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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 95 insertions, 186 deletions

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f95a150..b8ab5c8 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -184,25 +184,44 @@
 
 #define func_enter() pr_debug("entering %s\n", __func__);
 
+#define PKT_FLAGS							\
+	pf(IPV6)		/* Interface in IPV6 Mode */		\
+	pf(IPSRC_RND)		/* IP-Src Random  */			\
+	pf(IPDST_RND)		/* IP-Dst Random  */			\
+	pf(TXSIZE_RND)		/* Transmit size is random */		\
+	pf(UDPSRC_RND)		/* UDP-Src Random */			\
+	pf(UDPDST_RND)		/* UDP-Dst Random */			\
+	pf(UDPCSUM)		/* Include UDP checksum */		\
+	pf(NO_TIMESTAMP)	/* Don't timestamp packets (default TS) */ \
+	pf(MPLS_RND)		/* Random MPLS labels */		\
+	pf(QUEUE_MAP_RND)	/* queue map Random */			\
+	pf(QUEUE_MAP_CPU)	/* queue map mirrors smp_processor_id() */ \
+	pf(FLOW_SEQ)		/* Sequential flows */			\
+	pf(IPSEC)		/* ipsec on for flows */		\
+	pf(MACSRC_RND)		/* MAC-Src Random */			\
+	pf(MACDST_RND)		/* MAC-Dst Random */			\
+	pf(VID_RND)		/* Random VLAN ID */			\
+	pf(SVID_RND)		/* Random SVLAN ID */			\
+	pf(NODE)		/* Node memory alloc*/			\
+
+#define pf(flag)		flag##_SHIFT,
+enum pkt_flags {
+	PKT_FLAGS
+};
+#undef pf
+
 /* Device flag bits */
-#define F_IPSRC_RND   (1<<0)	/* IP-Src Random  */
-#define F_IPDST_RND   (1<<1)	/* IP-Dst Random  */
-#define F_UDPSRC_RND  (1<<2)	/* UDP-Src Random */
-#define F_UDPDST_RND  (1<<3)	/* UDP-Dst Random */
-#define F_MACSRC_RND  (1<<4)	/* MAC-Src Random */
-#define F_MACDST_RND  (1<<5)	/* MAC-Dst Random */
-#define F_TXSIZE_RND  (1<<6)	/* Transmit size is random */
-#define F_IPV6        (1<<7)	/* Interface in IPV6 Mode */
-#define F_MPLS_RND    (1<<8)	/* Random MPLS labels */
-#define F_VID_RND     (1<<9)	/* Random VLAN ID */
-#define F_SVID_RND    (1<<10)	/* Random SVLAN ID */
-#define F_FLOW_SEQ    (1<<11)	/* Sequential flows */
-#define F_IPSEC_ON    (1<<12)	/* ipsec on for flows */
-#define F_QUEUE_MAP_RND (1<<13)	/* queue map Random */
-#define F_QUEUE_MAP_CPU (1<<14)	/* queue map mirrors smp_processor_id() */
-#define F_NODE          (1<<15)	/* Node memory alloc*/
-#define F_UDPCSUM       (1<<16)	/* Include UDP checksum */
-#define F_NO_TIMESTAMP  (1<<17)	/* Don't timestamp packets (default TS) */
+#define pf(flag)		static const __u32 F_##flag = (1<<flag##_SHIFT);
+PKT_FLAGS
+#undef pf
+
+#define pf(flag)		__stringify(flag),
+static char *pkt_flag_names[] = {
+	PKT_FLAGS
+};
+#undef pf
+
+#define NR_PKT_FLAGS		ARRAY_SIZE(pkt_flag_names)
 
