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

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/s390/kvm/kvm-s390.c

@@ -769,7 +769,7 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 
 /*
  * Must be called with kvm->srcu held to avoid races on memslots, and with
- * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
+ * kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
  */
 static int kvm_s390_vm_start_migration(struct kvm *kvm)
 {
@@ -825,7 +825,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 }
 
 /*
- * Must be called with kvm->lock to avoid races with ourselves and
+ * Must be called with kvm->slots_lock to avoid races with ourselves and
  * kvm_s390_vm_start_migration.
  */
 static int kvm_s390_vm_stop_migration(struct kvm *kvm)
@@ -840,6 +840,8 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 
 	if (kvm->arch.use_cmma) {
 		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
+		/* We have to wait for the essa emulation to finish */
+		synchronize_srcu(&kvm->srcu);
 		vfree(mgs->pgste_bitmap);
 	}
 	kfree(mgs);
@@ -849,14 +851,12 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 static int kvm_s390_vm_set_migration(struct kvm *kvm,
 				     struct kvm_device_attr *attr)
 {
-	int idx, res = -ENXIO;
+	int res = -ENXIO;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->slots_lock);
 	switch (attr->attr) {
 	case KVM_S390_VM_MIGRATION_START:
-		idx = srcu_read_lock(&kvm->srcu);
 		res = kvm_s390_vm_start_migration(kvm);
-		srcu_read_unlock(&kvm->srcu, idx);
 		break;
 	case KVM_S390_VM_MIGRATION_STOP:
 		res = kvm_s390_vm_stop_migration(kvm);
@@ -864,7 +864,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 	default:
 		break;
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return res;
 }
@@ -1754,7 +1754,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_get_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		if (!r) {
 			r = copy_to_user(argp, &args, sizeof(args));
 			if (r)
@@ -1768,7 +1770,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_set_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		break;
 	}
 	default:

drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c

@@ -71,6 +71,10 @@ nvkm_pci_intr(int irq, void *arg)
 	struct nvkm_pci *pci = arg;
 	struct nvkm_device *device = pci->subdev.device;
 	bool handled = false;
+
+	if (pci->irq < 0)
+		return IRQ_HANDLED;
+
 	nvkm_mc_intr_unarm(device);
 	if (pci->msi)
 		pci->func->msi_rearm(pci);
@@ -84,11 +88,6 @@ nvkm_pci_fini(struct nvkm_subdev *subdev, bool suspend)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
 
-	if (pci->irq >= 0) {
-		free_irq(pci->irq, pci);
-		pci->irq = -1;
-	}
-
 	if (pci->agp.bridge)
 		nvkm_agp_fini(pci);
 
@@ -108,8 +107,20 @@ static int
 nvkm_pci_oneinit(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
-	if (pci_is_pcie(pci->pdev))
-		return nvkm_pcie_oneinit(pci);
+	struct pci_dev *pdev = pci->pdev;
+	int ret;
+
+	if (pci_is_pcie(pci->pdev)) {
+		ret = nvkm_pcie_oneinit(pci);
+		if (ret)
+			return ret;
+	}
+
+	ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
+	if (ret)
+		return ret;
+
+	pci->irq = pdev->irq;
 	return 0;
 }
 
@@ -117,7 +128,6 @@ static int
 nvkm_pci_init(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
-	struct pci_dev *pdev = pci->pdev;
 	int ret;
 
 	if (pci->agp.bridge) {
@@ -131,28 +141,34 @@ nvkm_pci_init(struct nvkm_subdev *subdev)
 	if (pci->func->init)
 		pci->func->init(pci);
 
-	ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
-	if (ret)
-		return ret;
-
-	pci->irq = pdev->irq;
-
 	/* Ensure MSI interrupts are armed, for the case where there are
 	 * already interrupts pending (for whatever reason) at load time.
 	 */
 	if (pci->msi)
 		pci->func->msi_rearm(pci);
 
