERROR_FW		BIT(2)
-#define BE_ERROR_HW		(BE_ERROR_EEH | BE_ERROR_UE)
-#define BE_ERROR_ANY		(BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_FW)
+#define BE_ERROR_TX		BIT(3)
+#define BE_ERROR_HW		(BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_TX)
+#define BE_ERROR_ANY		(BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_FW | \
+				 BE_ERROR_TX)
 #define BE_CLEAR_ALL		0xFF
 
 static inline u8 be_check_error(struct be_adapter *adapter, u32 err_type)

drivers/net/ethernet/emulex/benet/be_ethtool.c

@@ -189,6 +189,7 @@ static const struct be_ethtool_stat et_tx_stats[] = {
 	 * packet data. This counter is applicable only for Lancer adapters.
 	 */
 	{DRVSTAT_TX_INFO(tx_internal_parity_err)},
+	{DRVSTAT_TX_INFO(tx_sge_err)},
 	{DRVSTAT_TX_INFO(tx_bytes)},
 	{DRVSTAT_TX_INFO(tx_pkts)},
 	{DRVSTAT_TX_INFO(tx_vxlan_offload_pkts)},

drivers/net/ethernet/emulex/benet/be_hw.h

@@ -261,6 +261,7 @@ struct be_eth_hdr_wrb {
 #define LANCER_TX_COMP_HSW_DROP_MAC_ERR		0x3
 #define LANCER_TX_COMP_HSW_DROP_VLAN_ERR	0x5
 #define LANCER_TX_COMP_QINQ_ERR			0x7
+#define LANCER_TX_COMP_SGE_ERR			0x9
 #define LANCER_TX_COMP_PARITY_ERR		0xb
 #define LANCER_TX_COMP_DMA_ERR			0xd
 

drivers/net/ethernet/emulex/benet/be_main.c

@@ -2583,7 +2583,48 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp, u32 frags_needed)
 	}
 }
 
-static struct be_tx_compl_info *be_tx_compl_get(struct be_tx_obj *txo)
+static inline void be_update_tx_err(struct be_tx_obj *txo, u8 status)
+{
+	switch (status) {
+	case BE_TX_COMP_HDR_PARSE_ERR:
+		tx_stats(txo)->tx_hdr_parse_err++;
+		break;
+	case BE_TX_COMP_NDMA_ERR:
+		tx_stats(txo)->tx_dma_err++;
+		break;
+	case BE_TX_COMP_ACL_ERR:
+		tx_stats(txo)->tx_spoof_check_err++;
+		break;
+	}
+}
+
+static inline void lancer_update_tx_err(struct be_tx_obj *txo, u8 status)
+{
+	switch (status) {
+	case LANCER_TX_COMP_LSO_ERR:
+		tx_stats(txo)->tx_tso_err++;
+		break;
+	case LANCER_TX_COMP_HSW_DROP_MAC_ERR:
+	case LANCER_TX_COMP_HSW_DROP_VLAN_ERR:
+		tx_stats(txo)->tx_spoof_check_err++;
+		break;
+	case LANCER_TX_COMP_QINQ_ERR:
+		tx_stats(txo)->tx_qinq_err++;
+		break;
+	case LANCER_TX_COMP_PARITY_ERR:
+		tx_stats(txo)->tx_internal_parity_err++;
+		break;
+	case LANCER_TX_COMP_DMA_ERR:
+		tx_stats(txo)->tx_dma_err++;
+		break;
+	case LANCER_TX_COMP_SGE_ERR:
+		tx_stats(txo)->tx_sge_err++;
+		break;
+	}
+}
+
+static struct be_tx_compl_info *be_tx_compl_get(struct be_adapter *adapter,
+						struct be_tx_obj *txo)
 {
 	struct be_queue_info *tx_cq = &txo->cq;
 	struct be_tx_compl_info *txcp = &txo->txcp;
@@ -2599,6 +2640,24 @@ static struct be_tx_compl_info *be_tx_compl_get(struct be_tx_obj *txo)
 	txcp->status = GET_TX_COMPL_BITS(status, compl);
 	txcp->end_index = GET_TX_COMPL_BITS(wrb_index, compl);
 
+	if (txcp->status) {
+		if (lancer_chip(adapter)) {
+			lancer_update_tx_err(txo, txcp->status);
+			/* Reset the adapter incase of TSO,
+			 * SGE or Parity error
+			 */
+			if (txcp->status == LANCER_TX_COMP_LSO_ERR ||
+			    txcp->status == LANCER_TX_COMP_PARITY_ERR ||
+			    txcp->status == LANCER_TX_COMP_SGE_ERR)
+				be_set_error(adapter, BE_ERROR_TX);
+		} else {
+			be_update_tx_err(txo, txcp->status);
+		}
+	}
+
+	if (be_check_error(adapter, BE_ERROR_TX))
+		return NULL;
+
 	compl->dw[offsetof(struct amap_eth_tx_compl, valid) / 32] = 0;
 	queue_tail_inc(tx_cq);
 	return txcp;
@@ -2741,7 +2800,7 @@ static void be_tx_compl_clean(struct be_adapter *adapter)
 			cmpl = 0;
 			num_wrbs = 0;
 			txq = &txo->q;
-			while ((txcp = be_tx_compl_get(txo))) {
+			while ((txcp = be_tx_compl_get(adapter, txo))) {
 				num_wrbs +=
 					be_tx_compl_process(adapter, txo,
 							    txcp->end_index);
@@ -3120,42 +3179,6 @@ static int be_process_rx(struct be_rx_obj *rxo, struct napi_struct *napi,
 	return work_done;
 }
 
-static inline void be_update_tx_err(struct be_tx_obj *txo, u8 status)
-{
-	switch (status) {
-	case BE_TX_COMP_HDR_PARSE_ERR:
-		tx_stats(txo)->tx_hdr_parse_err++;
-		break;
-	case BE_TX_COMP_NDMA_ERR:
-		tx_stats(txo)->tx_dma_err++;
-		break;
-	case BE_TX_COMP_ACL_ERR:
-		tx_stats(txo)->tx_spoof_check_err++;
-		break;
-	}
-}
-
-static inline void lancer_update_tx_err(struct be_tx_obj *txo, u8 status)
-{
-	switch (status) {
-	case LANCER_TX_COMP_LSO_ERR:
-		tx_stats(txo)->tx_tso_err++;
-		break;
-	case LANCER_TX_COMP_HSW_DROP_MAC_ERR:
-	case LANCER_TX_COMP_HSW_DROP_VLAN_ERR:
-		tx_stats(txo)->tx_spoof_check_err++;
-		break;
-	case LANCER_TX_COMP_QINQ_ERR:
-		tx_stats(txo)->tx_qinq_err++;
-		break;
-	case LANCER_TX_COMP_PARITY_ERR:
-		tx_stats(txo)->tx_internal_parity_err++;
-		break;
-	case LANCER_TX_COMP_DMA_ERR:
-		tx_stats(txo)->tx_dma_err++;
-		break;
-	}
-}
 
 static void be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
 			  int idx)
@@ -3163,16 +3186,9 @@ static void be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
 	int num_wrbs = 0, work_done = 0;
 	struct be_tx_compl_info *txcp;
 
