Linux 3.14

Pull vfs fixes from Al Viro:
 "Switch mnt_hash to hlist, turning the races between __lookup_mnt() and
  hash modifications into false negatives from __lookup_mnt() (instead
  of hangs)"

On the false negatives from __lookup_mnt():
 "The *only* thing we care about is not getting stuck in __lookup_mnt().
  If it misses an entry because something in front of it just got moved
  around, etc, we are fine.  We'll notice that mount_lock mismatch and
  that'll be it"

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  switch mnt_hash to hlist
  don't bother with propagate_mnt() unless the target is shared
  keep shadowed vfsmounts together
  resizable namespace.c hashes

MAINTAINERS

@@ -1832,8 +1832,8 @@ F:	net/bluetooth/
 F:	include/net/bluetooth/
 
 BONDING DRIVER
-M:	Jay Vosburgh <fubar@us.ibm.com>
-M:	Veaceslav Falico <vfalico@redhat.com>
+M:	Jay Vosburgh <j.vosburgh@gmail.com>
+M:	Veaceslav Falico <vfalico@gmail.com>
 M:	Andy Gospodarek <andy@greyhouse.net>
 L:	netdev@vger.kernel.org
 W:	http://sourceforge.net/projects/bonding/
@@ -2801,9 +2801,9 @@ S:	Supported
 F:	drivers/acpi/dock.c
 
 DOCUMENTATION
-M:	Rob Landley <rob@landley.net>
+M:	Randy Dunlap <rdunlap@infradead.org>
 L:	linux-doc@vger.kernel.org
-T:	TBD
+T:	quilt http://www.infradead.org/~rdunlap/Doc/patches/
 S:	Maintained
 F:	Documentation/
 
@@ -6006,6 +6006,7 @@ F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
 F:	tools/net/
 F:	tools/testing/selftests/net/
+F:	lib/random32.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*

arch/x86/include/asm/pgtable.h

@@ -445,20 +445,10 @@ static inline int pte_same(pte_t a, pte_t b)
 	return a.pte == b.pte;
 }
 
-static inline int pteval_present(pteval_t pteval)
-{
-	/*
-	 * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this
-	 * way clearly states that the intent is that protnone and numa
-	 * hinting ptes are considered present for the purposes of
-	 * pagetable operations like zapping, protection changes, gup etc.
-	 */
-	return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA);
-}
-
 static inline int pte_present(pte_t a)
 {
-	return pteval_present(pte_flags(a));
+	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
+			       _PAGE_NUMA);
 }
 
 #define pte_accessible pte_accessible

arch/x86/include/asm/topology.h

@@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { }
 
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 #endif

arch/x86/xen/mmu.c

@@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-	if (pteval_present(val)) {
+	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		unsigned long pfn = mfn_to_pfn(mfn);
 
@@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 
 static pteval_t pte_pfn_to_mfn(pteval_t val)
 {
-	if (pteval_present(val)) {
+	if (val & _PAGE_PRESENT) {
 		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & PTE_FLAGS_MASK;
 		unsigned long mfn;

drivers/block/rbd.c

@@ -2109,7 +2109,6 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request)
 	rbd_assert(img_request->obj_request_count > 0);
 	rbd_assert(which != BAD_WHICH);
 	rbd_assert(which < img_request->obj_request_count);
-	rbd_assert(which >= img_request->next_completion);
 
 	spin_lock_irq(&img_request->completion_lock);
 	if (which != img_request->next_completion)

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -842,7 +842,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 	dev_priv->gtt.base.clear_range(&dev_priv->gtt.base,
 				       dev_priv->gtt.base.start / PAGE_SIZE,
 				       dev_priv->gtt.base.total / PAGE_SIZE,
-				       false);
+				       true);
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -866,13 +866,16 @@ static int nouveau_pmops_runtime_suspend(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (nouveau_runtime_pm == 0)
-		return -EINVAL;
+	if (nouveau_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	/* are we optimus enabled? */
 	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
 		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
-		return -EINVAL;
+		pm_runtime_forbid(dev);
+		return -EBUSY;
 	}
 
 	nv_debug_level(SILENT);
@@ -923,12 +926,15 @@ static int nouveau_pmops_runtime_idle(struct device *dev)
 	struct nouveau_drm *drm = nouveau_drm(drm_dev);
 	struct drm_crtc *crtc;
 
