Linux 3.4.88

commit dfccbb5e49 upstream.

wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and
drops tasklist_lock.  If this task is not the natural child and it is
traced, we change its state back to EXIT_ZOMBIE for ->real_parent.

The last transition is racy, this is even documented in 50b8d25748
"ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE
race".  wait_consider_task() tries to detect this transition and clear
->notask_error but we can't rely on ptrace_reparented(), debugger can
exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.

And there is another problem which were missed before: this transition
can also race with reparent_leader() which doesn't reset >exit_signal if
EXIT_DEAD, assuming that this task must be reaped by someone else.  So
the tracee can be re-parented with ->exit_signal != SIGCHLD, and if
/sbin/init doesn't use __WALL it becomes unreapable.

Change reparent_leader() to update ->exit_signal even if EXIT_DEAD.
Note: this is the simple temporary hack for -stable, it doesn't try to
solve all problems, it will be reverted by the next changes.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com>
Reported-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Michal Schmidt <mschmidt@redhat.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Lennart Poettering <lpoetter@redhat.com>
Cc: Roland McGrath <roland@hack.frob.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 87
+SUBLEVEL = 88
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

arch/sparc/Kconfig

@@ -24,7 +24,7 @@ config SPARC
 	select HAVE_IRQ_WORK
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select USE_GENERIC_SMP_HELPERS if SMP

arch/sparc/include/asm/uaccess_64.h

@@ -266,8 +266,8 @@ extern long __strnlen_user(const char __user *, long len);
 
 #define strlen_user __strlen_user
 #define strnlen_user __strnlen_user
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
 #endif  /* __ASSEMBLY__ */
 

arch/sparc/kernel/pci.c

@@ -486,8 +486,8 @@ static void __devinit apb_fake_ranges(struct pci_dev *dev,
 	apb_calc_first_last(map, &first, &last);
 	res = bus->resource[1];
 	res->flags = IORESOURCE_MEM;
-	region.start = (first << 21);
-	region.end = (last << 21) + ((1 << 21) - 1);
+	region.start = (first << 29);
+	region.end = (last << 29) + ((1 << 29) - 1);
 	pcibios_bus_to_resource(dev, res, &region);
 }
 

arch/sparc/kernel/syscalls.S

@@ -184,7 +184,8 @@ linux_sparc_syscall32:
 	 mov	%i0, %l5				! IEU1
 5:	call	%l7					! CTI	Group brk forced
 	 srl	%i5, 0, %o5				! IEU1
-	ba,a,pt	%xcc, 3f
+	ba,pt	%xcc, 3f
+	 sra	%o0, 0, %o0
 
 	/* Linux native system calls enter here... */
 	.align	32
@@ -212,7 +213,6 @@ linux_sparc_syscall:
 3:	stx	%o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
 	ldx	[%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-	sra	%o0, 0, %o0
 	mov	%ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
 	sllx	%g2, 32, %g2
 

drivers/char/ipmi/ipmi_bt_sm.c

@@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt)
 
 static inline int read_all_bytes(struct si_sm_data *bt)
 {
-	unsigned char i;
+	unsigned int i;
 
 	/*
 	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.

drivers/isdn/isdnloop/isdnloop.c

@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card *card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }
@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
 	case 7:
 		/* 0x;EAZ */
 		p += 3;
+		if (strlen(p) >= sizeof(card->eazlist[0]))
+			break;
 		strcpy(card->eazlist[ch - 1], p);
 		break;
 	case 8:
@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 	case ISDN_PTYPE_EURO:
@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;
 