 /* Thread control flag bits */
 #define T_STOP        (1<<0)	/* Stop run */
@@ -399,7 +418,7 @@ struct pktgen_dev {
 	__u8	ipsmode;		/* IPSEC mode (config) */
 	__u8	ipsproto;		/* IPSEC type (config) */
 	__u32	spi;
-	struct dst_entry dst;
+	struct xfrm_dst xdst;
 	struct dst_ops dstops;
 #endif
 	char result[512];
@@ -523,7 +542,6 @@ static int pgctrl_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations pktgen_fops = {
-	.owner   = THIS_MODULE,
 	.open    = pgctrl_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
@@ -535,6 +553,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 {
 	const struct pktgen_dev *pkt_dev = seq->private;
 	ktime_t stopped;
+	unsigned int i;
 	u64 idle;
 
 	seq_printf(seq,
@@ -596,7 +615,6 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 		   pkt_dev->src_mac_count, pkt_dev->dst_mac_count);
 
 	if (pkt_dev->nr_labels) {
-		unsigned int i;
 		seq_puts(seq, "     mpls: ");
 		for (i = 0; i < pkt_dev->nr_labels; i++)
 			seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
@@ -632,68 +650,21 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 
 	seq_puts(seq, "     Flags: ");
 
-	if (pkt_dev->flags & F_IPV6)
-		seq_puts(seq, "IPV6  ");
-
-	if (pkt_dev->flags & F_IPSRC_RND)
-		seq_puts(seq, "IPSRC_RND  ");
-
-	if (pkt_dev->flags & F_IPDST_RND)
-		seq_puts(seq, "IPDST_RND  ");
-
-	if (pkt_dev->flags & F_TXSIZE_RND)
-		seq_puts(seq, "TXSIZE_RND  ");
-
-	if (pkt_dev->flags & F_UDPSRC_RND)
-		seq_puts(seq, "UDPSRC_RND  ");
-
-	if (pkt_dev->flags & F_UDPDST_RND)
-		seq_puts(seq, "UDPDST_RND  ");
-
-	if (pkt_dev->flags & F_UDPCSUM)
-		seq_puts(seq, "UDPCSUM  ");
-
-	if (pkt_dev->flags & F_NO_TIMESTAMP)
-		seq_puts(seq, "NO_TIMESTAMP  ");
-
-	if (pkt_dev->flags & F_MPLS_RND)
-		seq_puts(seq,  "MPLS_RND  ");
-
-	if (pkt_dev->flags & F_QUEUE_MAP_RND)
-		seq_puts(seq,  "QUEUE_MAP_RND  ");
+	for (i = 0; i < NR_PKT_FLAGS; i++) {
+		if (i == F_FLOW_SEQ)
+			if (!pkt_dev->cflows)
+				continue;
 
-	if (pkt_dev->flags & F_QUEUE_MAP_CPU)
-		seq_puts(seq,  "QUEUE_MAP_CPU  ");
-
-	if (pkt_dev->cflows) {
-		if (pkt_dev->flags & F_FLOW_SEQ)
-			seq_puts(seq,  "FLOW_SEQ  "); /*in sequence flows*/
-		else
-			seq_puts(seq,  "FLOW_RND  ");
-	}
+		if (pkt_dev->flags & (1 << i))
+			seq_printf(seq, "%s  ", pkt_flag_names[i]);
+		else if (i == F_FLOW_SEQ)
+			seq_puts(seq, "FLOW_RND  ");
 
 #ifdef CONFIG_XFRM
-	if (pkt_dev->flags & F_IPSEC_ON) {
-		seq_puts(seq,  "IPSEC  ");
-		if (pkt_dev->spi)
+		if (i == F_IPSEC && pkt_dev->spi)
 			seq_printf(seq, "spi:%u", pkt_dev->spi);
-	}
 #endif
-
-	if (pkt_dev->flags & F_MACSRC_RND)
-		seq_puts(seq, "MACSRC_RND  ");
-
-	if (pkt_dev->flags & F_MACDST_RND)
-		seq_puts(seq, "MACDST_RND  ");
-
-	if (pkt_dev->flags & F_VID_RND)
-		seq_puts(seq, "VID_RND  ");
-
-	if (pkt_dev->flags & F_SVID_RND)
-		seq_puts(seq, "SVID_RND  ");
-
-	if (pkt_dev->flags & F_NODE)
-		seq_puts(seq, "NODE_ALLOC  ");
+	}
 
 	seq_puts(seq, "\n");
 
@@ -859,6 +830,35 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
 	return i;
 }
 