-	while ((txcp = be_tx_compl_get(txo))) {
+	while ((txcp = be_tx_compl_get(adapter, txo))) {
 		num_wrbs += be_tx_compl_process(adapter, txo, txcp->end_index);
 		work_done++;
-
-		if (txcp->status) {
-			if (lancer_chip(adapter))
-				lancer_update_tx_err(txo, txcp->status);
-			else
-				be_update_tx_err(txo, txcp->status);
-		}
 	}
 
 	if (work_done) {
@@ -5104,9 +5120,12 @@ static netdev_features_t be_features_check(struct sk_buff *skb,
 			features &= ~NETIF_F_TSO6;
 
 		/* Lancer cannot handle the packet with MSS less than 256.
+		 * Also it can't handle a TSO packet with a single segment
 		 * Disable the GSO support in such cases
 		 */
-		if (lancer_chip(adapter) && skb_shinfo(skb)->gso_size < 256)
+		if (lancer_chip(adapter) &&
+		    (skb_shinfo(skb)->gso_size < 256 ||
+		     skb_shinfo(skb)->gso_segs == 1))
 			features &= ~NETIF_F_GSO_MASK;
 	}
 

drivers/net/ethernet/ibm/ibmvnic.c

@@ -3286,7 +3286,7 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq,
 			   struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
-	unsigned char *substr = NULL, *ptr = NULL;
+	unsigned char *substr = NULL;
 	u8 fw_level_len = 0;
 
 	memset(adapter->fw_version, 0, 32);
@@ -3306,10 +3306,6 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq,
 	substr = strnstr(adapter->vpd->buff, "RM", adapter->vpd->len);
 	if (!substr) {
 		dev_info(dev, "Warning - No FW level has been provided in the VPD buffer by the VIOS Server\n");
-		ptr = strncpy((char *)adapter->fw_version, "N/A",
-			      3 * sizeof(char));
-		if (!ptr)
-			dev_err(dev, "Failed to inform that firmware version is unavailable to the adapter\n");
 		goto complete;
 	}
 
@@ -3324,16 +3320,14 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq,
 	/* copy firmware version string from vpd into adapter */
 	if ((substr + 3 + fw_level_len) <
 	    (adapter->vpd->buff + adapter->vpd->len)) {
-		ptr = strncpy((char *)adapter->fw_version,
-			      substr + 3, fw_level_len);
-
-		if (!ptr)
-			dev_err(dev, "Failed to isolate FW level string\n");
+		strncpy((char *)adapter->fw_version, substr + 3, fw_level_len);
 	} else {
 		dev_info(dev, "FW substr extrapolated VPD buff\n");
 	}
 
 complete:
+	if (adapter->fw_version[0] == '\0')
+		strncpy((char *)adapter->fw_version, "N/A", 3 * sizeof(char));
 	complete(&adapter->fw_done);
 }
 

drivers/net/ethernet/netronome/nfp/bpf/main.h

@@ -112,22 +112,22 @@ enum pkt_vec {
  * @map_elems_in_use:	number of elements allocated to offloaded maps
  *
  * @adjust_head:	adjust head capability
- * @flags:		extra flags for adjust head
- * @off_min:		minimal packet offset within buffer required
- * @off_max:		maximum packet offset within buffer required
- * @guaranteed_sub:	amount of negative adjustment guaranteed possible
- * @guaranteed_add:	amount of positive adjustment guaranteed possible
+ * @adjust_head.flags:		extra flags for adjust head
+ * @adjust_head.off_min:	minimal packet offset within buffer required
+ * @adjust_head.off_max:	maximum packet offset within buffer required
+ * @adjust_head.guaranteed_sub:	negative adjustment guaranteed possible
+ * @adjust_head.guaranteed_add:	positive adjustment guaranteed possible
  *
  * @maps:		map capability
- * @types:		supported map types
- * @max_maps:		max number of maps supported
- * @max_elems:		max number of entries in each map
- * @max_key_sz:		max size of map key
- * @max_val_sz:		max size of map value
- * @max_elem_sz:	max size of map entry (key + value)
+ * @maps.types:			supported map types
+ * @maps.max_maps:		max number of maps supported
+ * @maps.max_elems:		max number of entries in each map
+ * @maps.max_key_sz:		max size of map key
+ * @maps.max_val_sz:		max size of map value
+ * @maps.max_elem_sz:		max size of map entry (key + value)
  *
  * @helpers:		helper addressess for various calls
- * @map_lookup:		map lookup helper address
+ * @helpers.map_lookup:		map lookup helper address
  */
 struct nfp_app_bpf {
 	struct nfp_app *app;

drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c

@@ -50,9 +50,9 @@
  * @seq:		sequence number of the message
  * @count:		number of tunnels report in message
  * @flags:		options part of the request
- * @ipv4:		dest IPv4 address of active route
- * @egress_port:	port the encapsulated packet egressed
- * @extra:		reserved for future use
+ * @tun_info.ipv4:		dest IPv4 address of active route
+ * @tun_info.egress_port:	port the encapsulated packet egressed
+ * @tun_info.extra:		reserved for future use
  * @tun_info:		tunnels that have sent traffic in reported period
  */
 struct nfp_tun_active_tuns {
@@ -132,8 +132,8 @@ struct nfp_ipv4_addr_entry {
  * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP
  * @reserved:	reserved for future use
  * @count:	number of MAC addresses in the message
- * @index:	index of MAC address in the lookup table
- * @addr:	interface MAC address
+ * @addresses.index:	index of MAC address in the lookup table
+ * @addresses.addr:	interface MAC address
  * @addresses:	series of MACs to offload
  */
 struct nfp_tun_mac_addr {

drivers/net/ethernet/netronome/nfp/nfp_net.h

@@ -193,7 +193,8 @@ struct nfp_net_tx_desc {
 
 /**
  * struct nfp_net_tx_buf - software TX buffer descriptor
- * @skb:	sk_buff associated with this buffer
+ * @skb:	normal ring, sk_buff associated with this buffer
+ * @frag:	XDP ring, page frag associated with this buffer
  * @dma_addr:	DMA mapping address of the buffer
  * @fidx:	Fragment index (-1 for the head and [0..nr_frags-1] for frags)
  * @pkt_cnt:	Number of packets to be produced out of the skb associated
@@ -377,6 +378,9 @@ struct nfp_net_rx_ring {
  * struct nfp_net_r_vector - Per ring interrupt vector configuration
  * @nfp_net:        Backpointer to nfp_net structure
  * @napi:           NAPI structure for this ring vec
+ * @tasklet:        ctrl vNIC, tasklet for servicing the r_vec
+ * @queue:          ctrl vNIC, send queue
+ * @lock:           ctrl vNIC, r_vec lock protects @queue
  * @tx_ring:        Pointer to TX ring
  * @rx_ring:        Pointer to RX ring
  * @xdp_ring:	    Pointer to an extra TX ring for XDP

drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h

@@ -98,28 +98,29 @@ enum nfp_eth_fec {
  * @max_index:	max of @index fields of all @ports
  * @ports:	table of ports
  *
- * @eth_index:	port index according to legacy ethX numbering
- * @index:	chip-wide first channel index
- * @nbi:	NBI index
- * @base:	first channel index (within NBI)
- * @lanes:	number of channels
- * @speed:	interface speed (in Mbps)
- * @interface:	interface (module) plugged in
- * @media:	media type of the @interface
- * @fec:	forward error correction mode
- * @aneg:	auto negotiation mode
- * @mac_addr:	interface MAC address
- * @label_port:	port id
- * @label_subport:  id of interface within port (for split ports)
- * @enabled:	is enabled?
- * @tx_enabled:	is TX enabled?
- * @rx_enabled:	is RX enabled?
- * @override_changed: is media reconfig pending?
+ * @ports.eth_index:	port index according to legacy ethX numbering
+ * @ports.index:	chip-wide first channel index
+ * @ports.nbi:		NBI index
+ * @ports.base:		first channel index (within NBI)
+ * @ports.lanes:	number of channels
+ * @ports.speed:	interface speed (in Mbps)
+ * @ports.interface:	interface (module) plugged in
+ * @ports.media:	media type of the @interface
+ * @ports.fec:		forward error correction mode
+ * @ports.aneg:		auto negotiation mode
+ * @ports.mac_addr:	interface MAC address
+ * @ports.label_port:	port id
+ * @ports.label_subport:  id of interface within port (for split ports)
+ * @ports.enabled:	is enabled?
+ * @ports.tx_enabled:	is TX enabled?
+ * @ports.rx_enabled:	is RX enabled?
+ * @ports.override_changed: is media reconfig pending?
  *
- * @port_type:	one of %PORT_* defines for ethtool
- * @port_lanes:	total number of lanes on the port (sum of lanes of all subports)
- * @is_split:	is interface part of a split port
- * @fec_modes_supported:	bitmap of FEC modes supported
+ * @ports.port_type:	one of %PORT_* defines for ethtool
+ * @ports.port_lanes:	total number of lanes on the port (sum of lanes of all
+ *			subports)
+ * @ports.is_split:	is interface part of a split port
+ * @ports.fec_modes_supported:	bitmap of FEC modes supported
  */
 struct nfp_eth_table {
 	unsigned int count;

drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c

@@ -56,16 +56,17 @@
 
 /**
  * struct nfp_resource_entry - Resource table entry
- * @owner:		NFP CPP Lock, interface owner
- * @key:		NFP CPP Lock, posix_crc32(name, 8)
- * @region:		Memory region descriptor
- * @name:		ASCII, zero padded name
- * @reserved
- * @cpp_action:		CPP Action
- * @cpp_token:		CPP Token
- * @cpp_target:		CPP Target ID
- * @page_offset:	256-byte page offset into target's CPP address
- * @page_size:		size, in 256-byte pages
+ * @mutex:	NFP CPP Lock
+ * @mutex.owner:	NFP CPP Lock, interface owner
+ * @mutex.key:		NFP CPP Lock, posix_crc32(name, 8)
+ * @region:	Memory region descriptor
+ * @region.name:	ASCII, zero padded name
+ * @region.reserved:	padding
+ * @region.cpp_action:	CPP Action
+ * @region.cpp_token:	CPP Token
+ * @region.cpp_target:	CPP Target ID
+ * @region.page_offset:	256-byte page offset into target's CPP address
+ * @region.page_size:	size, in 256-byte pages
  */
 struct nfp_resource_entry {
 	struct nfp_resource_entry_mutex {

drivers/net/netdevsim/bpf.c

@@ -480,8 +480,7 @@ static int
 nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 {
 	struct nsim_bpf_bound_map *nmap;
-	unsigned int i;
-	int err;
+	int i, err;
 
 	if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY &&
 		    offmap->map.map_type != BPF_MAP_TYPE_HASH))
@@ -518,7 +517,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	return 0;
 
 err_free:
-	while (--i) {
+	while (--i >= 0) {
 		kfree(nmap->entry[i].key);
 		kfree(nmap->entry[i].value);
 	}

drivers/net/phy/mdio_bus.c

@@ -56,7 +56,8 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev)
 		gpiod = fwnode_get_named_gpiod(&mdiodev->dev.of_node->fwnode,
 					       "reset-gpios", 0, GPIOD_OUT_LOW,
 					       "PHY reset");
-	if (PTR_ERR(gpiod) == -ENOENT)
+	if (PTR_ERR(gpiod) == -ENOENT ||
+	    PTR_ERR(gpiod) == -ENOSYS)
 		gpiod = NULL;
 	else if (IS_ERR(gpiod))
 		return PTR_ERR(gpiod);

include/linux/netdevice.h

@@ -3228,6 +3228,12 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev,
 }
 #endif
 
+static inline struct netdev_rx_queue *
+__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
+{
+	return dev->_rx + rxq;
+}
+
 #ifdef CONFIG_SYSFS
 static inline unsigned int get_netdev_rx_queue_index(
 		struct netdev_rx_queue *queue)

include/net/erspan.h

@@ -159,13 +159,13 @@ static inline void erspan_build_header(struct sk_buff *skb,
 	struct ethhdr *eth = (struct ethhdr *)skb->data;
 	enum erspan_encap_type enc_type;
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *ersmd;
 	struct qtag_prefix {
 		__be16 eth_type;
 		__be16 tci;
 	} *qp;
 	u16 vlan_tci = 0;
 	u8 tos;
+	__be32 *idx;
 
 	tos = is_ipv4 ? ip_hdr(skb)->tos :
 			(ipv6_hdr(skb)->priority << 4) +
@@ -195,8 +195,8 @@ static inline void erspan_build_header(struct sk_buff *skb,
 	set_session_id(ershdr, id);
 
 	/* Build metadata */
-	ersmd = (struct erspan_metadata *)(ershdr + 1);
-	ersmd->u.index = htonl(index & INDEX_MASK);
+	idx = (__be32 *)(ershdr + 1);
+	*idx = htonl(index & INDEX_MASK);
 }
 
 /* ERSPAN GRA: timestamp granularity
@@ -225,7 +225,7 @@ static inline void erspan_build_header_v2(struct sk_buff *skb,
 {
 	struct ethhdr *eth = (struct ethhdr *)skb->data;
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *md;
+	struct erspan_md2 *md2;
 	struct qtag_prefix {
 		__be16 eth_type;
 		__be16 tci;
@@ -261,15 +261,15 @@ static inline void erspan_build_header_v2(struct sk_buff *skb,
 	set_session_id(ershdr, id);
 
 	/* Build metadata */
-	md = (struct erspan_metadata *)(ershdr + 1);
-	md->u.md2.timestamp = erspan_get_timestamp();
-	md->u.md2.sgt = htons(sgt);
-	md->u.md2.p = 1;
-	md->u.md2.ft = 0;
-	md->u.md2.dir = direction;
-	md->u.md2.gra = gra;
-	md->u.md2.o = 0;
-	set_hwid(&md->u.md2, hwid);
+	md2 = (struct erspan_md2 *)(ershdr + 1);
+	md2->timestamp = erspan_get_timestamp();
+	md2->sgt = htons(sgt);
+	md2->p = 1;
+	md2->ft = 0;
+	md2->dir = direction;
+	md2->gra = gra;
+	md2->o = 0;
+	set_hwid(md2, hwid);
 }
 
