Merge android-4.4@89074de (v4.4.94) into msm-4.4

* refs/heads/tmp-89074de
  Linux 4.4.94
  Revert "tty: goldfish: Fix a parameter of a call to free_irq"
  cpufreq: CPPC: add ACPI_PROCESSOR dependency
  nfsd/callback: Cleanup callback cred on shutdown
  target/iscsi: Fix unsolicited data seq_end_offset calculation
  uapi: fix linux/mroute6.h userspace compilation errors
  uapi: fix linux/rds.h userspace compilation errors
  ceph: clean up unsafe d_parent accesses in build_dentry_path
  i2c: at91: ensure state is restored after suspending
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  scsi: scsi_dh_emc: return success in clariion_std_inquiry()
  slub: do not merge cache if slub_debug contains a never-merge flag
  ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock
  crypto: xts - Add ECB dependency
  net/mlx4_core: Fix VF overwrite of module param which disables DMFS on new probed PFs
  sparc64: Migrate hvcons irq to panicked cpu
  md/linear: shutup lockdep warnning
  f2fs: do not wait for writeback in write_begin
  Btrfs: send, fix failure to rename top level inode due to name collision
  iio: adc: xilinx: Fix error handling
  netfilter: nf_ct_expect: Change __nf_ct_expect_check() return value.
  net/mlx4_en: fix overflow in mlx4_en_init_timestamp()
  mac80211: fix power saving clients handling in iwlwifi
  mac80211_hwsim: check HWSIM_ATTR_RADIO_NAME length
  irqchip/crossbar: Fix incorrect type of local variables
  watchdog: kempld: fix gcc-4.3 build
  locking/lockdep: Add nest_lock integrity test
  Revert "bsg-lib: don't free job in bsg_prepare_job"
  tipc: use only positive error codes in messages
  net: Set sk_prot_creator when cloning sockets to the right proto
  packet: only test po->has_vnet_hdr once in packet_snd
  packet: in packet_do_bind, test fanout with bind_lock held
  tun: bail out from tun_get_user() if the skb is empty
  l2tp: fix race condition in l2tp_tunnel_delete
  l2tp: Avoid schedule while atomic in exit_net
  vti: fix use after free in vti_tunnel_xmit/vti6_tnl_xmit
  isdn/i4l: fetch the ppp_write buffer in one shot
  bpf: one perf event close won't free bpf program attached by another perf event
  packet: hold bind lock when rebinding to fanout hook
  net: emac: Fix napi poll list corruption
  ip6_gre: skb_push ipv6hdr before packing the header in ip6gre_header
  udpv6: Fix the checksum computation when HW checksum does not apply
  bpf/verifier: reject BPF_ALU64|BPF_END
  sctp: potential read out of bounds in sctp_ulpevent_type_enabled()
  MIPS: Fix minimum alignment requirement of IRQ stack
  drm/dp/mst: save vcpi with payloads
  percpu: make this_cpu_generic_read() atomic w.r.t. interrupts
  trace: sched: Fix util_avg_walt in sched_load_avg_cpu trace
  sched/fair: remove erroneous RCU_LOCKDEP_WARN from start_cpu()
  sched: EAS/WALT: finish accounting prior to task_tick
  cpufreq: sched: update capacity request upon tick always
  sched/fair: prevent meaningless active migration
  sched: walt: Leverage existing helper APIs to apply invariance

Conflicts:
	kernel/sched/core.c
	kernel/sched/fair.c
	kernel/sched/sched.h

Change-Id: I0effac90fb6a4db559479bfa2fefa31c41200ce9
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

56 files changed, 367 insertions, 431 deletions

diff --git a/Makefile b/Makefile
index c826d1ecc91d..9fa2f82f66ed 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 93
+SUBLEVEL = 94
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 77edb22f855d..5433ccc9d706 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -18,7 +18,7 @@
 #include <irq.h>
 
 #define IRQ_STACK_SIZE			THREAD_SIZE
-#define IRQ_STACK_START			(IRQ_STACK_SIZE - sizeof(unsigned long))
+#define IRQ_STACK_START			(IRQ_STACK_SIZE - 16)
 
 extern void *irq_stack[NR_CPUS];
 
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index be0cc1beed41..3fae200dd251 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -59,8 +59,11 @@ extern atomic_t dcpage_flushes;
 extern atomic_t dcpage_flushes_xcall;
 
 extern int sysctl_tsb_ratio;
-#endif
 
+#ifdef CONFIG_SERIAL_SUNHV
+void sunhv_migrate_hvcons_irq(int cpu);
+#endif
+#endif
 void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 4511caa3b7e9..46866b2097e8 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1443,8 +1443,12 @@ void smp_send_stop(void)
 	int cpu;
 
 	if (tlb_type == hypervisor) {
+		int this_cpu = smp_processor_id();
+#ifdef CONFIG_SERIAL_SUNHV
+		sunhv_migrate_hvcons_irq(this_cpu);
+#endif
 		for_each_online_cpu(cpu) {
-			if (cpu == smp_processor_id())
+			if (cpu == this_cpu)
 				continue;
 #ifdef CONFIG_SUN_LDOMS
 			if (ldom_domaining_enabled) {
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 341b8d858e67..650f427d915b 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -147,6 +147,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
 failjob_rls_rqst_payload:
 	kfree(job->request_payload.sg_list);
 failjob_rls_job:
+	kfree(job);
 	return -ENOMEM;
 }
 
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 3240d394426c..248d1a8f9409 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -361,6 +361,7 @@ config CRYPTO_XTS
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
+	select CRYPTO_ECB
 	help
 	  XTS: IEEE1619/D16 narrow block cipher use with aes-xts-plain,
 	  key size 256, 384 or 512 bits. This implementation currently
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index e2c02f9dd141..ff0fd0e44f07 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -241,7 +241,7 @@ config ARM_PXA2xx_CPUFREQ
 
 config ACPI_CPPC_CPUFREQ
 	tristate "CPUFreq driver based on the ACPI CPPC spec"
-	depends on ACPI
+	depends on ACPI_PROCESSOR
 	select ACPI_CPPC_LIB
 	default n
 	help
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 58bf94b69186..273e05a3c933 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1802,6 +1802,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 				return -EINVAL;
 			}
 			req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots;
+			req_payload.vcpi = mgr->proposed_vcpis[i]->vcpi;
 		} else {
 			port = NULL;
 			req_payload.num_slots = 0;
@@ -1817,6 +1818,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			if (req_payload.num_slots) {
 				drm_dp_create_payload_step1(mgr, mgr->proposed_vcpis[i]->vcpi, &req_payload);
 				mgr->payloads[i].num_slots = req_payload.num_slots;
+				mgr->payloads[i].vcpi = req_payload.vcpi;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
 				drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]);
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 10835d1f559b..dee0fc421054 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -1131,6 +1131,7 @@ static int at91_twi_suspend_noirq(struct device *dev)
 
 static int at91_twi_resume_noirq(struct device *dev)
 {
+	struct at91_twi_dev *twi_dev = dev_get_drvdata(dev);
 	int ret;
 
 	if (!pm_runtime_status_suspended(dev)) {
@@ -1142,6 +1143,8 @@ static int at91_twi_resume_noirq(struct device *dev)
 	pm_runtime_mark_last_busy(dev);
 	pm_request_autosuspend(dev);
 