+static __u32 pktgen_read_flag(const char *f, bool *disable)
+{
+	__u32 i;
+
+	if (f[0] == '!') {
+		*disable = true;
+		f++;
+	}
+
+	for (i = 0; i < NR_PKT_FLAGS; i++) {
+		if (!IS_ENABLED(CONFIG_XFRM) && i == IPSEC_SHIFT)
+			continue;
+
+		/* allow only disabling ipv6 flag */
+		if (!*disable && i == IPV6_SHIFT)
+			continue;
+
+		if (strcmp(f, pkt_flag_names[i]) == 0)
+			return 1 << i;
+	}
+
+	if (strcmp(f, "FLOW_RND") == 0) {
+		*disable = !*disable;
+		return F_FLOW_SEQ;
+	}
+
+	return 0;
+}
+
 static ssize_t pktgen_if_write(struct file *file,
 			       const char __user * user_buffer, size_t count,
 			       loff_t * offset)
@@ -1216,7 +1216,10 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "flag")) {
+		__u32 flag;
 		char f[32];
+		bool disable = false;
+
 		memset(f, 0, 32);
 		len = strn_len(&user_buffer[i], sizeof(f) - 1);
 		if (len < 0)
@@ -1225,107 +1228,15 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
 		i += len;
-		if (strcmp(f, "IPSRC_RND") == 0)
-			pkt_dev->flags |= F_IPSRC_RND;
-
-		else if (strcmp(f, "!IPSRC_RND") == 0)
-			pkt_dev->flags &= ~F_IPSRC_RND;
-
-		else if (strcmp(f, "TXSIZE_RND") == 0)
-			pkt_dev->flags |= F_TXSIZE_RND;
-
-		else if (strcmp(f, "!TXSIZE_RND") == 0)
-			pkt_dev->flags &= ~F_TXSIZE_RND;
-
-		else if (strcmp(f, "IPDST_RND") == 0)
-			pkt_dev->flags |= F_IPDST_RND;
-
-		else if (strcmp(f, "!IPDST_RND") == 0)
-			pkt_dev->flags &= ~F_IPDST_RND;
-
-		else if (strcmp(f, "UDPSRC_RND") == 0)
-			pkt_dev->flags |= F_UDPSRC_RND;
-
-		else if (strcmp(f, "!UDPSRC_RND") == 0)
-			pkt_dev->flags &= ~F_UDPSRC_RND;
-
-		else if (strcmp(f, "UDPDST_RND") == 0)
-			pkt_dev->flags |= F_UDPDST_RND;
-
-		else if (strcmp(f, "!UDPDST_RND") == 0)
-			pkt_dev->flags &= ~F_UDPDST_RND;
-
-		else if (strcmp(f, "MACSRC_RND") == 0)
-			pkt_dev->flags |= F_MACSRC_RND;
-
-		else if (strcmp(f, "!MACSRC_RND") == 0)
-			pkt_dev->flags &= ~F_MACSRC_RND;
-
-		else if (strcmp(f, "MACDST_RND") == 0)
-			pkt_dev->flags |= F_MACDST_RND;
-
-		else if (strcmp(f, "!MACDST_RND") == 0)
-			pkt_dev->flags &= ~F_MACDST_RND;
-
-		else if (strcmp(f, "MPLS_RND") == 0)
-			pkt_dev->flags |= F_MPLS_RND;
-
-		else if (strcmp(f, "!MPLS_RND") == 0)
-			pkt_dev->flags &= ~F_MPLS_RND;
 
-		else if (strcmp(f, "VID_RND") == 0)
-			pkt_dev->flags |= F_VID_RND;
+		flag = pktgen_read_flag(f, &disable);
 