-	return ret;
+	return 0;
 }
 
 static void *
 nvkm_pci_dtor(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pci *pci = nvkm_pci(subdev);
+
 	nvkm_agp_dtor(pci);
+
+	if (pci->irq >= 0) {
+		/* freq_irq() will call the handler, we use pci->irq == -1
+		 * to signal that it's been torn down and should be a noop.
+		 */
+		int irq = pci->irq;
+		pci->irq = -1;
+		free_irq(irq, pci);
+	}
+
 	if (pci->msi)
 		pci_disable_msi(pci->pdev);
+
 	return nvkm_pci(subdev);
 }
 

drivers/gpu/drm/vc4/vc4_gem.c

@@ -146,7 +146,7 @@ vc4_save_hang_state(struct drm_device *dev)
 	struct vc4_exec_info *exec[2];
 	struct vc4_bo *bo;
 	unsigned long irqflags;
-	unsigned int i, j, unref_list_count, prev_idx;
+	unsigned int i, j, k, unref_list_count;
 
 	kernel_state = kcalloc(1, sizeof(*kernel_state), GFP_KERNEL);
 	if (!kernel_state)
@@ -182,7 +182,7 @@ vc4_save_hang_state(struct drm_device *dev)
 		return;
 	}
 
-	prev_idx = 0;
+	k = 0;
 	for (i = 0; i < 2; i++) {
 		if (!exec[i])
 			continue;
@@ -197,7 +197,7 @@ vc4_save_hang_state(struct drm_device *dev)
 			WARN_ON(!refcount_read(&bo->usecnt));
 			refcount_inc(&bo->usecnt);
 			drm_gem_object_get(&exec[i]->bo[j]->base);
-			kernel_state->bo[j + prev_idx] = &exec[i]->bo[j]->base;
+			kernel_state->bo[k++] = &exec[i]->bo[j]->base;
 		}
 
 		list_for_each_entry(bo, &exec[i]->unref_list, unref_head) {
@@ -205,12 +205,12 @@ vc4_save_hang_state(struct drm_device *dev)
 			 * because they are naturally unpurgeable.
 			 */
 			drm_gem_object_get(&bo->base.base);
-			kernel_state->bo[j + prev_idx] = &bo->base.base;
-			j++;
+			kernel_state->bo[k++] = &bo->base.base;
 		}
-		prev_idx = j + 1;
 	}
 
+	WARN_ON_ONCE(k != state->bo_count);
+
 	if (exec[0])
 		state->start_bin = exec[0]->ct0ca;
 	if (exec[1])
@@ -436,6 +436,19 @@ vc4_flush_caches(struct drm_device *dev)
 		  VC4_SET_FIELD(0xf, V3D_SLCACTL_ICC));
 }
 
+static void
+vc4_flush_texture_caches(struct drm_device *dev)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	V3D_WRITE(V3D_L2CACTL,
+		  V3D_L2CACTL_L2CCLR);
+
+	V3D_WRITE(V3D_SLCACTL,
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T1CC) |
+		  VC4_SET_FIELD(0xf, V3D_SLCACTL_T0CC));
+}
+
 /* Sets the registers for the next job to be actually be executed in
  * the hardware.
  *
@@ -474,6 +487,14 @@ vc4_submit_next_render_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	/* A previous RCL may have written to one of our textures, and
+	 * our full cache flush at bin time may have occurred before
+	 * that RCL completed.  Flush the texture cache now, but not
+	 * the instructions or uniforms (since we don't write those
+	 * from an RCL).
+	 */
+	vc4_flush_texture_caches(dev);
+
 	submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
 }
 

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -1456,8 +1456,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb,
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
 	int e = skb_queue_empty(&priv->cm.skb_queue);
 
-	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)

drivers/input/joystick/xpad.c

@@ -229,6 +229,7 @@ static const struct xpad_device {
 	{ 0x0e6f, 0x0213, "Afterglow Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0e6f, 0x021f, "Rock Candy Gamepad for Xbox 360", 0, XTYPE_XBOX360 },
 	{ 0x0e6f, 0x0246, "Rock Candy Gamepad for Xbox One 2015", 0, XTYPE_XBOXONE },
+	{ 0x0e6f, 0x02ab, "PDP Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0301, "Logic3 Controller", 0, XTYPE_XBOX360 },
 	{ 0x0e6f, 0x0346, "Rock Candy Gamepad for Xbox One 2016", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0401, "Logic3 Controller", 0, XTYPE_XBOX360 },
@@ -475,6 +476,22 @@ static const u8 xboxone_hori_init[] = {
 	0x00, 0x00, 0x00, 0x80, 0x00
 };
 
