[ciqlts9_2] Multiple patches tested (8 commits)

arch/x86/kernel/apic/vector.c

@@ -982,7 +982,8 @@ static void __send_cleanup_vector(struct apic_chip_data *apicd)
 		hlist_add_head(&apicd->clist, per_cpu_ptr(&cleanup_list, cpu));
 		apic->send_IPI(cpu, IRQ_MOVE_CLEANUP_VECTOR);
 	} else {
-		apicd->prev_vector = 0;
+		pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu);
+		free_moved_vector(apicd);
 	}
 	raw_spin_unlock(&vector_lock);
 }
@@ -1019,6 +1020,7 @@ void irq_complete_move(struct irq_cfg *cfg)
  */
 void irq_force_complete_move(struct irq_desc *desc)
 {
+	unsigned int cpu = smp_processor_id();
 	struct apic_chip_data *apicd;
 	struct irq_data *irqd;
 	unsigned int vector;
@@ -1043,10 +1045,11 @@ void irq_force_complete_move(struct irq_desc *desc)
 		goto unlock;
 
 	/*
-	 * If prev_vector is empty, no action required.
+	 * If prev_vector is empty or the descriptor is neither currently
+	 * nor previously on the outgoing CPU no action required.
 	 */
 	vector = apicd->prev_vector;
-	if (!vector)
+	if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu))
 		goto unlock;
 
 	/*

drivers/net/ethernet/realtek/r8169_main.c

@@ -4289,11 +4289,11 @@ static void rtl8169_doorbell(struct rtl8169_private *tp)
 static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
-	unsigned int frags = skb_shinfo(skb)->nr_frags;
 	struct rtl8169_private *tp = netdev_priv(dev);
 	unsigned int entry = tp->cur_tx % NUM_TX_DESC;
 	struct TxDesc *txd_first, *txd_last;
 	bool stop_queue, door_bell;
+	unsigned int frags;
 	u32 opts[2];
 
 	if (unlikely(!rtl_tx_slots_avail(tp))) {
@@ -4316,6 +4316,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd_first = tp->TxDescArray + entry;
 
+	frags = skb_shinfo(skb)->nr_frags;
 	if (frags) {
 		if (rtl8169_xmit_frags(tp, skb, opts, entry))
 			goto err_dma_1;

drivers/nvme/host/core.c

@@ -959,6 +959,7 @@ void nvme_cleanup_cmd(struct request *req)
 			clear_bit_unlock(0, &ctrl->discard_page_busy);
 		else
 			kfree(bvec_virt(&req->special_vec));
+		req->rq_flags &= ~RQF_SPECIAL_PAYLOAD;
 	}
 }
 EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);

drivers/nvme/target/core.c

@@ -799,6 +799,15 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
 	percpu_ref_exit(&sq->ref);
 	nvmet_auth_sq_free(sq);
 
+	/*
+	 * we must reference the ctrl again after waiting for inflight IO
+	 * to complete. Because admin connect may have sneaked in after we
+	 * store sq->ctrl locally, but before we killed the percpu_ref. the
+	 * admin connect allocates and assigns sq->ctrl, which now needs a
+	 * final ref put, as this ctrl is going away.
+	 */
+	ctrl = sq->ctrl;
+
 	if (ctrl) {
 		/*
 		 * The teardown flow may take some time, and the host may not

kernel/irq/cpuhotplug.c

@@ -69,6 +69,14 @@ static bool migrate_one_irq(struct irq_desc *desc)
 		return false;
 	}
 
+	/*
+	 * Complete an eventually pending irq move cleanup. If this
+	 * interrupt was moved in hard irq context, then the vectors need
+	 * to be cleaned up. It can't wait until this interrupt actually
+	 * happens and this CPU was involved.
+	 */
+	irq_force_complete_move(desc);
+
 	/*
 	 * No move required, if:
 	 * - Interrupt is per cpu
@@ -87,14 +95,6 @@ static bool migrate_one_irq(struct irq_desc *desc)
 		return false;
 	}
 
-	/*
-	 * Complete an eventually pending irq move cleanup. If this
-	 * interrupt was moved in hard irq context, then the vectors need
-	 * to be cleaned up. It can't wait until this interrupt actually
-	 * happens and this CPU was involved.
-	 */
-	irq_force_complete_move(desc);
-
 	/*
 	 * If there is a setaffinity pending, then try to reuse the pending
 	 * mask, so the last change of the affinity does not get lost. If

mm/memory-failure.c

@@ -2144,6 +2144,13 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
+	if (is_huge_zero_page(page)) {
+		unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n",
+				 pfn, &unpoison_rs);
+		ret = -EOPNOTSUPP;
+		goto unlock_mutex;
+	}
+
 	if (!PageHWPoison(p)) {
 		unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n",
 				 pfn, &unpoison_rs);

net/ipv4/netfilter/nf_tproxy_ipv4.c

@@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 
 	laddr = 0;
 	indev = __in_dev_get_rcu(skb->dev);
+	if (!indev)
+		return daddr;
 
 	in_dev_for_each_ifa_rcu(ifa, indev) {
 		if (ifa->ifa_flags & IFA_F_SECONDARY)

net/mptcp/protocol.c

@@ -3581,6 +3581,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	WRITE_ONCE(msk->write_seq, subflow->idsn);
 	WRITE_ONCE(msk->snd_nxt, subflow->idsn);
+	WRITE_ONCE(msk->snd_una, subflow->idsn);
 	if (likely(!__mptcp_check_fallback(msk)))
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);
 

net/tls/tls_main.c

@@ -830,9 +830,17 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 		return NULL;
 
 	mutex_init(&ctx->tx_lock);
-	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	ctx->sk_proto = READ_ONCE(sk->sk_prot);
 	ctx->sk = sk;
+	/* Release semantic of rcu_assign_pointer() ensures that
+	 * ctx->sk_proto is visible before changing sk->sk_prot in
+	 * update_sk_prot(), and prevents reading uninitialized value in
+	 * tls_{getsockopt, setsockopt}. Note that we do not need a
+	 * read barrier in tls_{getsockopt,setsockopt} as there is an
+	 * address dependency between sk->sk_proto->{getsockopt,setsockopt}
+	 * and ctx->sk_proto.
+	 */
+	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	return ctx;
 }