@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			break;
 		if ((c->arg & 255) < ISDNLOOP_BCH) {
 			char *p;
-			char dial[50];
 			char dcode[4];
 
 			a = c->arg;
@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			} else
 				/* Normal Dial */
 				strcpy(dcode, "CAL");
-			strcpy(dial, p);
-			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-				dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+			snprintf(cbuf, sizeof(cbuf),
+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+				 dcode, p, c->parm.setup.si1,
+				 c->parm.setup.si2, c->parm.setup.eazmsn);
 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 		}
 		break;

drivers/net/xen-netback/netback.c

@@ -338,8 +338,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;

drivers/vhost/net.c

@@ -324,9 +324,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;
@@ -351,6 +355,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -405,6 +415,14 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {

fs/jffs2/compr_rtime.c

@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in,
 				unsigned char *cpage_out,
 				uint32_t *sourcelen, uint32_t *dstlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 
@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in,
 				  unsigned char *cpage_out,
 				  uint32_t srclen, uint32_t destlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 

fs/jffs2/nodelist.h

@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
 	uint32_t version;
 	uint32_t data_crc;
 	uint32_t partial_crc;
-	uint16_t csize;
+	uint32_t csize;
 	uint16_t overlapped;
 };
 

fs/jffs2/nodemgmt.c

@@ -139,6 +139,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
+					remove_wait_queue(&c->erase_wait, &wait);
 				} else
 					spin_unlock(&c->erase_completion_lock);
 			} else if (ret)
@@ -169,20 +170,25 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 			   uint32_t *len, uint32_t sumsize)
 {
-	int ret = -EAGAIN;
+	int ret;
 	minsize = PAD(minsize);
 
 	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
 
-	spin_lock(&c->erase_completion_lock);
-	while(ret == -EAGAIN) {
+	while (true) {
+		spin_lock(&c->erase_completion_lock);
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
 			jffs2_dbg(1, "%s(): looping, ret is %d\n",
 				  __func__, ret);
 		}
+		spin_unlock(&c->erase_completion_lock);
+
+		if (ret == -EAGAIN)
+			cond_resched();
+		else
+			break;
 	}
-	spin_unlock(&c->erase_completion_lock);
 	if (!ret)
 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
 

kernel/exit.c

@@ -761,9 +761,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.
@@ -771,9 +768,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/*
+	 * We don't want people slaying init.
+	 *
+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+	 * state, do_notify_parent() was already called and ->exit_signal
+	 * doesn't matter.
+	 */
 	p->exit_signal = SIGCHLD;
 
+	if (p->exit_state == EXIT_DEAD)
+		return;
+
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {

lib/nlattr.c

@@ -299,9 +299,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);
 

net/8021q/vlan_dev.c

@@ -533,6 +533,9 @@ static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 
+	if (saddr == NULL)
+		saddr = dev->dev_addr;
+
 	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
 }
 

net/bluetooth/hci_event.c

@@ -3383,7 +3383,13 @@ static inline void hci_le_ltk_request_evt(struct hci_dev *hdev,
 
 	hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
 
-	if (ltk->type & HCI_SMP_STK) {
+	/* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
+	 * temporary key used to encrypt a connection following
+	 * pairing. It is used during the Encrypted Session Setup to
+	 * distribute the keys. Later, security can be re-established
+	 * using a distributed LTK.
+	 */
+	if (ltk->type == HCI_SMP_STK_SLAVE) {
 		list_del(&ltk->list);
 		kfree(ltk);
 	}

net/bridge/br_multicast.c

@@ -1138,6 +1138,12 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
 
+	/* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+	if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (skb->len == sizeof(*mld)) {
 		if (!pskb_may_pull(skb, sizeof(*mld))) {
 			err = -EINVAL;

net/ipv6/addrconf.c

@@ -897,8 +897,11 @@ retry:
 	 * Lifetime is greater than REGEN_ADVANCE time units.  In particular,
 	 * an implementation must not create a temporary address with a zero
 	 * Preferred Lifetime.
+	 * Use age calculation as in addrconf_verify to avoid unnecessary
+	 * temporary addresses being generated.
 	 */
-	if (tmp_prefered_lft <= regen_advance) {
+	age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+	if (tmp_prefered_lft <= regen_advance + age) {
 		in6_ifa_put(ifp);
 		in6_dev_put(idev);
 		ret = -1;

