Merge branch 'for-linus' into for-4.12/block

We've added a considerable amount of fixes for stalls and issues
with the blk-mq scheduling in the 4.11 series since forking
off the for-4.12/block branch. We need to do improvements on
top of that for 4.12, so pull in the previous fixes to make
our lives easier going forward.

Signed-off-by: Jens Axboe <axboe@fb.com>

3 files changed, 48 insertions, 27 deletions

diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6ae56037bb13..029a61ac6cdd 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -71,27 +71,17 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void update_classid(struct cgroup_subsys_state *css, void *v)
+static void cgrp_attach(struct cgroup_taskset *tset)
 {
-	struct css_task_iter it;
+	struct cgroup_subsys_state *css;
 	struct task_struct *p;
 
-	css_task_iter_start(css, &it);
-	while ((p = css_task_iter_next(&it))) {
+	cgroup_taskset_for_each(p, css, tset) {
 		task_lock(p);
-		iterate_fd(p->files, 0, update_classid_sock, v);
+		iterate_fd(p->files, 0, update_classid_sock,
+			   (void *)(unsigned long)css_cls_state(css)->classid);
 		task_unlock(p);
 	}
-	css_task_iter_end(&it);
-}
-
-static void cgrp_attach(struct cgroup_taskset *tset)
-{
-	struct cgroup_subsys_state *css;
-
-	cgroup_taskset_first(tset, &css);
-	update_classid(css,
-		       (void *)(unsigned long)css_cls_state(css)->classid);
 }
 
 static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -103,12 +93,22 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
 			 u64 value)
 {
 	struct cgroup_cls_state *cs = css_cls_state(css);
+	struct css_task_iter it;
+	struct task_struct *p;
 
 	cgroup_sk_alloc_disable();
 
 	cs->classid = (u32)value;
 
-	update_classid(css, (void *)(unsigned long)cs->classid);
+	css_task_iter_start(css, &it);
+	while ((p = css_task_iter_next(&it))) {
+		task_lock(p);
+		iterate_fd(p->files, 0, update_classid_sock,
+			   (void *)(unsigned long)cs->classid);
+		task_unlock(p);
+	}
+	css_task_iter_end(&it);
+
 	return 0;
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cd4ba8c6b609..9f781092fda9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3694,6 +3694,15 @@ static void sock_rmem_free(struct sk_buff *skb)
 	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 }
 
+static void skb_set_err_queue(struct sk_buff *skb)
+{
+	/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
+	 * So, it is safe to (mis)use it to mark skbs on the error queue.
+	 */
+	skb->pkt_type = PACKET_OUTGOING;
+	BUILD_BUG_ON(PACKET_OUTGOING == 0);
+}
+
 /*
  * Note: We dont mem charge error packets (no sk_forward_alloc changes)
  */
@@ -3707,6 +3716,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 	skb->sk = sk;
 	skb->destructor = sock_rmem_free;
 	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+	skb_set_err_queue(skb);
 
 	/* before exiting rcu section, make sure dst is refcounted */
 	skb_dst_force(skb);
@@ -3783,16 +3793,20 @@ EXPORT_SYMBOL(skb_clone_sk);
 
 static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 					struct sock *sk,
-					int tstype)
+					int tstype,
+					bool opt_stats)
 {
 	struct sock_exterr_skb *serr;
 	int err;
 
+	BUILD_BUG_ON(sizeof(struct sock_exterr_skb) > sizeof(skb->cb));
+
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	serr->ee.ee_info = tstype;
+	serr->opt_stats = opt_stats;
 	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk->sk_protocol == IPPROTO_TCP &&
@@ -3833,7 +3847,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	 */
 	if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) {
 		*skb_hwtstamps(skb) = *hwtstamps;
-		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+		__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
 		sock_put(sk);
 	}
 }
@@ -3844,7 +3858,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
-	bool tsonly;
+	bool tsonly, opt_stats = false;
 
 	if (!sk)
 		return;
@@ -3857,9 +3871,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 #ifdef CONFIG_INET
 		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk->sk_protocol == IPPROTO_TCP &&
-		    sk->sk_type == SOCK_STREAM)
+		    sk->sk_type == SOCK_STREAM) {
 			skb = tcp_get_timestamping_opt_stats(sk);
-		else
+			opt_stats = true;
+		} else
 #endif
 			skb = alloc_skb(0, GFP_ATOMIC);
 	} else {
@@ -3878,7 +3893,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	else
 		skb->tstamp = ktime_get_real();
 
-	__skb_complete_tx_timestamp(skb, sk, tstype);
+	__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats);
 }
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index a96d5f7a5734..2c4f574168fb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1442,6 +1442,11 @@ static void __sk_destruct(struct rcu_head *head)
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
 
+	if (sk->sk_frag.page) {
+		put_page(sk->sk_frag.page);
+		sk->sk_frag.page = NULL;
+	}
+
 	if (sk->sk_peer_cred)
 		put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
@@ -1539,6 +1544,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 			is_charged = sk_filter_charge(newsk, filter);
 
 		if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
+			/* We need to make sure that we don't uncharge the new
+			 * socket if we couldn't charge it in the first place
+			 * as otherwise we uncharge the parent's filter.
+			 */
+			if (!is_charged)
+				RCU_INIT_POINTER(newsk->sk_filter, NULL);
 			sk_free_unlock_clone(newsk);
 			newsk = NULL;
 			goto out;
@@ -2787,11 +2798,6 @@ void sk_common_release(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	if (sk->sk_frag.page) {
-		put_page(sk->sk_frag.page);
-		sk->sk_frag.page = NULL;
-	}
-
 	sock_put(sk);
 }
 EXPORT_SYMBOL(sk_common_release);