+/*
+ * This packet is required for some of the PDP pads to start
+ * sending input reports. One of those pads is (0x0e6f:0x02ab).
+ */
+static const u8 xboxone_pdp_init1[] = {
+	0x0a, 0x20, 0x00, 0x03, 0x00, 0x01, 0x14
+};
+
+/*
+ * This packet is required for some of the PDP pads to start
+ * sending input reports. One of those pads is (0x0e6f:0x02ab).
+ */
+static const u8 xboxone_pdp_init2[] = {
+	0x06, 0x20, 0x00, 0x02, 0x01, 0x00
+};
+
 /*
  * A specific rumble packet is required for some PowerA pads to start
  * sending input reports. One of those pads is (0x24c6:0x543a).
@@ -505,6 +522,8 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init),
 	XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init),
+	XBOXONE_INIT_PKT(0x0e6f, 0x02ab, xboxone_pdp_init1),
+	XBOXONE_INIT_PKT(0x0e6f, 0x02ab, xboxone_pdp_init2),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumblebegin_init),

drivers/input/mouse/trackpoint.h

@@ -21,10 +21,16 @@
 #define TP_COMMAND		0xE2	/* Commands start with this */
 
 #define TP_READ_ID		0xE1	/* Sent for device identification */
-#define TP_MAGIC_IDENT		0x03	/* Sent after a TP_READ_ID followed */
-					/* by the firmware ID */
-					/* Firmware ID includes 0x1, 0x2, 0x3 */
 
+/*
+ * Valid first byte responses to the "Read Secondary ID" (0xE1) command.
+ * 0x01 was the original IBM trackpoint, others implement very limited
+ * subset of trackpoint features.
+ */
+#define TP_VARIANT_IBM		0x01
+#define TP_VARIANT_ALPS		0x02
+#define TP_VARIANT_ELAN		0x03
+#define TP_VARIANT_NXP		0x04
 
 /*
  * Commands
@@ -136,18 +142,20 @@
 
 #define MAKE_PS2_CMD(params, results, cmd) ((params<<12) | (results<<8) | (cmd))
 
-struct trackpoint_data
-{
-	unsigned char sensitivity, speed, inertia, reach;
-	unsigned char draghys, mindrag;
-	unsigned char thresh, upthresh;
-	unsigned char ztime, jenks;
-	unsigned char drift_time;
+struct trackpoint_data {
+	u8 variant_id;
+	u8 firmware_id;
+
+	u8 sensitivity, speed, inertia, reach;
+	u8 draghys, mindrag;
+	u8 thresh, upthresh;
+	u8 ztime, jenks;
+	u8 drift_time;
 
 	/* toggles */
-	unsigned char press_to_select;
-	unsigned char skipback;
-	unsigned char ext_dev;
+	bool press_to_select;
+	bool skipback;
+	bool ext_dev;
 };
 
 #ifdef CONFIG_MOUSE_PS2_TRACKPOINT

drivers/input/rmi4/rmi_f01.c

@@ -570,14 +570,19 @@ static int rmi_f01_probe(struct rmi_function *fn)
 
 	dev_set_drvdata(&fn->dev, f01);
 
-	error = devm_device_add_group(&fn->rmi_dev->dev, &rmi_f01_attr_group);
+	error = sysfs_create_group(&fn->rmi_dev->dev.kobj, &rmi_f01_attr_group);
 	if (error)
-		dev_warn(&fn->dev,
-			 "Failed to create attribute group: %d\n", error);
+		dev_warn(&fn->dev, "Failed to create sysfs group: %d\n", error);
 
 	return 0;
 }
 
+static void rmi_f01_remove(struct rmi_function *fn)
+{
+	/* Note that the bus device is used, not the F01 device */
+	sysfs_remove_group(&fn->rmi_dev->dev.kobj, &rmi_f01_attr_group);
+}
+
 static int rmi_f01_config(struct rmi_function *fn)
 {
 	struct f01_data *f01 = dev_get_drvdata(&fn->dev);
@@ -717,6 +722,7 @@ struct rmi_function_handler rmi_f01_handler = {
 	},
 	.func		= 0x01,
 	.probe		= rmi_f01_probe,
+	.remove		= rmi_f01_remove,
 	.config		= rmi_f01_config,
 	.attention	= rmi_f01_attention,
 	.suspend	= rmi_f01_suspend,

drivers/input/touchscreen/s6sy761.c

-/*
- * Copyright (c) 2017 Samsung Electronics Co., Ltd.
- * Author: Andi Shyti <andi.shyti@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Samsung S6SY761 Touchscreen device driver
- */
+// SPDX-License-Identifier: GPL-2.0
+// Samsung S6SY761 Touchscreen device driver
+//
+// Copyright (c) 2017 Samsung Electronics Co., Ltd.
+// Copyright (c) 2017 Andi Shyti <andi.shyti@samsung.com>
 