 #endif

kernel/bpf/core.c

@@ -1576,25 +1576,41 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 				__u32 __user *prog_ids, u32 cnt)
 {
 	struct bpf_prog **prog;
-	u32 i = 0, id;
-
+	unsigned long err = 0;
+	u32 i = 0, *ids;
+	bool nospc;
+
+	/* users of this function are doing:
+	 * cnt = bpf_prog_array_length();
+	 * if (cnt > 0)
+	 *     bpf_prog_array_copy_to_user(..., cnt);
+	 * so below kcalloc doesn't need extra cnt > 0 check, but
+	 * bpf_prog_array_length() releases rcu lock and
+	 * prog array could have been swapped with empty or larger array,
+	 * so always copy 'cnt' prog_ids to the user.
+	 * In a rare race the user will see zero prog_ids
+	 */
+	ids = kcalloc(cnt, sizeof(u32), GFP_USER);
+	if (!ids)
+		return -ENOMEM;
 	rcu_read_lock();
 	prog = rcu_dereference(progs)->progs;
 	for (; *prog; prog++) {
 		if (*prog == &dummy_bpf_prog.prog)
 			continue;
-		id = (*prog)->aux->id;
-		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
-			rcu_read_unlock();
-			return -EFAULT;
-		}
+		ids[i] = (*prog)->aux->id;
 		if (++i == cnt) {
 			prog++;
 			break;
 		}
 	}
+	nospc = !!(*prog);
 	rcu_read_unlock();
-	if (*prog)
+	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
+	kfree(ids);
+	if (err)
+		return -EFAULT;
+	if (nospc)
 		return -ENOSPC;
 	return 0;
 }

net/bpf/test_run.c

@@ -151,6 +151,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 {
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
+	struct netdev_rx_queue *rxqueue;
 	struct xdp_buff xdp = {};
 	u32 retval, duration;
 	void *data;
@@ -165,6 +166,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	xdp.data_meta = xdp.data;
 	xdp.data_end = xdp.data + size;
 
+	rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
+	xdp.rxq = &rxqueue->xdp_rxq;
+
 	retval = bpf_test_run(prog, &xdp, repeat, &duration);
 	if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 		size = xdp.data_end - xdp.data;

net/ipv4/ip_gre.c

@@ -261,6 +261,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	struct ip_tunnel_net *itn;
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph;
+	struct erspan_md2 *md2;
 	int ver;
 	int len;
 
@@ -313,21 +314,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 				return PACKET_REJECT;
 
 			md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
-			memcpy(md, pkt_md, sizeof(*md));
 			md->version = ver;
+			md2 = &md->u.md2;
+			memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE :
+						       ERSPAN_V2_MDSIZE);
 
 			info = &tun_dst->u.tun_info;
 			info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
 			info->options_len = sizeof(*md);
-		} else {
-			tunnel->erspan_ver = ver;
-			if (ver == 1) {
-				tunnel->index = ntohl(pkt_md->u.index);
-			} else {
-				tunnel->dir = pkt_md->u.md2.dir;
-				tunnel->hwid = get_hwid(&pkt_md->u.md2);
-			}
-
 		}
 
 		skb_reset_mac_header(skb);

net/ipv6/ip6_gre.c

@@ -505,6 +505,7 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 	struct erspan_base_hdr *ershdr;
 	struct erspan_metadata *pkt_md;
 	const struct ipv6hdr *ipv6h;
+	struct erspan_md2 *md2;
 	struct ip6_tnl *tunnel;
 	u8 ver;
 
@@ -551,24 +552,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len,
 
 			info = &tun_dst->u.tun_info;
 			md = ip_tunnel_info_opts(info);
-
-			memcpy(md, pkt_md, sizeof(*md));
 			md->version = ver;
+			md2 = &md->u.md2;
+			memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE :
+						       ERSPAN_V2_MDSIZE);
 			info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
 			info->options_len = sizeof(*md);
 
 			ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);
 
 		} else {
-			tunnel->parms.erspan_ver = ver;
-
-			if (ver == 1) {
-				tunnel->parms.index = ntohl(pkt_md->u.index);
-			} else {
-				tunnel->parms.dir = pkt_md->u.md2.dir;
-				tunnel->parms.hwid = get_hwid(&pkt_md->u.md2);
-			}
-
 			ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
 		}
 

net/rds/ib.c

@@ -345,7 +345,8 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
 	/* Create a CMA ID and try to bind it. This catches both
 	 * IB and iWARP capable NICs.
 	 */
-	cm_id = rdma_create_id(&init_net, NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
+	cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler,
+			       NULL, RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 

net/sched/cls_u32.c

@@ -398,10 +398,12 @@ static int u32_init(struct tcf_proto *tp)
 static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
 			   bool free_pf)
 {
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+
 	tcf_exts_destroy(&n->exts);
 	tcf_exts_put_net(&n->exts);
-	if (n->ht_down)
-		n->ht_down->refcnt--;
+	if (ht && --ht->refcnt == 0)
+		kfree(ht);
 #ifdef CONFIG_CLS_U32_PERF
 	if (free_pf)
 		free_percpu(n->pf);
@@ -659,16 +661,15 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 
 		hlist_del(&tp_c->hnode);
 
-		for (ht = rtnl_dereference(tp_c->hlist);
-		     ht;
-		     ht = rtnl_dereference(ht->next)) {
-			ht->refcnt--;
-			u32_clear_hnode(tp, ht, extack);
-		}
-
 		while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) {
+			u32_clear_hnode(tp, ht, extack);
 			RCU_INIT_POINTER(tp_c->hlist, ht->next);
-			kfree_rcu(ht, rcu);
+
+			/* u32_destroy_key() will later free ht for us, if it's
+			 * still referenced by some knode
+			 */
+			if (--ht->refcnt == 0)
+				kfree_rcu(ht, rcu);
 		}
 
 		idr_destroy(&tp_c->handle_idr);

net/sctp/ipv6.c

@@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
 		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
 
-		if (!IS_ERR(bdst) &&
-		    ipv6_chk_addr(dev_net(bdst->dev),
+		if (IS_ERR(bdst))
+			continue;
+
+		if (ipv6_chk_addr(dev_net(bdst->dev),
 				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
 			if (!IS_ERR_OR_NULL(dst))
 				dst_release(dst);
@@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		}
 
 		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-		if (matchlen > bmatchlen)
+		if (matchlen > bmatchlen) {
+			dst_release(bdst);
 			continue;
+		}
 
 		if (!IS_ERR_OR_NULL(dst))
 			dst_release(dst);

net/sctp/protocol.c

@@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		if (IS_ERR(rt))
 			continue;
 
-		if (!dst)
-			dst = &rt->dst;
-
 		/* Ensure the src address belongs to the output
 		 * interface.
 		 */
 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
 				     false);
 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (&rt->dst != dst)
+			if (!dst)
+				dst = &rt->dst;
+			else
 				dst_release(&rt->dst);
 			continue;
 		}
 
-		if (dst != &rt->dst)
-			dst_release(dst);
+		dst_release(dst);
 		dst = &rt->dst;
 		break;
 	}

samples/bpf/Makefile

@@ -45,7 +45,7 @@ hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
 
 # Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o
+LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
 CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 
 test_lru_dist-objs := test_lru_dist.o $(LIBBPF)

samples/bpf/bpf_load.c

@@ -695,105 +695,3 @@ struct ksym *ksym_search(long key)
 	return &syms[0];
 }
 
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		printf("open netlink socket: %s\n", strerror(errno));
-		return -1;
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		printf("bind to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
-	}
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		printf("send to netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		printf("recv from netlink: %s\n", strerror(errno));
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != getpid()) {
-			printf("Wrong pid %d, expected %d\n",
-			       nh->nlmsg_pid, getpid());
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			printf("Wrong seq %d, expected %d\n",
-			       nh->nlmsg_seq, seq);
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			printf("nlmsg error %s\n", strerror(-err->error));
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}

samples/bpf/bpf_load.h

@@ -61,5 +61,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
-int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif

samples/bpf/tcbpf2_kern.c

@@ -15,6 +15,7 @@
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/filter.h>
 #include <uapi/linux/pkt_cls.h>
+#include <uapi/linux/erspan.h>
 #include <net/ipv6.h>
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
@@ -35,24 +36,10 @@ struct geneve_opt {
 	u8	opt_data[8]; /* hard-coded to 8 byte */
 };
 