+	at91_init_twi_bus(twi_dev);
+
 	return 0;
 }
 
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 02e636a1c49a..475c5a74f2d1 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -1208,7 +1208,7 @@ static int xadc_probe(struct platform_device *pdev)
 
 	ret = xadc->ops->setup(pdev, indio_dev, irq);
 	if (ret)
-		goto err_free_samplerate_trigger;
+		goto err_clk_disable_unprepare;
 
 	ret = request_irq(irq, xadc->ops->interrupt_handler, 0,
 			dev_name(&pdev->dev), indio_dev);
@@ -1268,6 +1268,8 @@ static int xadc_probe(struct platform_device *pdev)
 
 err_free_irq:
 	free_irq(irq, indio_dev);
+err_clk_disable_unprepare:
+	clk_disable_unprepare(xadc->clk);
 err_free_samplerate_trigger:
 	if (xadc->ops->flags & XADC_FLAGS_BUFFERED)
 		iio_trigger_free(xadc->samplerate_trigger);
@@ -1277,8 +1279,6 @@ err_free_convst_trigger:
 err_triggered_buffer_cleanup:
 	if (xadc->ops->flags & XADC_FLAGS_BUFFERED)
 		iio_triggered_buffer_cleanup(indio_dev);
-err_clk_disable_unprepare:
-	clk_disable_unprepare(xadc->clk);
 err_device_free:
 	kfree(indio_dev->channels);
 
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 75573fa431ba..63faee04a008 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 
 static int __init crossbar_of_init(struct device_node *node)
 {
-	int i, size, max = 0, reserved = 0, entry;
+	int i, size, reserved = 0;
+	u32 max = 0, entry;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index bf3fbd00a091..64b586458d3d 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -828,7 +828,6 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	isdn_net_local *lp;
 	struct ippp_struct *is;
 	int proto;
-	unsigned char protobuf[4];
 
 	is = file->private_data;
 
@@ -842,24 +841,28 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 	if (!lp)
 		printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
 	else {
-		/*
-		 * Don't reset huptimer for
-		 * LCP packets. (Echo requests).
-		 */
-		if (copy_from_user(protobuf, buf, 4))
-			return -EFAULT;
-		proto = PPP_PROTOCOL(protobuf);
-		if (proto != PPP_LCP)
-			lp->huptimer = 0;
+		if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+			unsigned char protobuf[4];
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			if (copy_from_user(protobuf, buf, 4))
+				return -EFAULT;
+
+			proto = PPP_PROTOCOL(protobuf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
 
-		if (lp->isdn_device < 0 || lp->isdn_channel < 0)
 			return 0;
+		}
 
 		if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
 		    lp->dialstate == 0 &&
 		    (lp->flags & ISDN_NET_CONNECTED)) {
 			unsigned short hl;
 			struct sk_buff *skb;
+			unsigned char *cpy_buf;
 			/*
 			 * we need to reserve enough space in front of
 			 * sk_buff. old call to dev_alloc_skb only reserved
@@ -872,11 +875,21 @@ isdn_ppp_write(int min, struct file *file, const char __user *buf, int count)
 				return count;
 			}
 			skb_reserve(skb, hl);
-			if (copy_from_user(skb_put(skb, count), buf, count))
+			cpy_buf = skb_put(skb, count);
+			if (copy_from_user(cpy_buf, buf, count))
 			{
 				kfree_skb(skb);
 				return -EFAULT;
 			}
+
+			/*
+			 * Don't reset huptimer for
+			 * LCP packets. (Echo requests).
+			 */
+			proto = PPP_PROTOCOL(cpy_buf);
+			if (proto != PPP_LCP)
+				lp->huptimer = 0;
+
 			if (is->debug & 0x40) {
 				printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
 				isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 79223dceb1c2..b19205ea1a10 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -223,7 +223,8 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	 * oldconf until no one uses it anymore.
 	 */
 	mddev_suspend(mddev);
-	oldconf = rcu_dereference(mddev->private);
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
 	mddev->raid_disks++;
 	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
 		"copied raid_disks doesn't match mddev->raid_disks");
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index fdb5cdb3cd15..81abe46c9e0d 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -402,7 +402,7 @@ static int mal_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 
 	MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
 	/* Process TX skbs */
 	list_for_each(l, &mal->poll_list) {
 		struct mal_commac *mc =
@@ -451,7 +451,6 @@ static int mal_poll(struct napi_struct *napi, int budget)
 			spin_lock_irqsave(&mal->lock, flags);
 			mal_disable_eob_irq(mal);
 			spin_unlock_irqrestore(&mal->lock, flags);
-			goto again;
 		}
 		mc->ops->poll_tx(mc->dev);
 	}
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 0e67145bc418..4f34e1b79705 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -4415,13 +4415,12 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 		struct mvpp2_txq_pcpu_buf *tx_buf =
 			txq_pcpu->buffs + txq_pcpu->txq_get_index;
 
-		mvpp2_txq_inc_get(txq_pcpu);
-
 		dma_unmap_single(port->dev->dev.parent, tx_buf->phys,
 				 tx_buf->size, DMA_TO_DEVICE);
-		if (!tx_buf->skb)
-			continue;
-		dev_kfree_skb_any(tx_buf->skb);
+		if (tx_buf->skb)
+			dev_kfree_skb_any(tx_buf->skb);
+
+		mvpp2_txq_inc_get(txq_pcpu);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 1494997c4f7e..4dccf7287f0f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -88,10 +88,17 @@ void mlx4_en_remove_timestamp(struct mlx4_en_dev *mdev)
 	}
 }
 
+#define MLX4_EN_WRAP_AROUND_SEC	10UL
+/* By scheduling the overflow check every 5 seconds, we have a reasonably
+ * good chance we wont miss a wrap around.
+ * TOTO: Use a timer instead of a work queue to increase the guarantee.
+ */
+#define MLX4_EN_OVERFLOW_PERIOD (MLX4_EN_WRAP_AROUND_SEC * HZ / 2)
+
 void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev)
 {
 	bool timeout = time_is_before_jiffies(mdev->last_overflow_check +
-					      mdev->overflow_period);
+					      MLX4_EN_OVERFLOW_PERIOD);
 	unsigned long flags;
 
 	if (timeout) {
@@ -236,7 +243,6 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
-#define MLX4_EN_WRAP_AROUND_SEC	10ULL
 
 /* This function calculates the max shift that enables the user range
  * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
@@ -258,7 +264,6 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
 	unsigned long flags;
-	u64 ns, zero = 0;
 
 	/* mlx4_en_init_timestamp is called for each netdev.
 	 * mdev->ptp_clock is common for all ports, skip initialization if
@@ -282,13 +287,6 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 	write_unlock_irqrestore(&mdev->clock_lock, flags);
 