 #include <asm/unaligned.h>
 #include <linux/delay.h>

drivers/input/touchscreen/stmfts.c

-/*
- * Copyright (c) 2017 Samsung Electronics Co., Ltd.
- * Author: Andi Shyti <andi.shyti@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * STMicroelectronics FTS Touchscreen device driver
- */
+// SPDX-License-Identifier: GPL-2.0
+// STMicroelectronics FTS Touchscreen device driver
+//
+// Copyright (c) 2017 Samsung Electronics Co., Ltd.
+// Copyright (c) 2017 Andi Shyti <andi.shyti@samsung.com>
 
 #include <linux/delay.h>
 #include <linux/i2c.h>

drivers/net/ethernet/realtek/r8169.c

@@ -2235,19 +2235,14 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd)
 	void __iomem *ioaddr = tp->mmio_addr;
 	dma_addr_t paddr = tp->counters_phys_addr;
 	u32 cmd;
-	bool ret;
 
 	RTL_W32(CounterAddrHigh, (u64)paddr >> 32);
+	RTL_R32(CounterAddrHigh);
 	cmd = (u64)paddr & DMA_BIT_MASK(32);
 	RTL_W32(CounterAddrLow, cmd);
 	RTL_W32(CounterAddrLow, cmd | counter_cmd);
 
-	ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
-
-	RTL_W32(CounterAddrLow, 0);
-	RTL_W32(CounterAddrHigh, 0);
-
-	return ret;
+	return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000);
 }
 
 static bool rtl8169_reset_counters(struct net_device *dev)

drivers/net/geneve.c

@@ -829,7 +829,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		int mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr) -
 			  GENEVE_BASE_HLEN - info->options_len - 14;
 
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 	}
 
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
@@ -875,7 +875,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		int mtu = dst_mtu(dst) - sizeof(struct ipv6hdr) -
 			  GENEVE_BASE_HLEN - info->options_len - 14;
 
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 	}
 
 	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);

drivers/net/vrf.c

@@ -673,8 +673,9 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 				  struct sock *sk,
 				  struct sk_buff *skb)
 {
-	/* don't divert multicast */
-	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+	/* don't divert multicast or local broadcast */
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr) ||
+	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
 	if (qdisc_tx_is_default(vrf_dev))

drivers/net/vxlan.c

@@ -2158,8 +2158,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (skb_dst(skb)) {
 			int mtu = dst_mtu(ndst) - VXLAN_HEADROOM;
 
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL,
-						       skb, mtu);
+			skb_dst_update_pmtu(skb, mtu);
 		}
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
@@ -2200,8 +2199,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		if (skb_dst(skb)) {
 			int mtu = dst_mtu(ndst) - VXLAN6_HEADROOM;
 
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL,
-						       skb, mtu);
+			skb_dst_update_pmtu(skb, mtu);
 		}
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);

fs/btrfs/delayed-inode.c

@@ -1633,28 +1633,18 @@ void btrfs_readdir_put_delayed_items(struct inode *inode,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index)
 {
-	struct btrfs_delayed_item *curr, *next;
-	int ret;
-
-	if (list_empty(del_list))
-		return 0;
+	struct btrfs_delayed_item *curr;
+	int ret = 0;
 
-	list_for_each_entry_safe(curr, next, del_list, readdir_list) {
+	list_for_each_entry(curr, del_list, readdir_list) {
 		if (curr->key.offset > index)
 			break;
-
-		list_del(&curr->readdir_list);
-		ret = (curr->key.offset == index);
-
-		if (refcount_dec_and_test(&curr->refs))
-			kfree(curr);
-
-		if (ret)
-			return 1;
-		else
-			continue;
+		if (curr->key.offset == index) {
+			ret = 1;
+			break;
+		}
 	}
-	return 0;
+	return ret;
 }
 
 /*

fs/orangefs/file.c

@@ -452,7 +452,7 @@ ssize_t orangefs_inode_read(struct inode *inode,
 static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
-	loff_t pos = *(&iocb->ki_pos);
+	loff_t pos = iocb->ki_pos;
 	ssize_t rc = 0;
 
 	BUG_ON(iocb->private);
@@ -492,9 +492,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
 		}
 	}
 