-	if (nouveau_runtime_pm == 0)
+	if (nouveau_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
 		return -EBUSY;
+	}
 
 	/* are we optimus enabled? */
 	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
 		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 

drivers/gpu/drm/radeon/radeon_drv.c

@@ -403,11 +403,15 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (radeon_runtime_pm == 0)
-		return -EINVAL;
+	if (radeon_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
-	if (radeon_runtime_pm == -1 && !radeon_is_px())
-		return -EINVAL;
+	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
@@ -456,12 +460,15 @@ static int radeon_pmops_runtime_idle(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	struct drm_crtc *crtc;
 
-	if (radeon_runtime_pm == 0)
+	if (radeon_runtime_pm == 0) {
+		pm_runtime_forbid(dev);
 		return -EBUSY;
+	}
 
 	/* are we PX enabled? */
 	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
 		DRM_DEBUG_DRIVER("failing to power off - not px\n");
+		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 

drivers/gpu/drm/udl/udl_gem.c

@@ -177,8 +177,10 @@ void udl_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->vmapping)
 		udl_gem_vunmap(obj);
 
-	if (gem_obj->import_attach)
+	if (gem_obj->import_attach) {
 		drm_prime_gem_destroy(gem_obj, obj->sg);
+		put_device(gem_obj->dev->dev);
+	}
 
 	if (obj->pages)
 		udl_gem_put_pages(obj);
@@ -256,9 +258,12 @@ struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev,
 	int ret;
 
 	/* need to attach */
+	get_device(dev->dev);
 	attach = dma_buf_attach(dma_buf, dev->dev);
-	if (IS_ERR(attach))
+	if (IS_ERR(attach)) {
+		put_device(dev->dev);
 		return ERR_CAST(attach);
+	}
 
 	get_dma_buf(dma_buf);
 
@@ -282,6 +287,6 @@ fail_unmap:
 fail_detach:
 	dma_buf_detach(dma_buf, attach);
 	dma_buf_put(dma_buf);
-
+	put_device(dev->dev);
 	return ERR_PTR(ret);
 }

drivers/i2c/busses/i2c-cpm.c

@@ -39,7 +39,9 @@
 #include <linux/i2c.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <sysdev/fsl_soc.h>
 #include <asm/cpm.h>

drivers/input/evdev.c

@@ -954,11 +954,13 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 			return -EFAULT;
 
 		error = input_ff_upload(dev, &effect, file);
+		if (error)
+			return error;
 
 		if (put_user(effect.id, &(((struct ff_effect __user *)p)->id)))
 			return -EFAULT;
 
-		return error;
+		return 0;
 	}
 
 	/* Multi-number variable-length handlers */

drivers/input/keyboard/adp5588-keys.c

@@ -76,8 +76,18 @@ static int adp5588_gpio_get_value(struct gpio_chip *chip, unsigned off)
 	struct adp5588_kpad *kpad = container_of(chip, struct adp5588_kpad, gc);
 	unsigned int bank = ADP5588_BANK(kpad->gpiomap[off]);
 	unsigned int bit = ADP5588_BIT(kpad->gpiomap[off]);
+	int val;
 
-	return !!(adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank) & bit);
+	mutex_lock(&kpad->gpio_lock);
+
+	if (kpad->dir[bank] & bit)
+		val = kpad->dat_out[bank];
+	else
+		val = adp5588_read(kpad->client, GPIO_DAT_STAT1 + bank);
+
+	mutex_unlock(&kpad->gpio_lock);
+
+	return !!(val & bit);
 }
 
 static void adp5588_gpio_set_value(struct gpio_chip *chip,

drivers/input/misc/da9052_onkey.c

@@ -27,29 +27,32 @@ struct da9052_onkey {
 
 static void da9052_onkey_query(struct da9052_onkey *onkey)
 {
-	int key_stat;
+	int ret;
 