-	/* Calculate period in seconds to call the overflow watchdog - to make
-	 * sure counter is checked at least once every wrap around.
-	 */
-	ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask, zero, &zero);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
-	mdev->overflow_period = ns;
-
 	/* Configure the PHC */
 	mdev->ptp_clock_info = mlx4_en_ptp_clock_info;
 	snprintf(mdev->ptp_clock_info.name, 16, "mlx4 ptp");
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 31c491e02e69..99361352ed0d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -791,8 +791,6 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENOSYS;
 	}
 
-	mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;
-
 	dev->caps.hca_core_clock = hca_param.hca_core_clock;
 
 	memset(&dev_cap, 0, sizeof(dev_cap));
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index c41f15102ae0..10aa6544cf4d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -409,7 +409,6 @@ struct mlx4_en_dev {
 	struct cyclecounter	cycles;
 	struct timecounter	clock;
 	unsigned long		last_overflow_check;
-	unsigned long		overflow_period;
 	struct ptp_clock	*ptp_clock;
 	struct ptp_clock_info	ptp_clock_info;
 	struct notifier_block	nb;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a444294fb555..89ad2b750531 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1196,11 +1196,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case IFF_TUN:
 		if (tun->flags & IFF_NO_PI) {
-			switch (skb->data[0] & 0xf0) {
-			case 0x40:
+			u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0;
+
+			switch (ip_version) {
+			case 4:
 				pi.proto = htons(ETH_P_IP);
 				break;
-			case 0x60:
+			case 6:
 				pi.proto = htons(ETH_P_IPV6);
 				break;
 			default:
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 019d7165a045..2a996a68fc2b 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2884,6 +2884,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2,
 static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 {
 	struct hwsim_new_radio_params param = { 0 };
+	const char *hwname = NULL;
 
 	param.reg_strict = info->attrs[HWSIM_ATTR_REG_STRICT_REG];
 	param.p2p_device = info->attrs[HWSIM_ATTR_SUPPORT_P2P_DEVICE];
@@ -2897,8 +2898,14 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_NO_VIF])
 		param.no_vif = true;
 
-	if (info->attrs[HWSIM_ATTR_RADIO_NAME])
-		param.hwname = nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]);
+	if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
+		hwname = kasprintf(GFP_KERNEL, "%.*s",
+				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		if (!hwname)
+			return -ENOMEM;
+		param.hwname = hwname;
+	}
 
 	if (info->attrs[HWSIM_ATTR_USE_CHANCTX])
 		param.use_chanctx = true;
@@ -2926,11 +2933,15 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	s64 idx = -1;
 	const char *hwname = NULL;
 
-	if (info->attrs[HWSIM_ATTR_RADIO_ID])
+	if (info->attrs[HWSIM_ATTR_RADIO_ID]) {
 		idx = nla_get_u32(info->attrs[HWSIM_ATTR_RADIO_ID]);
-	else if (info->attrs[HWSIM_ATTR_RADIO_NAME])
-		hwname = (void *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]);
-	else
+	} else if (info->attrs[HWSIM_ATTR_RADIO_NAME]) {
+		hwname = kasprintf(GFP_KERNEL, "%.*s",
+				   nla_len(info->attrs[HWSIM_ATTR_RADIO_NAME]),
+				   (char *)nla_data(info->attrs[HWSIM_ATTR_RADIO_NAME]));
+		if (!hwname)
+			return -ENOMEM;
+	} else
 		return -EINVAL;
 
 	spin_lock_bh(&hwsim_radio_lock);
@@ -2939,7 +2950,8 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			if (data->idx != idx)
 				continue;
 		} else {
-			if (strcmp(hwname, wiphy_name(data->hw->wiphy)))
+			if (!hwname ||
+			    strcmp(hwname, wiphy_name(data->hw->wiphy)))
 				continue;
 		}
 
@@ -2947,10 +2959,12 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
 		spin_unlock_bh(&hwsim_radio_lock);
 		mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy),
 					 info);
+		kfree(hwname);
 		return 0;
 	}
 	spin_unlock_bh(&hwsim_radio_lock);
 
+	kfree(hwname);
 	return -ENODEV;
 }
 
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index e6fb97cb12f4..7c28dc1cb0dd 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -456,7 +456,7 @@ static int clariion_prep_fn(struct scsi_device *sdev, struct request *req)
 static int clariion_std_inquiry(struct scsi_device *sdev,
 				struct clariion_dh_data *csdev)
 {
-	int err;
+	int err = SCSI_DH_OK;
 	char *sp_model;
 
 	err = send_inquiry_cmd(sdev, 0, csdev);
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 6c88fb021444..4eeb82cf79e4 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -44,10 +44,8 @@ void iscsit_set_dataout_sequence_values(
 	 */
 	if (cmd->unsolicited_data) {
 		cmd->seq_start_offset = cmd->write_data_done;
-		cmd->seq_end_offset = (cmd->write_data_done +
-			((cmd->se_cmd.data_length >
-			  conn->sess->sess_ops->FirstBurstLength) ?
-			 conn->sess->sess_ops->FirstBurstLength : cmd->se_cmd.data_length));
+		cmd->seq_end_offset = min(cmd->se_cmd.data_length,
+					conn->sess->sess_ops->FirstBurstLength);
 		return;
 	}
 
diff --git a/drivers/tty/goldfish.c b/drivers/tty/goldfish.c
index b2f830d6a654..1e332855b933 100644
--- a/drivers/tty/goldfish.c
+++ b/drivers/tty/goldfish.c
@@ -300,7 +300,7 @@ static int goldfish_tty_probe(struct platform_device *pdev)
 	return 0;
 
 err_tty_register_device_failed:
-	free_irq(irq, qtty);
+	free_irq(irq, pdev);
 err_request_irq_failed:
 	goldfish_tty_current_line_count--;
 	if (goldfish_tty_current_line_count == 0)
diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c
index 4e603d060e80..59828d819145 100644
--- a/drivers/tty/serial/sunhv.c
+++ b/drivers/tty/serial/sunhv.c
@@ -398,6 +398,12 @@ static struct uart_driver sunhv_reg = {
 
 static struct uart_port *sunhv_port;
 
+void sunhv_migrate_hvcons_irq(int cpu)
+{
+	/* Migrate hvcons irq to param cpu */
+	irq_force_affinity(sunhv_port->irq, cpumask_of(cpu));
+}
+
 /* Copy 's' into the con_write_page, decoding "\n" into
  * "\r\n" along the way.  We have to return two lengths
  * because the caller needs to know how much to advance
diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c
index 5bf931ce1353..978098f71761 100644
--- a/drivers/watchdog/kempld_wdt.c
+++ b/drivers/watchdog/kempld_wdt.c
@@ -140,12 +140,19 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data,
 					unsigned int timeout)
 {
 	struct kempld_device_data *pld = wdt_data->pld;
-	u32 prescaler = kempld_prescaler[PRESCALER_21];
+	u32 prescaler;
 	u64 stage_timeout64;
 	u32 stage_timeout;
 	u32 remainder;
 	u8 stage_cfg;
 