-struct erspan_md2 {
-	__be32 timestamp;
-	__be16 sgt;
-	__be16 flags;
-};
-
 struct vxlan_metadata {
 	u32     gbp;
 };
 
-struct erspan_metadata {
-	union {
-		__be32 index;
-		struct erspan_md2 md2;
-	} u;
-	int version;
-};
-
 SEC("gre_set_tunnel")
 int _gre_set_tunnel(struct __sk_buff *skb)
 {
@@ -156,13 +143,15 @@ int _erspan_set_tunnel(struct __sk_buff *skb)
 	__builtin_memset(&md, 0, sizeof(md));
 #ifdef ERSPAN_V1
 	md.version = 1;
-	md.u.index = htonl(123);
+	md.u.index = bpf_htonl(123);
 #else
 	u8 direction = 1;
-	u16 hwid = 7;
+	u8 hwid = 7;
 
 	md.version = 2;
-	md.u.md2.flags = htons((direction << 3) | (hwid << 4));
+	md.u.md2.dir = direction;
+	md.u.md2.hwid = hwid & 0xf;
+	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -207,9 +196,9 @@ int _erspan_get_tunnel(struct __sk_buff *skb)
 	char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
 
 	bpf_trace_printk(fmt2, sizeof(fmt2),
-		(ntohs(md.u.md2.flags) >> 3) & 0x1,
-		(ntohs(md.u.md2.flags) >> 4) & 0x3f,
-		bpf_ntohl(md.u.md2.timestamp));
+			 md.u.md2.dir,
+			 (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+			 bpf_ntohl(md.u.md2.timestamp));
 #endif
 
 	return TC_ACT_OK;
@@ -242,10 +231,12 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
 	md.version = 1;
 #else
 	u8 direction = 0;
-	u16 hwid = 17;
+	u8 hwid = 17;
 
 	md.version = 2;
-	md.u.md2.flags = htons((direction << 3) | (hwid << 4));
+	md.u.md2.dir = direction;
+	md.u.md2.hwid = hwid & 0xf;
+	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -290,9 +281,9 @@ int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
 
 	bpf_trace_printk(fmt2, sizeof(fmt2),
-		(ntohs(md.u.md2.flags) >> 3) & 0x1,
-		(ntohs(md.u.md2.flags) >> 4) & 0x3f,
-		bpf_ntohl(md.u.md2.timestamp));
+			 md.u.md2.dir,
+			 (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+			 bpf_ntohl(md.u.md2.timestamp));
 #endif
 
 	return TC_ACT_OK;

samples/bpf/test_tunnel_bpf.sh

@@ -68,7 +68,7 @@ function add_erspan_tunnel {
 		ip netns exec at_ns0 \
 		ip link add dev $DEV_NS type $TYPE seq key 2 \
 		local 172.16.1.100 remote 172.16.1.200 \
-		erspan_ver 2 erspan_dir 1 erspan_hwid 3
+		erspan_ver 2 erspan_dir egress erspan_hwid 3
 	fi
 	ip netns exec at_ns0 ip link set dev $DEV_NS up
 	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
@@ -97,7 +97,7 @@ function add_ip6erspan_tunnel {
 		ip netns exec at_ns0 \
 		ip link add dev $DEV_NS type $TYPE seq key 2 \
 		local ::11 remote ::22 \
-		erspan_ver 2 erspan_dir 1 erspan_hwid 7
+		erspan_ver 2 erspan_dir egress erspan_hwid 7
 	fi
 	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
 	ip netns exec at_ns0 ip link set dev $DEV_NS up

samples/bpf/xdp1_user.c

@@ -25,7 +25,7 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -116,7 +116,7 @@ int main(int argc, char **argv)
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}

samples/bpf/xdp_redirect_cpu_user.c

@@ -26,7 +26,7 @@ static const char *__doc__ =
 
 /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
  * use bpf/libbpf.h), but cannot as (currently) needed for XDP
- * attaching to a device via set_link_xdp_fd()
+ * attaching to a device via bpf_set_link_xdp_fd()
  */
 #include "libbpf.h"
 #include "bpf_load.h"
@@ -67,7 +67,7 @@ static void int_exit(int sig)
 		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
 		ifindex, ifname);
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(EXIT_OK);
 }
 
@@ -682,7 +682,7 @@ int main(int argc, char **argv)
 	/* Remove XDP program when program is interrupted */
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
 		return EXIT_FAIL_XDP;
 	}

samples/bpf/xdp_redirect_map_user.c

@@ -34,9 +34,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -120,13 +120,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;

samples/bpf/xdp_redirect_user.c

@@ -33,9 +33,9 @@ static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex_in, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags);
 	if (ifindex_out_xdp_dummy_attached)
-		set_link_xdp_fd(ifindex_out, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags);
 	exit(0);
 }
 
@@ -114,13 +114,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
 		return 1;
 	}
 
 	/* Loading dummy XDP prog on out-device */
-	if (set_link_xdp_fd(ifindex_out, prog_fd[1],
+	if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1],
 			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
 		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
 		ifindex_out_xdp_dummy_attached = false;

samples/bpf/xdp_router_ipv4_user.c

@@ -37,7 +37,7 @@ static void int_exit(int sig)
 	int i = 0;
 
 	for (i = 0; i < total_ifindex; i++)
-		set_link_xdp_fd(ifindex_list[i], -1, flags);
+		bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 	exit(0);
 }
 
@@ -49,7 +49,7 @@ static void close_and_exit(int sig)
 	close(sock_arp);
 
 	for (i = 0; i < total_ifindex; i++)
-		set_link_xdp_fd(ifindex_list[i], -1, flags);
+		bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 	exit(0);
 }
 
@@ -183,7 +183,7 @@ static void read_route(struct nlmsghdr *nh, int nll)
 			int i = 0;
 
 			for (i = 0; i < total_ifindex; i++)
-				set_link_xdp_fd(ifindex_list[i], -1, flags);
+				bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 			exit(0);
 		}
 		assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0);
@@ -633,12 +633,12 @@ int main(int ac, char **argv)
 		}
 	}
 	for (i = 0; i < total_ifindex; i++) {
-		if (set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) {
+		if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) {
 			printf("link set xdp fd failed\n");
 			int recovery_index = i;
 
 			for (i = 0; i < recovery_index; i++)
-				set_link_xdp_fd(ifindex_list[i], -1, flags);
+				bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
 
 			return 1;
 		}

samples/bpf/xdp_rxq_info_user.c

@@ -56,7 +56,7 @@ static void int_exit(int sig)
 		"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
 		ifindex, ifname);
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(EXIT_OK);
 }
 
@@ -521,7 +521,7 @@ int main(int argc, char **argv)
 	/* Remove XDP program when program is interrupted */
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		fprintf(stderr, "link set xdp fd failed\n");
 		return EXIT_FAIL_XDP;
 	}

samples/bpf/xdp_tx_iptunnel_user.c

@@ -30,7 +30,7 @@ static __u32 xdp_flags = 0;
 static void int_exit(int sig)
 {
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1, xdp_flags);
+		bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -254,14 +254,14 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
 
 	poll_stats(kill_after_s);
 