-	key_stat = da9052_reg_read(onkey->da9052, DA9052_EVENT_B_REG);
-	if (key_stat < 0) {
+	ret = da9052_reg_read(onkey->da9052, DA9052_STATUS_A_REG);
+	if (ret < 0) {
 		dev_err(onkey->da9052->dev,
-			"Failed to read onkey event %d\n", key_stat);
+			"Failed to read onkey event err=%d\n", ret);
 	} else {
 		/*
 		 * Since interrupt for deassertion of ONKEY pin is not
 		 * generated, onkey event state determines the onkey
 		 * button state.
 		 */
-		key_stat &= DA9052_EVENTB_ENONKEY;
-		input_report_key(onkey->input, KEY_POWER, key_stat);
-		input_sync(onkey->input);
-	}
+		bool pressed = !(ret & DA9052_STATUSA_NONKEY);
 
-	/*
-	 * Interrupt is generated only when the ONKEY pin is asserted.
-	 * Hence the deassertion of the pin is simulated through work queue.
-	 */
-	if (key_stat)
-		schedule_delayed_work(&onkey->work, msecs_to_jiffies(50));
+		input_report_key(onkey->input, KEY_POWER, pressed);
+		input_sync(onkey->input);
+
+		/*
+		 * Interrupt is generated only when the ONKEY pin
+		 * is asserted.  Hence the deassertion of the pin
+		 * is simulated through work queue.
+		 */
+		if (pressed)
+			schedule_delayed_work(&onkey->work,
+						msecs_to_jiffies(50));
+	}
 }
 
 static void da9052_onkey_work(struct work_struct *work)

drivers/input/mouse/cypress_ps2.c

@@ -409,7 +409,6 @@ static int cypress_set_input_params(struct input_dev *input,
 	__clear_bit(REL_X, input->relbit);
 	__clear_bit(REL_Y, input->relbit);
 
-	__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
 	__set_bit(EV_KEY, input->evbit);
 	__set_bit(BTN_LEFT, input->keybit);
 	__set_bit(BTN_RIGHT, input->keybit);

drivers/input/mouse/synaptics.c

@@ -265,11 +265,22 @@ static int synaptics_identify(struct psmouse *psmouse)
  * Read touchpad resolution and maximum reported coordinates
  * Resolution is left zero if touchpad does not support the query
  */
+
+static const int *quirk_min_max;
+
 static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
 
+	if (quirk_min_max) {
+		priv->x_min = quirk_min_max[0];
+		priv->x_max = quirk_min_max[1];
+		priv->y_min = quirk_min_max[2];
+		priv->y_max = quirk_min_max[3];
+		return 0;
+	}
+
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
 
@@ -1485,10 +1496,54 @@ static const struct dmi_system_id olpc_dmi_table[] __initconst = {
 	{ }
 };
 
+static const struct dmi_system_id min_max_dmi_table[] __initconst = {
+#if defined(CONFIG_DMI)
+	{
+		/* Lenovo ThinkPad Helix */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+		},
+		.driver_data = (int []){1024, 5052, 2258, 4832},
+	},
+	{
+		/* Lenovo ThinkPad X240 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
+		},
+		.driver_data = (int []){1232, 5710, 1156, 4696},
+	},
+	{
+		/* Lenovo ThinkPad T440s */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T540p */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
+		},
+		.driver_data = (int []){1024, 5056, 2058, 4832},
+	},
+#endif
+	{ }
+};
+
 void __init synaptics_module_init(void)
 {
+	const struct dmi_system_id *min_max_dmi;
+
 	impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
 	broken_olpc_ec = dmi_check_system(olpc_dmi_table);
+
+	min_max_dmi = dmi_first_match(min_max_dmi_table);
+	if (min_max_dmi)
+		quirk_min_max = min_max_dmi->driver_data;
 }
 
 static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)

drivers/input/mousedev.c

@@ -67,7 +67,6 @@ struct mousedev {
 	struct device dev;
 	struct cdev cdev;
 	bool exist;
-	bool is_mixdev;
 
 	struct list_head mixdev_node;
 	bool opened_by_mixdev;
@@ -77,6 +76,9 @@ struct mousedev {
 	int old_x[4], old_y[4];
 	int frac_dx, frac_dy;
 	unsigned long touch;
+
+	int (*open_device)(struct mousedev *mousedev);
+	void (*close_device)(struct mousedev *mousedev);
 };
 
 enum mousedev_emul {
@@ -116,9 +118,6 @@ static unsigned char mousedev_imex_seq[] = { 0xf3, 200, 0xf3, 200, 0xf3, 80 };
 static struct mousedev *mousedev_mix;
 static LIST_HEAD(mousedev_mix_list);
 