+#if GCC_VERSION < 40400
+	/* work around a bug compiling do_div() */
+	prescaler = READ_ONCE(kempld_prescaler[PRESCALER_21]);
+#else
+	prescaler = kempld_prescaler[PRESCALER_21];
+#endif
+
 	if (!stage)
 		return -EINVAL;
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 63a6152be04b..c5bbb5300658 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1648,6 +1648,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
 {
 	int ret;
 
+	if (ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+
 	ret = get_cur_inode_state(sctx, ino, gen);
 	if (ret < 0)
 		goto out;
@@ -1833,7 +1836,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	 * not delted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
 	 */
-	if (sctx->parent_root) {
+	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
 				     NULL, NULL, NULL);
 		if (ret < 0 && ret != -ENOENT)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f54f77037d22..ead89489ae71 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1845,13 +1845,18 @@ static int build_dentry_path(struct dentry *dentry,
 			     int *pfreepath)
 {
 	char *path;
+	struct inode *dir;
 
-	if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) {
-		*pino = ceph_ino(d_inode(dentry->d_parent));
+	rcu_read_lock();
+	dir = d_inode_rcu(dentry->d_parent);
+	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
+		*pino = ceph_ino(dir);
+		rcu_read_unlock();
 		*ppath = dentry->d_name.name;
 		*ppathlen = dentry->d_name.len;
 		return 0;
 	}
+	rcu_read_unlock();
 	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 15bdc2d48cfe..24ace275160c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -696,6 +696,14 @@ int set_callback_cred(void)
 	return 0;
 }
 
+void cleanup_callback_cred(void)
+{
+	if (callback_cred) {
+		put_rpccred(callback_cred);
+		callback_cred = NULL;
+	}
+}
+
 static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
 {
 	if (clp->cl_minorversion == 0) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9e5a6842346e..ca9ebc3242d3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6792,23 +6792,24 @@ nfs4_state_start(void)
 
 	ret = set_callback_cred();
 	if (ret)
-		return -ENOMEM;
+		return ret;
+
 	laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
 	if (laundry_wq == NULL) {
 		ret = -ENOMEM;
-		goto out_recovery;
+		goto out_cleanup_cred;
 	}
 	ret = nfsd4_create_callback_queue();
 	if (ret)
 		goto out_free_laundry;
 
 	set_max_delegations();
-
 	return 0;
 
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
-out_recovery:
+out_cleanup_cred:
+	cleanup_callback_cred();
 	return ret;
 }
 
@@ -6847,6 +6848,7 @@ nfs4_state_shutdown(void)
 {
 	destroy_workqueue(laundry_wq);
 	nfsd4_destroy_callback_queue();
+	cleanup_callback_cred();
 }
 
 static void
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 5134eedcb16c..86af697c21d3 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -595,6 +595,7 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
 		struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
 extern int set_callback_cred(void);
+extern void cleanup_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 60a5f1548cd9..555b57a16499 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -531,6 +531,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
 	init_waitqueue_head(&res->l_event);
 	INIT_LIST_HEAD(&res->l_blocked_list);
 	INIT_LIST_HEAD(&res->l_mask_waiters);
+	INIT_LIST_HEAD(&res->l_holders);
 }
 
 void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
@@ -748,6 +749,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
 	res->l_flags = 0UL;
 }
 
+/*
+ * Keep a list of processes who have interest in a lockres.
+ * Note: this is now only uesed for check recursive cluster locking.
+ */
+static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
+				   struct ocfs2_lock_holder *oh)
+{
+	INIT_LIST_HEAD(&oh->oh_list);
+	oh->oh_owner_pid = get_pid(task_pid(current));
+
+	spin_lock(&lockres->l_lock);
+	list_add_tail(&oh->oh_list, &lockres->l_holders);
+	spin_unlock(&lockres->l_lock);
+}
+
+static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
+				       struct ocfs2_lock_holder *oh)
+{
+	spin_lock(&lockres->l_lock);
+	list_del(&oh->oh_list);
+	spin_unlock(&lockres->l_lock);
+
+	put_pid(oh->oh_owner_pid);
+}
+
+static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres)
+{
+	struct ocfs2_lock_holder *oh;
+	struct pid *pid;
+
+	/* look in the list of holders for one with the current task as owner */
+	spin_lock(&lockres->l_lock);
+	pid = task_pid(current);
+	list_for_each_entry(oh, &lockres->l_holders, oh_list) {
+		if (oh->oh_owner_pid == pid) {
+			spin_unlock(&lockres->l_lock);
+			return 1;
+		}
+	}
+	spin_unlock(&lockres->l_lock);
+
+	return 0;
+}
+
 static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres,
 				     int level)
 {
@@ -2343,8 +2388,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 		goto getbh;
 	}
 
-	if (ocfs2_mount_local(osb))
-		goto local;
+	if ((arg_flags & OCFS2_META_LOCK_GETBH) ||
+	    ocfs2_mount_local(osb))
+		goto update;
 
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
@@ -2373,7 +2419,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
 
-local:
+update:
 	/*
 	 * We only see this flag if we're being called from
 	 * ocfs2_read_locked_inode(). It means we're locking an inode
@@ -2515,6 +2561,59 @@ void ocfs2_inode_unlock(struct inode *inode,
 		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
 }
 
+/*
+ * This _tracker variantes are introduced to deal with the recursive cluster
+ * locking issue. The idea is to keep track of a lock holder on the stack of
+ * the current process. If there's a lock holder on the stack, we know the
+ * task context is already protected by cluster locking. Currently, they're
+ * used in some VFS entry routines.
+ *
+ * return < 0 on error, return == 0 if there's no lock holder on the stack
+ * before this call, return == 1 if this call would be a recursive locking.
+ */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh)
+{
+	int status;
+	int arg_flags = 0, has_locked;
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = ocfs2_is_locked_by_me(lockres);
+	/* Just get buffer head if the cluster lock has been taken */
+	if (has_locked)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+
+	if (likely(!has_locked || ret_bh)) {
+		status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags);
+		if (status < 0) {
+			if (status != -ENOENT)
+				mlog_errno(status);
+			return status;
+		}
+	}
+	if (!has_locked)
+		ocfs2_add_holder(lockres, oh);
+
+	return has_locked;
+}
+
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock)
+{
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	if (!had_lock) {
+		ocfs2_remove_holder(lockres, oh);
+		ocfs2_inode_unlock(inode, ex);
+	}
+}
+
 int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
 {
 	struct ocfs2_lock_res *lockres;
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index d293a22c32c5..a7fc18ba0dc1 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb {
 	__be32	lvb_os_seqno;
 };
 
+struct ocfs2_lock_holder {
+	struct list_head oh_list;
+	struct pid *oh_owner_pid;
+};
+
 /* ocfs2_inode_lock_full() 'arg_flags' flags */
 /* don't wait on recovery. */
 #define OCFS2_META_LOCK_RECOVERY	(0x01)
@@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb {
 #define OCFS2_META_LOCK_NOQUEUE		(0x02)
 /* don't block waiting for the downconvert thread, instead return -EAGAIN */
 #define OCFS2_LOCK_NONBLOCK		(0x04)
+/* just get back disk inode bh if we've got cluster lock. */
+#define OCFS2_META_LOCK_GETBH		(0x08)
 