-	set_link_xdp_fd(ifindex, -1, xdp_flags);
+	bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
 
 	return 0;
 }

tools/include/uapi/linux/netlink.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__LINUX_NETLINK_H
+#define _UAPI__LINUX_NETLINK_H
+
+#include <linux/kernel.h>
+#include <linux/socket.h> /* for __kernel_sa_family_t */
+#include <linux/types.h>
+
+#define NETLINK_ROUTE		0	/* Routing/device hook				*/
+#define NETLINK_UNUSED		1	/* Unused number				*/
+#define NETLINK_USERSOCK	2	/* Reserved for user mode socket protocols 	*/
+#define NETLINK_FIREWALL	3	/* Unused number, formerly ip_queue		*/
+#define NETLINK_SOCK_DIAG	4	/* socket monitoring				*/
+#define NETLINK_NFLOG		5	/* netfilter/iptables ULOG */
+#define NETLINK_XFRM		6	/* ipsec */
+#define NETLINK_SELINUX		7	/* SELinux event notifications */
+#define NETLINK_ISCSI		8	/* Open-iSCSI */
+#define NETLINK_AUDIT		9	/* auditing */
+#define NETLINK_FIB_LOOKUP	10	
+#define NETLINK_CONNECTOR	11
+#define NETLINK_NETFILTER	12	/* netfilter subsystem */
+#define NETLINK_IP6_FW		13
+#define NETLINK_DNRTMSG		14	/* DECnet routing messages */
+#define NETLINK_KOBJECT_UEVENT	15	/* Kernel messages to userspace */
+#define NETLINK_GENERIC		16
+/* leave room for NETLINK_DM (DM Events) */
+#define NETLINK_SCSITRANSPORT	18	/* SCSI Transports */
+#define NETLINK_ECRYPTFS	19
+#define NETLINK_RDMA		20
+#define NETLINK_CRYPTO		21	/* Crypto layer */
+#define NETLINK_SMC		22	/* SMC monitoring */
+
+#define NETLINK_INET_DIAG	NETLINK_SOCK_DIAG
+
+#define MAX_LINKS 32		
+
+struct sockaddr_nl {
+	__kernel_sa_family_t	nl_family;	/* AF_NETLINK	*/
+	unsigned short	nl_pad;		/* zero		*/
+	__u32		nl_pid;		/* port ID	*/
+       	__u32		nl_groups;	/* multicast groups mask */
+};
+
+struct nlmsghdr {
+	__u32		nlmsg_len;	/* Length of message including header */
+	__u16		nlmsg_type;	/* Message content */
+	__u16		nlmsg_flags;	/* Additional flags */
+	__u32		nlmsg_seq;	/* Sequence number */
+	__u32		nlmsg_pid;	/* Sending process port ID */
+};
+
+/* Flags values */
+
+#define NLM_F_REQUEST		0x01	/* It is request message. 	*/
+#define NLM_F_MULTI		0x02	/* Multipart message, terminated by NLMSG_DONE */
+#define NLM_F_ACK		0x04	/* Reply with ack, with zero or error code */
+#define NLM_F_ECHO		0x08	/* Echo this request 		*/
+#define NLM_F_DUMP_INTR		0x10	/* Dump was inconsistent due to sequence change */
+#define NLM_F_DUMP_FILTERED	0x20	/* Dump was filtered as requested */
+
+/* Modifiers to GET request */
+#define NLM_F_ROOT	0x100	/* specify tree	root	*/
+#define NLM_F_MATCH	0x200	/* return all matching	*/
+#define NLM_F_ATOMIC	0x400	/* atomic GET		*/
+#define NLM_F_DUMP	(NLM_F_ROOT|NLM_F_MATCH)
+
+/* Modifiers to NEW request */
+#define NLM_F_REPLACE	0x100	/* Override existing		*/
+#define NLM_F_EXCL	0x200	/* Do not touch, if it exists	*/
+#define NLM_F_CREATE	0x400	/* Create, if it does not exist	*/
+#define NLM_F_APPEND	0x800	/* Add to end of list		*/
+
+/* Modifiers to DELETE request */
+#define NLM_F_NONREC	0x100	/* Do not delete recursively	*/
+
+/* Flags for ACK message */
+#define NLM_F_CAPPED	0x100	/* request was capped */
+#define NLM_F_ACK_TLVS	0x200	/* extended ACK TVLs were included */
+
+/*
+   4.4BSD ADD		NLM_F_CREATE|NLM_F_EXCL
+   4.4BSD CHANGE	NLM_F_REPLACE
+
+   True CHANGE		NLM_F_CREATE|NLM_F_REPLACE
+   Append		NLM_F_CREATE
+   Check		NLM_F_EXCL
+ */
+
+#define NLMSG_ALIGNTO	4U
+#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
+#define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN)
+#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
+#define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
+#define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
+				  (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len)))
+#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \
+			   (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \
+			   (nlh)->nlmsg_len <= (len))
+#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len)))
+
+#define NLMSG_NOOP		0x1	/* Nothing.		*/
+#define NLMSG_ERROR		0x2	/* Error		*/
+#define NLMSG_DONE		0x3	/* End of a dump	*/
+#define NLMSG_OVERRUN		0x4	/* Data lost		*/
+
+#define NLMSG_MIN_TYPE		0x10	/* < 0x10: reserved control messages */
+
+struct nlmsgerr {
+	int		error;
+	struct nlmsghdr msg;
+	/*
+	 * followed by the message contents unless NETLINK_CAP_ACK was set
+	 * or the ACK indicates success (error == 0)
+	 * message length is aligned with NLMSG_ALIGN()
+	 */
+	/*
+	 * followed by TLVs defined in enum nlmsgerr_attrs
+	 * if NETLINK_EXT_ACK was set
+	 */
+};
+
+/**
+ * enum nlmsgerr_attrs - nlmsgerr attributes
+ * @NLMSGERR_ATTR_UNUSED: unused
+ * @NLMSGERR_ATTR_MSG: error message string (string)
+ * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original
+ *	 message, counting from the beginning of the header (u32)
+ * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
+ *	be used - in the success case - to identify a created
+ *	object or operation or similar (binary)
+ * @__NLMSGERR_ATTR_MAX: number of attributes
+ * @NLMSGERR_ATTR_MAX: highest attribute number
+ */
+enum nlmsgerr_attrs {
+	NLMSGERR_ATTR_UNUSED,
+	NLMSGERR_ATTR_MSG,
+	NLMSGERR_ATTR_OFFS,
+	NLMSGERR_ATTR_COOKIE,
+
+	__NLMSGERR_ATTR_MAX,
+	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
+};
+
+#define NETLINK_ADD_MEMBERSHIP		1
+#define NETLINK_DROP_MEMBERSHIP		2
+#define NETLINK_PKTINFO			3
+#define NETLINK_BROADCAST_ERROR		4
+#define NETLINK_NO_ENOBUFS		5
+#ifndef __KERNEL__
+#define NETLINK_RX_RING			6
+#define NETLINK_TX_RING			7
+#endif
+#define NETLINK_LISTEN_ALL_NSID		8
+#define NETLINK_LIST_MEMBERSHIPS	9
+#define NETLINK_CAP_ACK			10
+#define NETLINK_EXT_ACK			11
+
+struct nl_pktinfo {
+	__u32	group;
+};
+
+struct nl_mmap_req {
+	unsigned int	nm_block_size;
+	unsigned int	nm_block_nr;
+	unsigned int	nm_frame_size;
+	unsigned int	nm_frame_nr;
+};
+
+struct nl_mmap_hdr {
+	unsigned int	nm_status;
+	unsigned int	nm_len;
+	__u32		nm_group;
+	/* credentials */
+	__u32		nm_pid;
+	__u32		nm_uid;
+	__u32		nm_gid;
+};
+
+#ifndef __KERNEL__
+enum nl_mmap_status {
+	NL_MMAP_STATUS_UNUSED,
+	NL_MMAP_STATUS_RESERVED,
+	NL_MMAP_STATUS_VALID,
+	NL_MMAP_STATUS_COPY,
+	NL_MMAP_STATUS_SKIP,
+};
+
+#define NL_MMAP_MSG_ALIGNMENT		NLMSG_ALIGNTO
+#define NL_MMAP_MSG_ALIGN(sz)		__ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
+#define NL_MMAP_HDRLEN			NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
+
+#define NET_MAJOR 36		/* Major 36 is reserved for networking 						*/
+
+enum {
+	NETLINK_UNCONNECTED = 0,
+	NETLINK_CONNECTED,
+};
+
+/*
+ *  <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * |        Header       | Pad |     Payload       | Pad |
+ * |   (struct nlattr)   | ing |                   | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ *  <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr {
+	__u16           nla_len;
+	__u16           nla_type;
+};
+
+/*
+ * nla_type (16 bits)
+ * +---+---+-------------------------------+
+ * | N | O | Attribute Type                |
+ * +---+---+-------------------------------+
+ * N := Carries nested attributes
+ * O := Payload stored in network byte order
+ *
+ * Note: The N and O flag are mutually exclusive.
+ */
+#define NLA_F_NESTED		(1 << 15)
+#define NLA_F_NET_BYTEORDER	(1 << 14)
+#define NLA_TYPE_MASK		~(NLA_F_NESTED | NLA_F_NET_BYTEORDER)
+
+#define NLA_ALIGNTO		4
+#define NLA_ALIGN(len)		(((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN		((int) NLA_ALIGN(sizeof(struct nlattr)))
+
+/* Generic 32 bitflags attribute content sent to the kernel.
+ *
+ * The value is a bitmap that defines the values being set
+ * The selector is a bitmask that defines which value is legit
+ *
+ * Examples:
+ *  value = 0x0, and selector = 0x1
+ *  implies we are selecting bit 1 and we want to set its value to 0.
+ *
+ *  value = 0x2, and selector = 0x2
+ *  implies we are selecting bit 2 and we want to set its value to 1.
+ *
+ */
+struct nla_bitfield32 {
+	__u32 value;
+	__u32 selector;
+};
+
+#endif /* _UAPI__LINUX_NETLINK_H */