-static void mixdev_open_devices(void);
-static void mixdev_close_devices(void);
-
 #define fx(i)  (mousedev->old_x[(mousedev->pkt_count - (i)) & 03])
 #define fy(i)  (mousedev->old_y[(mousedev->pkt_count - (i)) & 03])
 
@@ -428,9 +427,7 @@ static int mousedev_open_device(struct mousedev *mousedev)
 	if (retval)
 		return retval;
 
-	if (mousedev->is_mixdev)
-		mixdev_open_devices();
-	else if (!mousedev->exist)
+	if (!mousedev->exist)
 		retval = -ENODEV;
 	else if (!mousedev->open++) {
 		retval = input_open_device(&mousedev->handle);
@@ -446,9 +443,7 @@ static void mousedev_close_device(struct mousedev *mousedev)
 {
 	mutex_lock(&mousedev->mutex);
 
-	if (mousedev->is_mixdev)
-		mixdev_close_devices();
-	else if (mousedev->exist && !--mousedev->open)
+	if (mousedev->exist && !--mousedev->open)
 		input_close_device(&mousedev->handle);
 
 	mutex_unlock(&mousedev->mutex);
@@ -459,21 +454,29 @@ static void mousedev_close_device(struct mousedev *mousedev)
  * stream. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_open_devices(void)
+static int mixdev_open_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	int error;
 
-	if (mousedev_mix->open++)
-		return;
+	error = mutex_lock_interruptible(&mixdev->mutex);
+	if (error)
+		return error;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (!mousedev->opened_by_mixdev) {
-			if (mousedev_open_device(mousedev))
-				continue;
+	if (!mixdev->open++) {
+		struct mousedev *mousedev;
 
-			mousedev->opened_by_mixdev = true;
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (!mousedev->opened_by_mixdev) {
+				if (mousedev_open_device(mousedev))
+					continue;
+
+				mousedev->opened_by_mixdev = true;
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
+	return 0;
 }
 
 /*
@@ -481,19 +484,22 @@ static void mixdev_open_devices(void)
  * device. Note that this function is called with mousedev_mix->mutex
  * held.
  */
-static void mixdev_close_devices(void)
+static void mixdev_close_devices(struct mousedev *mixdev)
 {
-	struct mousedev *mousedev;
+	mutex_lock(&mixdev->mutex);
 
-	if (--mousedev_mix->open)
-		return;
+	if (!--mixdev->open) {
+		struct mousedev *mousedev;
 
-	list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
-		if (mousedev->opened_by_mixdev) {
-			mousedev->opened_by_mixdev = false;
-			mousedev_close_device(mousedev);
+		list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+			if (mousedev->opened_by_mixdev) {
+				mousedev->opened_by_mixdev = false;
+				mousedev_close_device(mousedev);
+			}
 		}
 	}
+
+	mutex_unlock(&mixdev->mutex);
 }
 
 
@@ -522,7 +528,7 @@ static int mousedev_release(struct inode *inode, struct file *file)
 	mousedev_detach_client(mousedev, client);
 	kfree(client);
 
-	mousedev_close_device(mousedev);
+	mousedev->close_device(mousedev);
 
 	return 0;
 }
@@ -550,7 +556,7 @@ static int mousedev_open(struct inode *inode, struct file *file)
 	client->mousedev = mousedev;
 	mousedev_attach_client(mousedev, client);
 
-	error = mousedev_open_device(mousedev);
+	error = mousedev->open_device(mousedev);
 	if (error)
 		goto err_free_client;
 