 /* Locking subclasses of inode cluster lock */
 enum {
@@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
 
 /* To set the locking protocol on module initialization */
 void ocfs2_set_locking_protocol(void);
+
+/* The _tracker pair is used to avoid cluster recursive locking */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh);
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock);
+
 #endif	/* DLMGLUE_H */
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7a0126267847..2495066a9ca3 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -172,6 +172,7 @@ struct ocfs2_lock_res {
 
 	struct list_head         l_blocked_list;
 	struct list_head         l_mask_waiters;
+	struct list_head	 l_holders;
 
 	unsigned long		 l_flags;
 	char                     l_name[OCFS2_LOCK_ID_MAX_LEN];
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 4d9f233c4ba8..7d58ffdacd62 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -105,15 +105,35 @@ do {									\
 	(__ret);							\
 })
 
-#define this_cpu_generic_read(pcp)					\
+#define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
 	typeof(pcp) __ret;						\
 	preempt_disable();						\
-	__ret = *this_cpu_ptr(&(pcp));					\
+	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable();						\
 	__ret;								\
 })
 
+#define __this_cpu_generic_read_noirq(pcp)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = *raw_cpu_ptr(&(pcp));					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	if (__native_word(pcp))						\
+		__ret = __this_cpu_generic_read_nopreempt(pcp);		\
+	else								\
+		__ret = __this_cpu_generic_read_noirq(pcp);		\
+	__ret;								\
+})
+
 #define this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	unsigned long __flags;						\
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 6ff6ab8534dd..2181ae5db42e 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -303,6 +303,7 @@ struct trace_event_call {
 	int				perf_refcount;
 	struct hlist_head __percpu	*perf_events;
 	struct bpf_prog			*prog;
+	struct perf_event		*bpf_prog_owner;
 
 	int	(*perf_perm)(struct trace_event_call *,
 			     struct perf_event *);
diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h
index cccdcfd14973..f348c736e6e0 100644
--- a/include/net/sctp/ulpevent.h
+++ b/include/net/sctp/ulpevent.h
@@ -141,8 +141,12 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event);
 static inline int sctp_ulpevent_type_enabled(__u16 sn_type,
 					     struct sctp_event_subscribe *mask)
 {
+	int offset = sn_type - SCTP_SN_TYPE_BASE;
 	char *amask = (char *) mask;
-	return amask[sn_type - SCTP_SN_TYPE_BASE];
+
+	if (offset >= sizeof(struct sctp_event_subscribe))
+		return 0;
+	return amask[offset];
 }
 
 /* Given an event subscription, is this event enabled? */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index cea7c9cb70f3..7047c9589003 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -1544,9 +1544,9 @@ TRACE_EVENT(sched_load_avg_cpu,
 		__entry->util_avg_pelt	= cfs_rq->avg.util_avg;
 		__entry->util_avg_walt	= 0;
 #ifdef CONFIG_SCHED_WALT
-		__entry->util_avg_walt	=
-				cpu_rq(cpu)->prev_runnable_sum << SCHED_LOAD_SHIFT;
-		do_div(__entry->util_avg_walt, walt_ravg_window);
+		__entry->util_avg_walt =
+				div64_u64(cpu_rq(cpu)->cumulative_runnable_avg,
+						  walt_ravg_window >> SCHED_LOAD_SHIFT);
 		if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
 			__entry->util_avg		= __entry->util_avg_walt;
 #endif
@@ -1865,7 +1865,6 @@ TRACE_EVENT(walt_update_task_ravg,
 		__array(	char,	comm,   TASK_COMM_LEN	)
 		__field(	pid_t,	pid			)
 		__field(	pid_t,	cur_pid			)
-		__field(unsigned int,	cur_freq		)
 		__field(	u64,	wallclock		)
 		__field(	u64,	mark_start		)
 		__field(	u64,	delta_m			)
@@ -1893,7 +1892,6 @@ TRACE_EVENT(walt_update_task_ravg,
 		__entry->evt            = evt;
 		__entry->cpu            = rq->cpu;
 		__entry->cur_pid        = rq->curr->pid;
-		__entry->cur_freq       = rq->cur_freq;
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid            = p->pid;
 		__entry->mark_start     = p->ravg.mark_start;
@@ -1912,11 +1910,10 @@ TRACE_EVENT(walt_update_task_ravg,
 		__entry->active_windows	= p->ravg.active_windows;
 	),
 
-	TP_printk("wc %llu ws %llu delta %llu event %d cpu %d cur_freq %u cur_pid %d task %d (%s) ms %llu delta %llu demand %u sum %u irqtime %llu"
+	TP_printk("wc %llu ws %llu delta %llu event %d cpu %d cur_pid %d task %d (%s) ms %llu delta %llu demand %u sum %u irqtime %llu"
 		" cs %llu ps %llu util %lu cur_window %u prev_window %u active_wins %u"
 		, __entry->wallclock, __entry->win_start, __entry->delta,
-		__entry->evt, __entry->cpu,
-		__entry->cur_freq, __entry->cur_pid,
+		__entry->evt, __entry->cpu, __entry->cur_pid,
 		__entry->pid, __entry->comm, __entry->mark_start,
 		__entry->delta_m, __entry->demand,
 		__entry->sum, __entry->irqtime,
diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h
index ce91215cf7e6..e0b566dc72ef 100644
--- a/include/uapi/linux/mroute6.h
+++ b/include/uapi/linux/mroute6.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/sockios.h>
+#include <linux/in6.h>		/* For struct sockaddr_in6. */
 
 /*
  *	Based on the MROUTING 3.5 defines primarily to keep
diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index 0f9265cb2a96..7af20a136429 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -35,6 +35,7 @@
 #define _LINUX_RDS_H
 
 #include <linux/types.h>
+#include <linux/socket.h>		/* For __kernel_sockaddr_storage. */
 
 #define RDS_IB_ABI_VERSION		0x301
 
@@ -223,7 +224,7 @@ struct rds_get_mr_args {
 };
 
 struct rds_get_mr_for_dest_args {
-	struct sockaddr_storage	dest_addr;
+	struct __kernel_sockaddr_storage dest_addr;
 	struct rds_iovec 	vec;
 	uint64_t		cookie_addr;
 	uint64_t		flags;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c97bce6a0e0e..eb759f5008b8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1044,7 +1044,8 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
 			}
 		} else {
 			if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
-			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+			    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+			    BPF_CLASS(insn->code) == BPF_ALU64) {
 				verbose("BPF_END uses reserved fields\n");
 				return -EINVAL;
 			}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 98928fb7fecc..322f63370038 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7302,6 +7302,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 	}
 
 	event->tp_event->prog = prog;
+	event->tp_event->bpf_prog_owner = event;
 
 	return 0;
 }
@@ -7314,7 +7315,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
 		return;
 
 	prog = event->tp_event->prog;
-	if (prog) {
+	if (prog && event->tp_event->bpf_prog_owner == event) {
 		event->tp_event->prog = NULL;
 		bpf_prog_put_rcu(prog);
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56618f6..0e2c4911ba61 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3128,10 +3128,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references)
+			if (hlock->references) {
+				/*
+				 * Check: unsigned int references:12, overflow.
+				 */
+				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+					return 0;
+
 				hlock->references++;
-			else
+			} else {
 				hlock->references = 2;
+			}
 
 			return 1;
 		}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4581a6c9b16f..c408280ddd12 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3209,16 +3209,9 @@ static void sched_freq_tick_walt(int cpu)
 
 static void sched_freq_tick(int cpu)
 {
-	unsigned long capacity_orig, capacity_curr;
-
 	if (!sched_freq())
 		return;
 