tools/lib/bpf/Build

-libbpf-y := libbpf.o bpf.o
+libbpf-y := libbpf.o bpf.o nlattr.o

tools/lib/bpf/Makefile

@@ -160,6 +160,12 @@ $(BPF_IN): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
 	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \
+	(diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
+	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)

tools/lib/bpf/bpf.c

+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * common eBPF ELF operations.
  *
@@ -25,6 +27,16 @@
 #include <asm/unistd.h>
 #include <linux/bpf.h>
 #include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+#include <linux/rtnetlink.h>
+#include <linux/if_link.h>
+#include <sys/socket.h>
+#include <errno.h>
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -46,7 +58,9 @@
 # endif
 #endif
 
+#ifndef min
 #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
 
 static inline __u64 ptr_to_u64(const void *ptr)
 {
@@ -413,3 +427,124 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
 
 	return err;
 }
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	struct sockaddr_nl sa;
+	int sock, seq = 0, len, ret = -1;
+	char buf[4096];
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	struct nlmsghdr *nh;
+	struct nlmsgerr *err;
+	socklen_t addrlen;
+	int one = 1;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0) {
+		return -errno;
+	}
+
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	addrlen = sizeof(sa);
+	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	if (addrlen != sizeof(sa)) {
+		ret = -LIBBPF_ERRNO__INTERNAL;
+		goto cleanup;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+	nla->nla_len = NLA_HDRLEN;
+
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+	nla_xdp->nla_type = IFLA_XDP_FD;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_FLAGS;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
+	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	len = recv(sock, buf, sizeof(buf), 0);
+	if (len < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+	     nh = NLMSG_NEXT(nh, len)) {
+		if (nh->nlmsg_pid != sa.nl_pid) {
+			ret = -LIBBPF_ERRNO__WRNGPID;
+			goto cleanup;
+		}
+		if (nh->nlmsg_seq != seq) {
+			ret = -LIBBPF_ERRNO__INVSEQ;
+			goto cleanup;
+		}
+		switch (nh->nlmsg_type) {
+		case NLMSG_ERROR:
+			err = (struct nlmsgerr *)NLMSG_DATA(nh);
+			if (!err->error)
+				continue;
+			ret = err->error;
+			nla_dump_errormsg(nh);
+			goto cleanup;
+		case NLMSG_DONE:
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = 0;
+
+cleanup:
+	close(sock);
+	return ret;
+}

tools/lib/bpf/bpf.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * common eBPF ELF operations.
  *

tools/lib/bpf/libbpf.c

+// SPDX-License-Identifier: LGPL-2.1
+
 /*
  * Common eBPF ELF object loading operations.
  *
@@ -106,6 +108,8 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
 	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
 	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
+	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
+	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
 };
 
 int libbpf_strerror(int err, char *buf, size_t size)

tools/lib/bpf/libbpf.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
 /*
  * Common eBPF ELF object loading operations.
  *
@@ -42,6 +44,8 @@ enum libbpf_errno {
 	LIBBPF_ERRNO__PROG2BIG,	/* Program too big */
 	LIBBPF_ERRNO__KVER,	/* Incorrect kernel version */
 	LIBBPF_ERRNO__PROGTYPE,	/* Kernel doesn't support this program type */
+	LIBBPF_ERRNO__WRNGPID,	/* Wrong pid in netlink message */
+	LIBBPF_ERRNO__INVSEQ,	/* Invalid netlink sequence */
 	__LIBBPF_ERRNO__END,
 };
 
@@ -246,4 +250,6 @@ long libbpf_get_error(const void *ptr);
 
 int bpf_prog_load(const char *file, enum bpf_prog_type type,
 		  struct bpf_object **pobj, int *prog_fd);
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif

tools/lib/bpf/nlattr.c

+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * NETLINK      Netlink attributes
+ *
+ *	This library is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU Lesser General Public
+ *	License as published by the Free Software Foundation version 2.1
+ *	of the License.
+ *
+ * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <errno.h>
+#include "nlattr.h"
+#include <linux/rtnetlink.h>
+#include <string.h>
+#include <stdio.h>
+
+static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
+	[NLA_U8]	= sizeof(uint8_t),
+	[NLA_U16]	= sizeof(uint16_t),
+	[NLA_U32]	= sizeof(uint32_t),
+	[NLA_U64]	= sizeof(uint64_t),
+	[NLA_STRING]	= 1,
+	[NLA_FLAG]	= 0,
+};
+
+static int nla_len(const struct nlattr *nla)
+{
+	return nla->nla_len - NLA_HDRLEN;
+}
+
+static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
+{
+	int totlen = NLA_ALIGN(nla->nla_len);
+
+	*remaining -= totlen;
+	return (struct nlattr *) ((char *) nla + totlen);
+}
+
+static int nla_ok(const struct nlattr *nla, int remaining)
+{
+	return remaining >= sizeof(*nla) &&
+	       nla->nla_len >= sizeof(*nla) &&
+	       nla->nla_len <= remaining;
+}
+
+static void *nla_data(const struct nlattr *nla)
+{
+	return (char *) nla + NLA_HDRLEN;
+}
+
+static int nla_type(const struct nlattr *nla)
+{
+	return nla->nla_type & NLA_TYPE_MASK;
+}
+
+static int validate_nla(struct nlattr *nla, int maxtype,
+			struct nla_policy *policy)
+{
+	struct nla_policy *pt;
+	unsigned int minlen = 0;
+	int type = nla_type(nla);
+
+	if (type < 0 || type > maxtype)
+		return 0;
+
+	pt = &policy[type];
+
+	if (pt->type > NLA_TYPE_MAX)
+		return 0;
+
+	if (pt->minlen)
+		minlen = pt->minlen;
+	else if (pt->type != NLA_UNSPEC)
+		minlen = nla_attr_minlen[pt->type];
+
+	if (nla_len(nla) < minlen)
+		return -1;
+
+	if (pt->maxlen && nla_len(nla) > pt->maxlen)
+		return -1;
+
+	if (pt->type == NLA_STRING) {
+		char *data = nla_data(nla);
+		if (data[nla_len(nla) - 1] != '\0')
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int nlmsg_len(const struct nlmsghdr *nlh)
+{
+	return nlh->nlmsg_len - NLMSG_HDRLEN;
+}
+
+/**
+ * Create attribute index based on a stream of attributes.
+ * @arg tb		Index array to be filled (maxtype+1 elements).
+ * @arg maxtype		Maximum attribute type expected and accepted.
+ * @arg head		Head of attribute stream.
+ * @arg len		Length of attribute stream.
+ * @arg policy		Attribute validation policy.
+ *
+ * Iterates over the stream of attributes and stores a pointer to each
+ * attribute in the index array using the attribute type as index to
+ * the array. Attribute with a type greater than the maximum type
+ * specified will be silently ignored in order to maintain backwards
+ * compatibility. If \a policy is not NULL, the attribute will be
+ * validated using the specified policy.
+ *
+ * @see nla_validate
+ * @return 0 on success or a negative error code.
+ */
+static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+		     struct nla_policy *policy)
+{
+	struct nlattr *nla;
+	int rem, err;
+
+	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+	nla_for_each_attr(nla, head, len, rem) {
+		int type = nla_type(nla);
+
+		if (type > maxtype)
+			continue;
+
+		if (policy) {
+			err = validate_nla(nla, maxtype, policy);
+			if (err < 0)
+				goto errout;
+		}
+
+		if (tb[type])
+			fprintf(stderr, "Attribute of type %#x found multiple times in message, "
+				  "previous attribute is being ignored.\n", type);
+
+		tb[type] = nla;
+	}
+
+	err = 0;
+errout:
+	return err;
+}
+
+/* dump netlink extended ack error message */
+int nla_dump_errormsg(struct nlmsghdr *nlh)
+{
+	struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = {
+		[NLMSGERR_ATTR_MSG]	= { .type = NLA_STRING },
+		[NLMSGERR_ATTR_OFFS]	= { .type = NLA_U32 },
+	};
+	struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr;
+	struct nlmsgerr *err;
+	char *errmsg = NULL;
+	int hlen, alen;
+
+	/* no TLVs, nothing to do here */
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+		return 0;
+
+	err = (struct nlmsgerr *)NLMSG_DATA(nlh);
+	hlen = sizeof(*err);
+
+	/* if NLM_F_CAPPED is set then the inner err msg was capped */
+	if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+		hlen += nlmsg_len(&err->msg);
+
+	attr = (struct nlattr *) ((void *) err + hlen);
+	alen = nlh->nlmsg_len - hlen;
+
+	if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) {
+		fprintf(stderr,
+			"Failed to parse extended error attributes\n");
+		return 0;
+	}
+
+	if (tb[NLMSGERR_ATTR_MSG])
+		errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]);
+
+	fprintf(stderr, "Kernel error message: %s\n", errmsg);
+
+	return 0;
+}

tools/lib/bpf/nlattr.h

+/* SPDX-License-Identifier: LGPL-2.1 */
+
+/*
+ * NETLINK      Netlink attributes
+ *
+ *	This library is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU Lesser General Public
+ *	License as published by the Free Software Foundation version 2.1
+ *	of the License.
+ *
+ * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch>
+ */
+
+#ifndef __NLATTR_H
+#define __NLATTR_H
+
+#include <stdint.h>
+#include <linux/netlink.h>
+/* avoid multiple definition of netlink features */
+#define __LINUX_NETLINK_H
+
+/**
+ * Standard attribute types to specify validation policy
+ */
+enum {
+	NLA_UNSPEC,	/**< Unspecified type, binary data chunk */
+	NLA_U8,		/**< 8 bit integer */
+	NLA_U16,	/**< 16 bit integer */
+	NLA_U32,	/**< 32 bit integer */
+	NLA_U64,	/**< 64 bit integer */
+	NLA_STRING,	/**< NUL terminated character string */
+	NLA_FLAG,	/**< Flag */
+	NLA_MSECS,	/**< Micro seconds (64bit) */
+	NLA_NESTED,	/**< Nested attributes */
+	__NLA_TYPE_MAX,
+};
+
+#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1)
+
+/**
+ * @ingroup attr
+ * Attribute validation policy.
+ *
+ * See section @core_doc{core_attr_parse,Attribute Parsing} for more details.
+ */
+struct nla_policy {
+	/** Type of attribute or NLA_UNSPEC */
+	uint16_t	type;
+
+	/** Minimal length of payload required */
+	uint16_t	minlen;
+
+	/** Maximal length of payload allowed */
+	uint16_t	maxlen;
+};
+
+/**
+ * @ingroup attr
+ * Iterate over a stream of attributes
+ * @arg pos	loop counter, set to current attribute
+ * @arg head	head of attribute stream
+ * @arg len	length of attribute stream
+ * @arg rem	initialized to len, holds bytes currently remaining in stream
+ */
+#define nla_for_each_attr(pos, head, len, rem) \
+	for (pos = head, rem = len; \
+	     nla_ok(pos, rem); \
+	     pos = nla_next(pos, &(rem)))
+
+int nla_dump_errormsg(struct nlmsghdr *nlh);
+
+#endif /* __NLATTR_H */

tools/testing/selftests/bpf/.gitignore

@@ -8,5 +8,6 @@ fixdep
 test_align
 test_dev_cgroup
 test_progs
+test_tcpbpf_user
 test_verifier_log
 feature

tools/testing/selftests/bpf/Makefile

@@ -27,7 +27,7 @@ TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/libbpf.a $(OUTPUT)/cgroup_helpers.c
+BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
@@ -58,7 +58,7 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
-%.o: %.c
+$(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
 		 -O2 -target bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@

tools/testing/selftests/bpf/test_verifier.c

@@ -7779,6 +7779,20 @@ static struct bpf_test tests[] = {
 		.errstr = "unknown opcode d7",
 		.result = REJECT,
 	},
+	{
+		"XDP, using ifindex from netdev",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, ingress_ifindex)),
+			BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 1, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.retval = 1,
+	},
 	{
 		"meta access, test1",
 		.insns = {