@@ -861,16 +867,21 @@ static struct mousedev *mousedev_create(struct input_dev *dev,
 
 	if (mixdev) {
 		dev_set_name(&mousedev->dev, "mice");
+
+		mousedev->open_device = mixdev_open_devices;
+		mousedev->close_device = mixdev_close_devices;
 	} else {
 		int dev_no = minor;
 		/* Normalize device number if it falls into legacy range */
 		if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS)
 			dev_no -= MOUSEDEV_MINOR_BASE;
 		dev_set_name(&mousedev->dev, "mouse%d", dev_no);
+
+		mousedev->open_device = mousedev_open_device;
+		mousedev->close_device = mousedev_close_device;
 	}
 
 	mousedev->exist = true;
-	mousedev->is_mixdev = mixdev;
 	mousedev->handle.dev = input_get_device(dev);
 	mousedev->handle.name = dev_name(&mousedev->dev);
 	mousedev->handle.handler = handler;
@@ -919,7 +930,7 @@ static void mousedev_destroy(struct mousedev *mousedev)
 	device_del(&mousedev->dev);
 	mousedev_cleanup(mousedev);
 	input_free_minor(MINOR(mousedev->dev.devt));
-	if (!mousedev->is_mixdev)
+	if (mousedev != mousedev_mix)
 		input_unregister_handle(&mousedev->handle);
 	put_device(&mousedev->dev);
 }

drivers/net/ethernet/broadcom/tg3.c

@@ -17649,8 +17649,6 @@ static int tg3_init_one(struct pci_dev *pdev,
 
 	tg3_init_bufmgr_config(tp);
 
-	features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
 	/* 5700 B0 chips do not support checksumming correctly due
 	 * to hardware bugs.
 	 */
@@ -17682,7 +17680,8 @@ static int tg3_init_one(struct pci_dev *pdev,
 			features |= NETIF_F_TSO_ECN;
 	}
 
-	dev->features |= features;
+	dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features |= features;
 
 	/*

drivers/net/ethernet/marvell/mvneta.c

@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
+#include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
@@ -88,8 +89,9 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
-#define MVNETA_SGMII_SERDES_CFG			 0x24A0
+#define MVNETA_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
+#define      MVNETA_RGMII_SERDES_PROTO		 0x0667
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -161,7 +163,7 @@
 #define      MVNETA_GMAC_MAX_RX_SIZE_MASK        0x7ffc
 #define      MVNETA_GMAC0_PORT_ENABLE            BIT(0)
 #define MVNETA_GMAC_CTRL_2                       0x2c08
-#define      MVNETA_GMAC2_PSC_ENABLE             BIT(3)
+#define      MVNETA_GMAC2_PCS_ENABLE             BIT(3)
 #define      MVNETA_GMAC2_PORT_RGMII             BIT(4)
 #define      MVNETA_GMAC2_PORT_RESET             BIT(6)
 #define MVNETA_GMAC_STATUS                       0x2c10
@@ -710,35 +712,6 @@ static void mvneta_rxq_bm_disable(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
 }
 
-
-
-/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
-static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
-{
-	u32  val;
-
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
-	if (enable)
-		val |= MVNETA_GMAC2_PORT_RGMII;
-	else
-		val &= ~MVNETA_GMAC2_PORT_RGMII;
-
-	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-}
-
-/* Config SGMII port */
-static void mvneta_port_sgmii_config(struct mvneta_port *pp)
-{
-	u32 val;
-
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-	val |= MVNETA_GMAC2_PSC_ENABLE;
-	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
-
-	mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-}
-
 /* Start the Ethernet port RX and TX activity */
 static void mvneta_port_up(struct mvneta_port *pp)
 {
@@ -2756,12 +2729,15 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
 	if (phy_mode == PHY_INTERFACE_MODE_SGMII)
-		mvneta_port_sgmii_config(pp);
+		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+	else
+		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
 
-	mvneta_gmac_rgmii_set(pp, 1);
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+	val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
 
 	/* Cancel Port Reset */
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
 	val &= ~MVNETA_GMAC2_PORT_RESET;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
 
@@ -2774,6 +2750,7 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 static int mvneta_probe(struct platform_device *pdev)
 {
 	const struct mbus_dram_target_info *dram_target_info;
+	struct resource *res;
 	struct device_node *dn = pdev->dev.of_node;
 	struct device_node *phy_node;
 	u32 phy_addr;
@@ -2838,9 +2815,15 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	clk_prepare_enable(pp->clk);
 
-	pp->base = of_iomap(dn, 0);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		err = -ENODEV;
+		goto err_clk;
+	}
+
+	pp->base = devm_ioremap_resource(&pdev->dev, res);
 	if (pp->base == NULL) {
-		err = -ENOMEM;
+		err = PTR_ERR(pp->base);
 		goto err_clk;
 	}
 