-	capacity_orig = capacity_orig_of(cpu);
-	capacity_curr = capacity_curr_of(cpu);
-	if (capacity_curr == capacity_orig)
-		return;
-
 	_sched_freq_tick(cpu);
 }
 #else
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa016919eab8..6e3ab49c262a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7386,9 +7386,6 @@ static int start_cpu(bool boosted)
 {
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
 
-	RCU_LOCKDEP_WARN(rcu_read_lock_sched_held(),
-			   "sched RCU must be held");
-
 	return boosted ? rd->max_cap_orig_cpu : rd->min_cap_orig_cpu;
 }
 
@@ -10276,6 +10273,7 @@ static int need_active_balance(struct lb_env *env)
 
 	if (energy_aware() &&
 	    (capacity_of(env->src_cpu) < capacity_of(env->dst_cpu)) &&
+	    ((capacity_orig_of(env->src_cpu) < capacity_orig_of(env->dst_cpu))) &&
 				env->src_rq->cfs.h_nr_running == 1 &&
 				cpu_overutilized(env->src_cpu) &&
 				!cpu_overutilized(env->dst_cpu)) {
diff --git a/kernel/sched/walt.c b/kernel/sched/walt.c
index 28e999554463..441cba01bc04 100644
--- a/kernel/sched/walt.c
+++ b/kernel/sched/walt.c
@@ -20,7 +20,6 @@
  */
 
 #include <linux/syscore_ops.h>
-#include <linux/cpufreq.h>
 #include <trace/events/sched.h>
 #include "sched.h"
 #include "walt.h"
@@ -45,29 +44,6 @@ unsigned int sysctl_sched_walt_init_task_load_pct = 15;
 /* 1 -> use PELT based load stats, 0 -> use window-based load stats */
 unsigned int __read_mostly walt_disabled = 0;
 
-static unsigned int max_possible_efficiency = 1024;
-static unsigned int min_possible_efficiency = 1024;
-
-/*
- * Maximum possible frequency across all cpus. Task demand and cpu
- * capacity (cpu_power) metrics are scaled in reference to it.
- */
-static unsigned int max_possible_freq = 1;
-
-/*
- * Minimum possible max_freq across all cpus. This will be same as
- * max_possible_freq on homogeneous systems and could be different from
- * max_possible_freq on heterogenous systems. min_max_freq is used to derive
- * capacity (cpu_power) of cpus.
- */
-static unsigned int min_max_freq = 1;
-
-static unsigned int max_load_scale_factor = 1024;
-static unsigned int max_possible_capacity = 1024;
-
-/* Mask of all CPUs that have  max_possible_capacity */
-static cpumask_t mpc_mask = CPU_MASK_ALL;
-
 /* Window size (in ns) */
 __read_mostly unsigned int walt_ravg_window = 20000000;
 
@@ -206,24 +182,16 @@ update_window_start(struct rq *rq, u64 wallclock)
 	rq->window_start += (u64)nr_windows * (u64)walt_ravg_window;
 }
 
+/*
+ * Translate absolute delta time accounted on a CPU
+ * to a scale where 1024 is the capacity of the most
+ * capable CPU running at FMAX
+ */
 static u64 scale_exec_time(u64 delta, struct rq *rq)
 {
-	unsigned int cur_freq = rq->cur_freq;
-	int sf;
-
-	if (unlikely(cur_freq > max_possible_freq))
-		cur_freq = rq->max_possible_freq;
-
-	/* round up div64 */
-	delta = div64_u64(delta * cur_freq + max_possible_freq - 1,
-			  max_possible_freq);
-
-	sf = DIV_ROUND_UP(rq->efficiency * 1024, max_possible_efficiency);
-
-	delta *= sf;
-	delta >>= 10;
+	unsigned long capcurr = capacity_curr_of(cpu_of(rq));
 
-	return delta;
+	return (delta * capcurr) >> SCHED_CAPACITY_SHIFT;
 }
 
 static int cpu_is_waiting_on_io(struct rq *rq)
@@ -746,33 +714,6 @@ done:
 	p->ravg.mark_start = wallclock;
 }
 
-unsigned long __weak arch_get_cpu_efficiency(int cpu)
-{
-	return SCHED_LOAD_SCALE;
-}
-
-void walt_init_cpu_efficiency(void)
-{
-	int i, efficiency;
-	unsigned int max = 0, min = UINT_MAX;
-
-	for_each_possible_cpu(i) {
-		efficiency = arch_get_cpu_efficiency(i);
-		cpu_rq(i)->efficiency = efficiency;
-
-		if (efficiency > max)
-			max = efficiency;
-		if (efficiency < min)
-			min = efficiency;
-	}
-
-	if (max)
-		max_possible_efficiency = max;
-
-	if (min)
-		min_possible_efficiency = min;
-}
-
 static void reset_task_stats(struct task_struct *p)
 {
 	u32 sum = 0;
@@ -877,242 +818,6 @@ void walt_fixup_busy_time(struct task_struct *p, int new_cpu)
 		double_rq_unlock(src_rq, dest_rq);
 }
 
