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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

3 files changed, 121 insertions, 57 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index f30106459a32..3ef2e0e797e8 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -424,6 +424,38 @@ static void kauditd_send_skb(struct sk_buff *skb)
 }
 
 /*
+ * kauditd_send_multicast_skb - send the skb to multicast userspace listeners
+ *
+ * This function doesn't consume an skb as might be expected since it has to
+ * copy it anyways.
+ */
+static void kauditd_send_multicast_skb(struct sk_buff *skb)
+{
+	struct sk_buff		*copy;
+	struct audit_net	*aunet = net_generic(&init_net, audit_net_id);
+	struct sock		*sock = aunet->nlsk;
+
+	if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG))
+		return;
+
+	/*
+	 * The seemingly wasteful skb_copy() rather than bumping the refcount
+	 * using skb_get() is necessary because non-standard mods are made to
+	 * the skb by the original kaudit unicast socket send routine.  The
+	 * existing auditd daemon assumes this breakage.  Fixing this would
+	 * require co-ordinating a change in the established protocol between
+	 * the kaudit kernel subsystem and the auditd userspace code.  There is
+	 * no reason for new multicast clients to continue with this
+	 * non-compliance.
+	 */
+	copy = skb_copy(skb, GFP_KERNEL);
+	if (!copy)
+		return;
+
+	nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL);
+}
+
+/*
  * flush_hold_queue - empty the hold queue if auditd appears
  *
  * If auditd just started, drain the queue of messages already
@@ -1076,10 +1108,22 @@ static void audit_receive(struct sk_buff  *skb)
 	mutex_unlock(&audit_cmd_mutex);
 }
 
+/* Run custom bind function on netlink socket group connect or bind requests. */
+static int audit_bind(int group)
+{
+	if (!capable(CAP_AUDIT_READ))
+		return -EPERM;
+
+	return 0;
+}
+
 static int __net_init audit_net_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input	= audit_receive,
+		.bind	= audit_bind,
+		.flags	= NL_CFG_F_NONROOT_RECV,
+		.groups	= AUDIT_NLGRP_MAX,
 	};
 
 	struct audit_net *aunet = net_generic(net, audit_net_id);
@@ -1901,10 +1945,10 @@ out:
  * audit_log_end - end one audit record
  * @ab: the audit_buffer
  *
- * The netlink_* functions cannot be called inside an irq context, so
- * the audit buffer is placed on a queue and a tasklet is scheduled to
- * remove them from the queue outside the irq context.  May be called in
- * any context.
+ * netlink_unicast() cannot be called inside an irq context because it blocks
+ * (last arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed
+ * on a queue and a tasklet is scheduled to remove them from the queue outside
+ * the irq context.  May be called in any context.
  */
 void audit_log_end(struct audit_buffer *ab)
 {
@@ -1914,6 +1958,18 @@ void audit_log_end(struct audit_buffer *ab)
 		audit_log_lost("rate limit exceeded");
 	} else {
 		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
+
+		kauditd_send_multicast_skb(ab->skb);
+
+		/*
+		 * The original kaudit unicast socket sends up messages with
+		 * nlmsg_len set to the payload length rather than the entire
+		 * message length.  This breaks the standard set by netlink.
+		 * The existing auditd daemon assumes this breakage.  Fixing
+		 * this would require co-ordinating a change in the established
+		 * protocol between the kaudit kernel subsystem and the auditd
+		 * userspace code.
+		 */
 		nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN;
 
 		if (audit_pid) {
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f6d76bebe69f..301bbc24739c 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -54,8 +54,7 @@
 struct seccomp_filter {
 	atomic_t usage;
 	struct seccomp_filter *prev;
-	unsigned short len;  /* Instruction count */
-	struct sock_filter_int insnsi[];
+	struct sk_filter *prog;
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
@@ -104,60 +103,59 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 		u32 k = ftest->k;
 