@@ -2848,7 +2831,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
 	if (!pp->stats) {
 		err = -ENOMEM;
-		goto err_unmap;
+		goto err_clk;
 	}
 
 	for_each_possible_cpu(cpu) {
@@ -2913,8 +2896,6 @@ err_deinit:
 	mvneta_deinit(pp);
 err_free_stats:
 	free_percpu(pp->stats);
-err_unmap:
-	iounmap(pp->base);
 err_clk:
 	clk_disable_unprepare(pp->clk);
 err_free_irq:
@@ -2934,7 +2915,6 @@ static int mvneta_remove(struct platform_device *pdev)
 	mvneta_deinit(pp);
 	clk_disable_unprepare(pp->clk);
 	free_percpu(pp->stats);
-	iounmap(pp->base);
 	irq_dispose_mapping(dev->irq);
 	free_netdev(dev);
 

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -2681,7 +2681,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	int ret = __mlx4_init_one(pdev, 0);
+	const struct pci_device_id *id;
+	int ret;
+
+	id = pci_match_id(mlx4_pci_table, pdev);
+	ret = __mlx4_init_one(pdev, id->driver_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }

drivers/net/ethernet/qlogic/qlge/qlge_main.c

@@ -4765,7 +4765,9 @@ static int qlge_probe(struct pci_dev *pdev,
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = ndev->hw_features;
 	/* vlan gets same features (except vlan filter) */
-	ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER |
+				 NETIF_F_HW_VLAN_CTAG_TX |
+				 NETIF_F_HW_VLAN_CTAG_RX);
 
 	if (test_bit(QL_DMA64, &qdev->flags))
 		ndev->features |= NETIF_F_HIGHDMA;

drivers/net/ifb.c

@@ -180,7 +180,8 @@ static void ifb_setup(struct net_device *dev)
 	dev->tx_queue_len = TX_Q_LIMIT;
 
 	dev->features |= IFB_FEATURES;
-	dev->vlan_features |= IFB_FEATURES;
+	dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX |
+					       NETIF_F_HW_VLAN_STAG_TX);
 
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;

drivers/net/usb/usbnet.c

@@ -752,14 +752,12 @@ EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs);
 // precondition: never called in_interrupt
 static void usbnet_terminate_urbs(struct usbnet *dev)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
 	DECLARE_WAITQUEUE(wait, current);
 	int temp;
 
 	/* ensure there are no more active urbs */
-	add_wait_queue(&unlink_wakeup, &wait);
+	add_wait_queue(&dev->wait, &wait);
 	set_current_state(TASK_UNINTERRUPTIBLE);
-	dev->wait = &unlink_wakeup;
 	temp = unlink_urbs(dev, &dev->txq) +
 		unlink_urbs(dev, &dev->rxq);
 
@@ -773,15 +771,14 @@ static void usbnet_terminate_urbs(struct usbnet *dev)
 				  "waited for %d urb completions\n", temp);
 	}
 	set_current_state(TASK_RUNNING);
-	dev->wait = NULL;
-	remove_wait_queue(&unlink_wakeup, &wait);
+	remove_wait_queue(&dev->wait, &wait);
 }
 
 int usbnet_stop (struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
 	struct driver_info	*info = dev->driver_info;
-	int			retval;
+	int			retval, pm;
 
 	clear_bit(EVENT_DEV_OPEN, &dev->flags);
 	netif_stop_queue (net);
@@ -791,6 +788,8 @@ int usbnet_stop (struct net_device *net)
 		   net->stats.rx_packets, net->stats.tx_packets,
 		   net->stats.rx_errors, net->stats.tx_errors);
 
+	/* to not race resume */
+	pm = usb_autopm_get_interface(dev->intf);
 	/* allow minidriver to stop correctly (wireless devices to turn off
 	 * radio etc) */
 	if (info->stop) {
@@ -817,6 +816,9 @@ int usbnet_stop (struct net_device *net)
 	dev->flags = 0;
 	del_timer_sync (&dev->delay);
 	tasklet_kill (&dev->bh);
+	if (!pm)
+		usb_autopm_put_interface(dev->intf);
+
 	if (info->manage_power &&
 	    !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
 		info->manage_power(dev, 0);
@@ -1437,11 +1439,12 @@ static void usbnet_bh (unsigned long param)
 	/* restart RX again after disabling due to high error rate */
 	clear_bit(EVENT_RX_KILL, &dev->flags);
 