net/ipv6/icmp.c

@@ -501,7 +501,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info*)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,

net/ipv6/ip6_output.c

@@ -1194,21 +1194,19 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 				unsigned int fragheaderlen,
 				struct sk_buff *skb,
 				struct rt6_info *rt,
-				bool pmtuprobe)
+				unsigned int orig_mtu)
 {
 	if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
 		if (skb == NULL) {
 			/* first fragment, reserve header_len */
-			*mtu = *mtu - rt->dst.header_len;
+			*mtu = orig_mtu - rt->dst.header_len;
 
 		} else {
 			/*
 			 * this fragment is not first, the headers
 			 * space is regarded as data space.
 			 */
-			*mtu = min(*mtu, pmtuprobe ?
-				   rt->dst.dev->mtu :
-				   dst_mtu(rt->dst.path));
+			*mtu = orig_mtu;
 		}
 		*maxfraglen = ((*mtu - fragheaderlen) & ~7)
 			      + fragheaderlen - sizeof(struct frag_hdr);
@@ -1225,7 +1223,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_cork *cork;
 	struct sk_buff *skb, *skb_prev = NULL;
-	unsigned int maxfraglen, fragheaderlen, mtu;
+	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
 	int exthdrlen;
 	int dst_exthdrlen;
 	int hh_len;
@@ -1310,6 +1308,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		dst_exthdrlen = 0;
 		mtu = cork->fragsize;
 	}
+	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
@@ -1392,8 +1391,7 @@ alloc_new_skb:
 			if (skb == NULL || skb_prev == NULL)
 				ip6_append_data_mtu(&mtu, &maxfraglen,
 						    fragheaderlen, skb, rt,
-						    np->pmtudisc ==
-						    IPV6_PMTUDISC_PROBE);
+						    orig_mtu);
 
 			skb_prev = skb;
 
@@ -1663,8 +1661,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);

net/ipv6/mcast.c

@@ -1430,11 +1430,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;

net/ipv6/route.c

@@ -1302,7 +1302,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
+	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
 
 	if (!rt) {
 		err = -ENOMEM;

net/rds/iw.c

@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",

net/sctp/sm_make_chunk.c

@@ -1366,8 +1366,8 @@ static void sctp_chunk_destroy(struct sctp_chunk *chunk)
 	BUG_ON(!list_empty(&chunk->list));
 	list_del_init(&chunk->transmitted_list);
 
-	/* Free the chunk skb data and the SCTP_chunk stub itself. */
-	dev_kfree_skb(chunk->skb);
+	consume_skb(chunk->skb);
+	consume_skb(chunk->auth_chunk);
 
 	SCTP_DBG_OBJCNT_DEC(chunk);
 	kmem_cache_free(sctp_chunk_cachep, chunk);

net/sctp/sm_statefuns.c

@@ -749,7 +749,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
 
 		/* Make sure that we and the peer are AUTH capable */
 		if (!sctp_auth_enable || !new_asoc->peer.auth_capable) {
-			kfree_skb(chunk->auth_chunk);
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
 		}
@@ -764,10 +763,6 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep,
 		auth.transport = chunk->transport;
 
 		ret = sctp_sf_authenticate(ep, new_asoc, type, &auth);
-
-		/* We can now safely free the auth_chunk clone */
-		kfree_skb(chunk->auth_chunk);
-
 		if (ret != SCTP_IERROR_NO_ERROR) {
 			sctp_association_free(new_asoc);
 			return sctp_sf_pdiscard(ep, asoc, type, arg, commands);

net/socket.c

@@ -1907,6 +1907,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
 {
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;

net/unix/af_unix.c

@@ -1787,8 +1787,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
@@ -1910,6 +1913,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = msg->msg_name;
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;
@@ -1925,7 +1929,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
@@ -1937,8 +1941,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}