-	if (file->f_pos > i_size_read(file->f_mapping->host))
-		orangefs_i_size_write(file->f_mapping->host, file->f_pos);
-
 	rc = generic_write_checks(iocb, iter);
 
 	if (rc <= 0) {
@@ -508,7 +505,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
 	 * pos to the end of the file, so we will wait till now to set
 	 * pos...
 	 */
-	pos = *(&iocb->ki_pos);
+	pos = iocb->ki_pos;
 
 	rc = do_readv_writev(ORANGEFS_IO_WRITE,
 			     file,

fs/orangefs/orangefs-kernel.h

@@ -533,17 +533,6 @@ do {									\
 	sys_attr.mask = ORANGEFS_ATTR_SYS_ALL_SETABLE;			\
 } while (0)
 
-static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
-{
-#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
-	inode_lock(inode);
-#endif
-	i_size_write(inode, i_size);
-#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
-	inode_unlock(inode);
-#endif
-}
-
 static inline void orangefs_set_timeout(struct dentry *dentry)
 {
 	unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;

include/net/dst.h

@@ -504,4 +504,12 @@ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 }
 #endif
 
+static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (dst && dst->ops->update_pmtu)
+		dst->ops->update_pmtu(dst, NULL, skb, mtu);
+}
+
 #endif /* _NET_DST_H */

include/net/net_namespace.h

@@ -223,6 +223,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return net1 == net2;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return refcount_read(&net->count) != 0;
+}
+
 void net_drop_ns(void *);
 
 #else
@@ -247,6 +252,11 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return 1;
 }
 
+static inline int check_net(const struct net *net)
+{
+	return 1;
+}
+
 #define net_drop_ns NULL
 #endif
 

net/dccp/ccids/ccid2.c

@@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
+	if (sk->sk_state == DCCP_CLOSED)
+		goto out;
+
 	/* back-off timer */
 	hc->tx_rto <<= 1;
 	if (hc->tx_rto > DCCP_RTO_MAX)

net/ipv4/ip_tunnel.c

@@ -520,8 +520,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	else
 		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&

net/ipv4/ip_vti.c

@@ -200,7 +200,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));

net/ipv4/tcp.c

@@ -2322,6 +2322,9 @@ void tcp_close(struct sock *sk, long timeout)
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
+		} else if (!check_net(sock_net(sk))) {
+			/* Not possible to send reset; just close */
+			tcp_set_state(sk, TCP_CLOSE);
 		}
 	}
 

net/ipv4/tcp_timer.c

@@ -48,11 +48,19 @@ static void tcp_write_err(struct sock *sk)
  *  to prevent DoS attacks. It is called when a retransmission timeout
  *  or zero probe timeout occurs on orphaned socket.
  *
+ *  Also close if our net namespace is exiting; in that case there is no
+ *  hope of ever communicating again since all netns interfaces are already
+ *  down (or about to be down), and we need to release our dst references,
+ *  which have been moved to the netns loopback interface, so the namespace
+ *  can finish exiting.  This condition is only possible if we are a kernel
+ *  socket, as those do not hold references to the namespace.
+ *
  *  Criteria is still not confirmed experimentally and may change.
  *  We kill the socket, if:
  *  1. If number of orphaned sockets exceeds an administratively configured
  *     limit.
  *  2. If we have strong memory pressure.
+ *  3. If our net namespace is exiting.
  */
 static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
@@ -81,6 +89,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
 	}
+
+	if (!check_net(sock_net(sk))) {
+		/* Not possible to send reset; just close */
+		tcp_done(sk);
+		return 1;
+	}
+
 	return 0;
 }
 

net/ipv6/ip6_tunnel.c

@@ -642,8 +642,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2,
-						rel_info);
+		skb_dst_update_pmtu(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
@@ -1134,8 +1133,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		mtu = 576;
 	}
 
-	if (skb_dst(skb) && !t->parms.collect_md)
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;

net/ipv6/ip6_vti.c

@@ -483,7 +483,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (!skb->ignore_df && skb->len > mtu) {
-		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)

net/ipv6/sit.c

@@ -934,8 +934,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			df = 0;
 		}
 
-		if (tunnel->parms.iph.daddr && skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		if (tunnel->parms.iph.daddr)
+			skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);

net/vmw_vsock/af_vsock.c

@@ -951,7 +951,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		 * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
 		 * but local send is not shutdown.
 		 */
-		if (sk->sk_state == TCP_CLOSE) {
+		if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 				mask |= POLLOUT | POLLWRNORM;