-	// waiting for all pending urbs to complete?
-	if (dev->wait) {
-		if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
-			wake_up (dev->wait);
-		}
+	/* waiting for all pending urbs to complete?
+	 * only then can we forgo submitting anew
+	 */
+	if (waitqueue_active(&dev->wait)) {
+		if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+			wake_up_all(&dev->wait);
 
 	// or are we maybe short a few urbs?
 	} else if (netif_running (dev->net) &&
@@ -1580,6 +1583,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	dev->driver_name = name;
 	dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
 				| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+	init_waitqueue_head(&dev->wait);
 	skb_queue_head_init (&dev->rxq);
 	skb_queue_head_init (&dev->txq);
 	skb_queue_head_init (&dev->done);
@@ -1791,9 +1795,10 @@ int usbnet_resume (struct usb_interface *intf)
 		spin_unlock_irq(&dev->txq.lock);
 
 		if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
-			/* handle remote wakeup ASAP */
-			if (!dev->wait &&
-				netif_device_present(dev->net) &&
+			/* handle remote wakeup ASAP
+			 * we cannot race against stop
+			 */
+			if (netif_device_present(dev->net) &&
 				!timer_pending(&dev->delay) &&
 				!test_bit(EVENT_RX_HALT, &dev->flags))
 					rx_alloc_submit(dev, GFP_NOIO);

drivers/net/veth.c

@@ -286,7 +286,10 @@ static void veth_setup(struct net_device *dev)
 	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
 	dev->vlan_features = dev->features &
-			     ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX);
+			     ~(NETIF_F_HW_VLAN_CTAG_TX |
+			       NETIF_F_HW_VLAN_STAG_TX |
+			       NETIF_F_HW_VLAN_CTAG_RX |
+			       NETIF_F_HW_VLAN_STAG_RX);
 	dev->destructor = veth_dev_free;
 
 	dev->hw_features = VETH_FEATURES;

drivers/net/virtio_net.c

@@ -671,8 +671,7 @@ static bool try_fill_recv(struct receive_queue *rq, gfp_t gfp)
 		if (err)
 			break;
 	} while (rq->vq->num_free);
-	if (unlikely(!virtqueue_kick(rq->vq)))
-		return false;
+	virtqueue_kick(rq->vq);
 	return !oom;
 }
 
@@ -877,7 +876,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	err = xmit_skb(sq, skb);
 
 	/* This should not happen! */
-	if (unlikely(err) || unlikely(!virtqueue_kick(sq->vq))) {
+	if (unlikely(err)) {
 		dev->stats.tx_fifo_errors++;
 		if (net_ratelimit())
 			dev_warn(&dev->dev,
@@ -886,6 +885,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
+	virtqueue_kick(sq->vq);
 
 	/* Don't wait up for transmitted skbs to be freed. */
 	skb_orphan(skb);

drivers/vhost/net.c

@@ -505,9 +505,13 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
+		if (unlikely(r < 0))
+			goto err;
+
+		d = r;
 		if (d == vq->num) {
 			r = 0;
 			goto err;
@@ -532,6 +536,12 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 	*iovcount = seg;
 	if (unlikely(log))
 		*log_num = nlogs;
+
+	/* Detect overrun */
+	if (unlikely(datalen > 0)) {
+		r = UIO_MAXIOV + 1;
+		goto err;
+	}
 	return headcount;
 err:
 	vhost_discard_vq_desc(vq, headcount);
@@ -587,6 +597,14 @@ static void handle_rx(struct vhost_net *net)
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
 			break;
+		/* On overrun, truncate and discard */
+		if (unlikely(headcount > UIO_MAXIOV)) {
+			msg.msg_iovlen = 1;
+			err = sock->ops->recvmsg(NULL, sock, &msg,
+						 1, MSG_DONTWAIT | MSG_TRUNC);
+			pr_debug("Discarded rx packet: len %zd\n", sock_len);
+			continue;
+		}
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
 			if (unlikely(vhost_enable_notify(&net->dev, vq))) {

drivers/xen/balloon.c

@@ -399,12 +399,26 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			state = BP_EAGAIN;
 			break;
 		}
-
-		pfn = page_to_pfn(page);
-		frame_list[i] = pfn_to_mfn(pfn);
-
 		scrub_page(page);
 