 		switch (code) {
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
 			/* 32-bit aligned and not out of bounds. */
 			if (k >= sizeof(struct seccomp_data) || k & 3)
 				return -EINVAL;
 			continue;
-		case BPF_S_LD_W_LEN:
+		case BPF_LD | BPF_W | BPF_LEN:
 			ftest->code = BPF_LD | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
-		case BPF_S_LDX_W_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
 			ftest->code = BPF_LDX | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
 		/* Explicitly include allowed calls. */
-		case BPF_S_RET_K:
-		case BPF_S_RET_A:
-		case BPF_S_ALU_ADD_K:
-		case BPF_S_ALU_ADD_X:
-		case BPF_S_ALU_SUB_K:
-		case BPF_S_ALU_SUB_X:
-		case BPF_S_ALU_MUL_K:
-		case BPF_S_ALU_MUL_X:
-		case BPF_S_ALU_DIV_X:
-		case BPF_S_ALU_AND_K:
-		case BPF_S_ALU_AND_X:
-		case BPF_S_ALU_OR_K:
-		case BPF_S_ALU_OR_X:
-		case BPF_S_ALU_XOR_K:
-		case BPF_S_ALU_XOR_X:
-		case BPF_S_ALU_LSH_K:
-		case BPF_S_ALU_LSH_X:
-		case BPF_S_ALU_RSH_K:
-		case BPF_S_ALU_RSH_X:
-		case BPF_S_ALU_NEG:
-		case BPF_S_LD_IMM:
-		case BPF_S_LDX_IMM:
-		case BPF_S_MISC_TAX:
-		case BPF_S_MISC_TXA:
-		case BPF_S_ALU_DIV_K:
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
-		case BPF_S_ST:
-		case BPF_S_STX:
-		case BPF_S_JMP_JA:
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_K:
-		case BPF_S_JMP_JSET_X:
-			sk_decode_filter(ftest, ftest);
+		case BPF_RET | BPF_K:
+		case BPF_RET | BPF_A:
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_LSH | BPF_X:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_X:
+		case BPF_ALU | BPF_NEG:
+		case BPF_LD | BPF_IMM:
+		case BPF_LDX | BPF_IMM:
+		case BPF_MISC | BPF_TAX:
+		case BPF_MISC | BPF_TXA:
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+		case BPF_ST:
+		case BPF_STX:
+		case BPF_JMP | BPF_JA:
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			continue;
 		default:
 			return -EINVAL;
@@ -189,7 +187,8 @@ static u32 seccomp_run_filters(int syscall)
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (f = current->seccomp.filter; f; f = f->prev) {
-		u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
+		u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd);
+
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;
 	}
@@ -215,7 +214,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 		return -EINVAL;
 
 	for (filter = current->seccomp.filter; filter; filter = filter->prev)
-		total_insns += filter->len + 4;  /* include a 4 instr penalty */
+		total_insns += filter->prog->len + 4;  /* include a 4 instr penalty */
 	if (total_insns > MAX_INSNS_PER_PATH)
 		return -ENOMEM;
 
@@ -256,19 +255,25 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 
 	/* Allocate a new seccomp_filter */
 	ret = -ENOMEM;
-	filter = kzalloc(sizeof(struct seccomp_filter) +
-			 sizeof(struct sock_filter_int) * new_len,
+	filter = kzalloc(sizeof(struct seccomp_filter),
 			 GFP_KERNEL|__GFP_NOWARN);
 	if (!filter)
 		goto free_prog;
 
-	ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
-	if (ret)
+	filter->prog = kzalloc(sk_filter_size(new_len),
+			       GFP_KERNEL|__GFP_NOWARN);
+	if (!filter->prog)
 		goto free_filter;
+
+	ret = sk_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len);
+	if (ret)
+		goto free_filter_prog;
 	kfree(fp);
 
 	atomic_set(&filter->usage, 1);
-	filter->len = new_len;
+	filter->prog->len = new_len;
+
+	sk_filter_select_runtime(filter->prog);
 
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
@@ -278,6 +283,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	current->seccomp.filter = filter;
 	return 0;
 
+free_filter_prog:
+	kfree(filter->prog);
 free_filter:
 	kfree(filter);
 free_prog:
@@ -330,6 +337,7 @@ void put_seccomp_filter(struct task_struct *tsk)
 	while (orig && atomic_dec_and_test(&orig->usage)) {
 		struct seccomp_filter *freeme = orig;
 		orig = orig->prev;
+		sk_filter_free(freeme->prog);
 		kfree(freeme);
 	}
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db19e3e2aa4b..ba9ed453c4ed 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2568,11 +2568,11 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 	bool first = 1;
 	size_t left = *lenp;
 	unsigned long bitmap_len = table->maxlen;
-	unsigned long *bitmap = (unsigned long *) table->data;
+	unsigned long *bitmap = *(unsigned long **) table->data;
 	unsigned long *tmp_bitmap = NULL;
 	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
 
-	if (!bitmap_len || !left || (*ppos && !write)) {
+	if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}