-		else if (strcmp(f, "!VID_RND") == 0)
-			pkt_dev->flags &= ~F_VID_RND;
-
-		else if (strcmp(f, "SVID_RND") == 0)
-			pkt_dev->flags |= F_SVID_RND;
-
-		else if (strcmp(f, "!SVID_RND") == 0)
-			pkt_dev->flags &= ~F_SVID_RND;
-
-		else if (strcmp(f, "FLOW_SEQ") == 0)
-			pkt_dev->flags |= F_FLOW_SEQ;
-
-		else if (strcmp(f, "QUEUE_MAP_RND") == 0)
-			pkt_dev->flags |= F_QUEUE_MAP_RND;
-
-		else if (strcmp(f, "!QUEUE_MAP_RND") == 0)
-			pkt_dev->flags &= ~F_QUEUE_MAP_RND;
-
-		else if (strcmp(f, "QUEUE_MAP_CPU") == 0)
-			pkt_dev->flags |= F_QUEUE_MAP_CPU;
-
-		else if (strcmp(f, "!QUEUE_MAP_CPU") == 0)
-			pkt_dev->flags &= ~F_QUEUE_MAP_CPU;
-#ifdef CONFIG_XFRM
-		else if (strcmp(f, "IPSEC") == 0)
-			pkt_dev->flags |= F_IPSEC_ON;
-#endif
-
-		else if (strcmp(f, "!IPV6") == 0)
-			pkt_dev->flags &= ~F_IPV6;
-
-		else if (strcmp(f, "NODE_ALLOC") == 0)
-			pkt_dev->flags |= F_NODE;
-
-		else if (strcmp(f, "!NODE_ALLOC") == 0)
-			pkt_dev->flags &= ~F_NODE;
-
-		else if (strcmp(f, "UDPCSUM") == 0)
-			pkt_dev->flags |= F_UDPCSUM;
-
-		else if (strcmp(f, "!UDPCSUM") == 0)
-			pkt_dev->flags &= ~F_UDPCSUM;
-
-		else if (strcmp(f, "NO_TIMESTAMP") == 0)
-			pkt_dev->flags |= F_NO_TIMESTAMP;
-
-		else if (strcmp(f, "!NO_TIMESTAMP") == 0)
-			pkt_dev->flags &= ~F_NO_TIMESTAMP;
-
-		else {
+		if (flag) {
+			if (disable)
+				pkt_dev->flags &= ~flag;
+			else
+				pkt_dev->flags |= flag;
+		} else {
 			sprintf(pg_result,
 				"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
 				f,
@@ -1804,7 +1715,6 @@ static int pktgen_if_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations pktgen_if_fops = {
-	.owner   = THIS_MODULE,
 	.open    = pktgen_if_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
@@ -1942,7 +1852,6 @@ static int pktgen_thread_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations pktgen_thread_fops = {
-	.owner   = THIS_MODULE,
 	.open    = pktgen_thread_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
@@ -2544,7 +2453,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 				pkt_dev->flows[flow].cur_daddr =
 				    pkt_dev->cur_daddr;
 #ifdef CONFIG_XFRM
-				if (pkt_dev->flags & F_IPSEC_ON)
+				if (pkt_dev->flags & F_IPSEC)
 					get_ipsec_sa(pkt_dev, flow);
 #endif
 				pkt_dev->nflows++;
@@ -2609,7 +2518,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 	 * supports both transport/tunnel mode + ESP/AH type.
 	 */
 	if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0))
-		skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF;
+		skb->_skb_refdst = (unsigned long)&pkt_dev->xdst.u.dst | SKB_DST_NOREF;
 
 	rcu_read_lock_bh();
 	err = x->outer_mode->output(x, skb);
@@ -2649,7 +2558,7 @@ static void free_SAs(struct pktgen_dev *pkt_dev)
 static int process_ipsec(struct pktgen_dev *pkt_dev,
 			      struct sk_buff *skb, __be16 protocol)
 {
-	if (pkt_dev->flags & F_IPSEC_ON) {
+	if (pkt_dev->flags & F_IPSEC) {
 		struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x;
 		int nhead = 0;
 		if (x) {
@@ -3742,10 +3651,10 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 	 * performance under such circumstance.
 	 */
 	pkt_dev->dstops.family = AF_INET;
-	pkt_dev->dst.dev = pkt_dev->odev;
-	dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false);
-	pkt_dev->dst.child = &pkt_dev->dst;
-	pkt_dev->dst.ops = &pkt_dev->dstops;
+	pkt_dev->xdst.u.dst.dev = pkt_dev->odev;
+	dst_init_metrics(&pkt_dev->xdst.u.dst, pktgen_dst_metrics, false);
+	pkt_dev->xdst.child = &pkt_dev->xdst.u.dst;
+	pkt_dev->xdst.u.dst.ops = &pkt_dev->dstops;
 #endif
 
 	return add_dev_to_thread(t, pkt_dev);