-/*
- * Return 'capacity' of a cpu in reference to "least" efficient cpu, such that
- * least efficient cpu gets capacity of 1024
- */
-static unsigned long capacity_scale_cpu_efficiency(int cpu)
-{
-	return (1024 * cpu_rq(cpu)->efficiency) / min_possible_efficiency;
-}
-
-/*
- * Return 'capacity' of a cpu in reference to cpu with lowest max_freq
- * (min_max_freq), such that one with lowest max_freq gets capacity of 1024.
- */
-static unsigned long capacity_scale_cpu_freq(int cpu)
-{
-	return (1024 * cpu_rq(cpu)->max_freq) / min_max_freq;
-}
-
-/*
- * Return load_scale_factor of a cpu in reference to "most" efficient cpu, so
- * that "most" efficient cpu gets a load_scale_factor of 1
- */
-static unsigned long load_scale_cpu_efficiency(int cpu)
-{
-	return DIV_ROUND_UP(1024 * max_possible_efficiency,
-			    cpu_rq(cpu)->efficiency);
-}
-
-/*
- * Return load_scale_factor of a cpu in reference to cpu with best max_freq
- * (max_possible_freq), so that one with best max_freq gets a load_scale_factor
- * of 1.
- */
-static unsigned long load_scale_cpu_freq(int cpu)
-{
-	return DIV_ROUND_UP(1024 * max_possible_freq, cpu_rq(cpu)->max_freq);
-}
-
-static int compute_capacity(int cpu)
-{
-	int capacity = 1024;
-
-	capacity *= capacity_scale_cpu_efficiency(cpu);
-	capacity >>= 10;
-
-	capacity *= capacity_scale_cpu_freq(cpu);
-	capacity >>= 10;
-
-	return capacity;
-}
-
-static int compute_load_scale_factor(int cpu)
-{
-	int load_scale = 1024;
-
-	/*
-	 * load_scale_factor accounts for the fact that task load
-	 * is in reference to "best" performing cpu. Task's load will need to be
-	 * scaled (up) by a factor to determine suitability to be placed on a
-	 * (little) cpu.
-	 */
-	load_scale *= load_scale_cpu_efficiency(cpu);
-	load_scale >>= 10;
-
-	load_scale *= load_scale_cpu_freq(cpu);
-	load_scale >>= 10;
-
-	return load_scale;
-}
-
-static int cpufreq_notifier_policy(struct notifier_block *nb,
-		unsigned long val, void *data)
-{
-	struct cpufreq_policy *policy = (struct cpufreq_policy *)data;
-	int i, update_max = 0;
-	u64 highest_mpc = 0, highest_mplsf = 0;
-	const struct cpumask *cpus = policy->related_cpus;
-	unsigned int orig_min_max_freq = min_max_freq;
-	unsigned int orig_max_possible_freq = max_possible_freq;
-	/* Initialized to policy->max in case policy->related_cpus is empty! */
-	unsigned int orig_max_freq = policy->max;
-
-	if (val != CPUFREQ_NOTIFY)
-		return 0;
-
-	for_each_cpu(i, policy->related_cpus) {
-		cpumask_copy(&cpu_rq(i)->freq_domain_cpumask,
-			     policy->related_cpus);
-		orig_max_freq = cpu_rq(i)->max_freq;
-		cpu_rq(i)->min_freq = policy->min;
-		cpu_rq(i)->max_freq = policy->max;
-		cpu_rq(i)->cur_freq = policy->cur;
-		cpu_rq(i)->max_possible_freq = policy->cpuinfo.max_freq;
-	}
-
-	max_possible_freq = max(max_possible_freq, policy->cpuinfo.max_freq);
-	if (min_max_freq == 1)
-		min_max_freq = UINT_MAX;
-	min_max_freq = min(min_max_freq, policy->cpuinfo.max_freq);
-	BUG_ON(!min_max_freq);
-	BUG_ON(!policy->max);
-
-	/* Changes to policy other than max_freq don't require any updates */
-	if (orig_max_freq == policy->max)
-		return 0;
-
-	/*
-	 * A changed min_max_freq or max_possible_freq (possible during bootup)
-	 * needs to trigger re-computation of load_scale_factor and capacity for
-	 * all possible cpus (even those offline). It also needs to trigger
-	 * re-computation of nr_big_task count on all online cpus.
-	 *
-	 * A changed rq->max_freq otoh needs to trigger re-computation of
-	 * load_scale_factor and capacity for just the cluster of cpus involved.
-	 * Since small task definition depends on max_load_scale_factor, a
-	 * changed load_scale_factor of one cluster could influence
-	 * classification of tasks in another cluster. Hence a changed
-	 * rq->max_freq will need to trigger re-computation of nr_big_task
-	 * count on all online cpus.
-	 *
-	 * While it should be sufficient for nr_big_tasks to be
-	 * re-computed for only online cpus, we have inadequate context
-	 * information here (in policy notifier) with regard to hotplug-safety
-	 * context in which notification is issued. As a result, we can't use
-	 * get_online_cpus() here, as it can lead to deadlock. Until cpufreq is
-	 * fixed up to issue notification always in hotplug-safe context,
-	 * re-compute nr_big_task for all possible cpus.
-	 */
-
-	if (orig_min_max_freq != min_max_freq ||
-		orig_max_possible_freq != max_possible_freq) {
-			cpus = cpu_possible_mask;
-			update_max = 1;
-	}
-
-	/*
-	 * Changed load_scale_factor can trigger reclassification of tasks as
-	 * big or small. Make this change "atomic" so that tasks are accounted
-	 * properly due to changed load_scale_factor
-	 */
-	for_each_cpu(i, cpus) {
-		struct rq *rq = cpu_rq(i);
-
-		rq->capacity = compute_capacity(i);
-		rq->load_scale_factor = compute_load_scale_factor(i);
-
-		if (update_max) {
-			u64 mpc, mplsf;
-
-			mpc = div_u64(((u64) rq->capacity) *
-				rq->max_possible_freq, rq->max_freq);
-			rq->max_possible_capacity = (int) mpc;
-
-			mplsf = div_u64(((u64) rq->load_scale_factor) *
-				rq->max_possible_freq, rq->max_freq);
-
-			if (mpc > highest_mpc) {
-				highest_mpc = mpc;
-				cpumask_clear(&mpc_mask);
-				cpumask_set_cpu(i, &mpc_mask);
-			} else if (mpc == highest_mpc) {
-				cpumask_set_cpu(i, &mpc_mask);
-			}
-
-			if (mplsf > highest_mplsf)
-				highest_mplsf = mplsf;
-		}
-	}
-
-	if (update_max) {
-		max_possible_capacity = highest_mpc;
-		max_load_scale_factor = highest_mplsf;
-	}
-
-	return 0;
-}
-
-static int cpufreq_notifier_trans(struct notifier_block *nb,
-		unsigned long val, void *data)
-{
-	struct cpufreq_freqs *freq = (struct cpufreq_freqs *)data;
-	unsigned int cpu = freq->cpu, new_freq = freq->new;
-	unsigned long flags;
-	int i;
-
-	if (val != CPUFREQ_POSTCHANGE)
-		return 0;
-
-	BUG_ON(!new_freq);
-
-	if (cpu_rq(cpu)->cur_freq == new_freq)
-		return 0;
-
-	for_each_cpu(i, &cpu_rq(cpu)->freq_domain_cpumask) {
-		struct rq *rq = cpu_rq(i);
-
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		walt_update_task_ravg(rq->curr, rq, TASK_UPDATE,
-				      walt_ktime_clock(), 0);
-		rq->cur_freq = new_freq;
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-	}
-
-	return 0;
-}
-
-static struct notifier_block notifier_policy_block = {
-	.notifier_call = cpufreq_notifier_policy
-};
-
-static struct notifier_block notifier_trans_block = {
-	.notifier_call = cpufreq_notifier_trans
-};
-
-static int register_sched_callback(void)
-{
-	int ret;
-
-	ret = cpufreq_register_notifier(&notifier_policy_block,
-						CPUFREQ_POLICY_NOTIFIER);
-
-	if (!ret)
-		ret = cpufreq_register_notifier(&notifier_trans_block,
-						CPUFREQ_TRANSITION_NOTIFIER);
-
-	return 0;
-}
-
-/*
- * cpufreq callbacks can be registered at core_initcall or later time.
- * Any registration done prior to that is "forgotten" by cpufreq. See
- * initialization of variable init_cpufreq_transition_notifier_list_called
- * for further information.
- */
-core_initcall(register_sched_callback);
-
 void walt_init_new_task_load(struct task_struct *p)
 {
 	int i;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index bec2fce9fafc..01e7246de8df 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -250,7 +250,7 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 {
 	struct kmem_cache *s;
 
-	if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
+	if (slab_nomerge)
 		return NULL;
 
 	if (ctor)
@@ -261,6 +261,9 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 	size = ALIGN(size, align);
 	flags = kmem_cache_flags(size, flags, name, NULL);
 
+	if (flags & SLAB_NEVER_MERGE)
+		return NULL;
+
 	list_for_each_entry_reverse(s, &slab_caches, list) {
 		if (slab_unmergeable(s))
 			continue;
diff --git a/net/core/sock.c b/net/core/sock.c
index 39e9ab7c598e..acc60ec11630 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1528,6 +1528,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 
 		sock_copy(newsk, sk);
 
+		newsk->sk_prot_creator = sk->sk_prot;
+
 		/* SANITY */
 		if (likely(newsk->sk_net_refcnt))
 			get_net(sock_net(newsk));
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 65036891e080..a03f834f16d5 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -156,6 +156,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct ip_tunnel_parm *parms = &tunnel->parms;
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;	/* Device to other host */
+	int pkt_len = skb->len;
 	int err;
 
 	if (!dst) {
@@ -199,7 +200,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	err = dst_output(tunnel->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0)
-		err = skb->len;
+		err = pkt_len;
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 	return NETDEV_TX_OK;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ab0efaca4a78..6150a038711b 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1177,24 +1177,25 @@ static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
 }
 
 static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
-			unsigned short type,
-			const void *daddr, const void *saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen);
-	__be16 *p = (__be16 *)(ipv6h+1);
+	struct ipv6hdr *ipv6h;
+	__be16 *p;
 
-	ip6_flow_hdr(ipv6h, 0,
-		     ip6_make_flowlabel(dev_net(dev), skb,
-					t->fl.u.ip6.flowlabel, true,
-					&t->fl.u.ip6));
+	ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen + sizeof(*ipv6h));
+	ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+						  t->fl.u.ip6.flowlabel,
+						  true, &t->fl.u.ip6));
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = NEXTHDR_GRE;
 	ipv6h->saddr = t->parms.laddr;
 	ipv6h->daddr = t->parms.raddr;
 
-	p[0]		= t->parms.o_flags;
-	p[1]		= htons(type);
+	p = (__be16 *)(ipv6h + 1);
+	p[0] = t->parms.o_flags;
+	p[1] = htons(type);
 
 	/*
 	 *	Set the source hardware address.
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5b7433887eda..f615f982961a 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -434,6 +434,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *tdev;
 	struct xfrm_state *x;
+	int pkt_len = skb->len;
 	int err = -1;
 	int mtu;
 
@@ -487,7 +488,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
 
 		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += skb->len;
+		tstats->tx_bytes += pkt_len;
 		tstats->tx_packets++;
 		u64_stats_update_end(&tstats->syncp);
 	} else {
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index d3dec414fd44..d48281ca9c72 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1321,6 +1321,9 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	struct sock *sk = NULL;
 
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
+
+	l2tp_tunnel_closeall(tunnel);
+
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
 		goto out;
@@ -1640,15 +1643,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 
 /* This function is used by the netlink TUNNEL_DELETE command.
  */
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	l2tp_tunnel_inc_refcount(tunnel);
-	l2tp_tunnel_closeall(tunnel);
-	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
-		l2tp_tunnel_dec_refcount(tunnel);
-		return 1;
+	if (!test_and_set_bit(0, &tunnel->dead)) {
+		l2tp_tunnel_inc_refcount(tunnel);
+		queue_work(l2tp_wq, &tunnel->del_work);
 	}
-	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 555d962a62d2..9cf546846edb 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -169,6 +169,9 @@ struct l2tp_tunnel_cfg {
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+
+	unsigned long		dead;
+
 	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
@@ -253,7 +256,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
 					 u32 session_id, u32 peer_session_id,
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index d2075804cbff..a450be6812b8 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -662,7 +662,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
 	}
 
 	/* No need to do anything if the driver does all */
-	if (ieee80211_hw_check(&local->hw, AP_LINK_PS))
+	if (ieee80211_hw_check(&local->hw, AP_LINK_PS) && !local->ops->set_tim)
 		return;
 
 	if (sta->dead)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index acf5c7b3f378..7f16d19d6198 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -395,7 +395,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
 	struct net *net = nf_ct_exp_net(expect);
 	struct hlist_node *next;
 	unsigned int h;
-	int ret = 1;
+	int ret = 0;
 
 	if (!master_help) {
 		ret = -ESHUTDOWN;
@@ -445,7 +445,7 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 
 	spin_lock_bh(&nf_conntrack_expect_lock);
 	ret = __nf_ct_expect_check(expect);
-	if (ret <= 0)
+	if (ret < 0)
 		goto out;
 
 	ret = nf_ct_expect_insert(expect);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b70055fc30cb..241f69039a72 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1652,10 +1652,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 	mutex_lock(&fanout_mutex);
 
-	err = -EINVAL;
-	if (!po->running)
-		goto out;
-
 	err = -EALREADY;
 	if (po->fanout)
 		goto out;
@@ -1704,7 +1700,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
-	if (match->type == type &&
+
+	spin_lock(&po->bind_lock);
+	if (po->running &&
+	    match->type == type &&
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
@@ -1716,6 +1715,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 			err = 0;
 		}
 	}
+	spin_unlock(&po->bind_lock);
+
+	if (err && !atomic_read(&match->sk_ref)) {
+		list_del(&match->list);
+		kfree(match);
+	}
+
 out:
 	if (err && rollover) {
 		kfree(rollover);
@@ -2650,6 +2656,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	int vnet_hdr_len;
 	struct packet_sock *po = pkt_sk(sk);
 	unsigned short gso_type = 0;
+	bool has_vnet_hdr = false;
 	int hlen, tlen, linear;
 	int extra_len = 0;
 	ssize_t n;
@@ -2737,6 +2744,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 				goto out_unlock;
 
 		}
+		has_vnet_hdr = true;
 	}
 
 	if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
@@ -2796,7 +2804,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	packet_pick_tx_queue(dev, skb);
 
-	if (po->has_vnet_hdr) {
+	if (has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
 			u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start);
 			u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset);
@@ -2938,13 +2946,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 	int ret = 0;
 	bool unlisted = false;
 
-	if (po->fanout)
-		return -EINVAL;
-
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
 	rcu_read_lock();
 
+	if (po->fanout) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	if (name) {
 		dev = dev_get_by_name_rcu(sock_net(sk), name);
 		if (!dev) {
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 8740930f0787..67bddcb2ff46 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -541,7 +541,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 		return false;
 	if (msg_errcode(msg))
 		return false;
-	*err = -TIPC_ERR_NO_NAME;
+	*err = TIPC_ERR_NO_NAME;
 	if (skb_linearize(skb))
 		return false;
 	msg = buf_msg(skb);