+		frame_list[i] = page_to_pfn(page);
+	}
+
+	/*
+	 * Ensure that ballooned highmem pages don't have kmaps.
+	 *
+	 * Do this before changing the p2m as kmap_flush_unused()
+	 * reads PTEs to obtain pages (and hence needs the original
+	 * p2m entry).
+	 */
+	kmap_flush_unused();
+
+	/* Update direct mapping, invalidate P2M, and add to balloon. */
+	for (i = 0; i < nr_pages; i++) {
+		pfn = frame_list[i];
+		frame_list[i] = pfn_to_mfn(pfn);
+		page = pfn_to_page(pfn);
+
 #ifdef CONFIG_XEN_HAVE_PVMMU
 		/*
 		 * Ballooned out frames are effectively replaced with
@@ -429,11 +443,9 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 		}
 #endif
 
-		balloon_append(pfn_to_page(pfn));
+		balloon_append(page);
 	}
 
-	/* Ensure that ballooned highmem pages don't have kmaps. */
-	kmap_flush_unused();
 	flush_tlb_all();
 
 	set_xen_guest_handle(reservation.extent_start, frame_list);

fs/anon_inodes.c

@@ -41,19 +41,8 @@ static const struct dentry_operations anon_inodefs_dentry_operations = {
 static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	struct dentry *root;
-	root = mount_pseudo(fs_type, "anon_inode:", NULL,
+	return mount_pseudo(fs_type, "anon_inode:", NULL,
 			&anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
-	if (!IS_ERR(root)) {
-		struct super_block *s = root->d_sb;
-		anon_inode_inode = alloc_anon_inode(s);
-		if (IS_ERR(anon_inode_inode)) {
-			dput(root);
-			deactivate_locked_super(s);
-			root = ERR_CAST(anon_inode_inode);
-		}
-	}
-	return root;
 }
 
 static struct file_system_type anon_inode_fs_type = {
@@ -175,22 +164,15 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
 
 static int __init anon_inode_init(void)
 {
-	int error;
-
-	error = register_filesystem(&anon_inode_fs_type);
-	if (error)
-		goto err_exit;
 	anon_inode_mnt = kern_mount(&anon_inode_fs_type);
-	if (IS_ERR(anon_inode_mnt)) {
-		error = PTR_ERR(anon_inode_mnt);
-		goto err_unregister_filesystem;
-	}
-	return 0;
+	if (IS_ERR(anon_inode_mnt))
+		panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt));
 
-err_unregister_filesystem:
-	unregister_filesystem(&anon_inode_fs_type);
-err_exit:
-	panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
+	anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
+	if (IS_ERR(anon_inode_inode))
+		panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode));
+
+	return 0;
 }
 
 fs_initcall(anon_inode_init);

fs/dcache.c

@@ -2833,9 +2833,9 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
-	if (*buflen < dlen + 1)
-		return -ENAMETOOLONG;
 	*buflen -= dlen + 1;
+	if (*buflen < 0)
+		return -ENAMETOOLONG;
 	p = *buffer -= dlen + 1;
 	*p++ = '/';
 	while (dlen--) {

fs/ext4/inode.c

@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 #include <linux/aio.h>
+#include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -3921,18 +3922,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 void ext4_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
+	unsigned int new_fl = 0;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 	if (flags & EXT4_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & EXT4_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & EXT4_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */

fs/file.c

@@ -713,27 +713,16 @@ unsigned long __fdget_raw(unsigned int fd)
 
 unsigned long __fdget_pos(unsigned int fd)
 {
-	struct files_struct *files = current->files;
-	struct file *file;
-	unsigned long v;
+	unsigned long v = __fdget(fd);
+	struct file *file = (struct file *)(v & ~3);
 
-	if (atomic_read(&files->count) == 1) {
-		file = __fcheck_files(files, fd);
-		v = 0;
-	} else {
-		file = __fget(fd, 0);
-		v = FDPUT_FPUT;
-	}
-	if (!file)
-		return 0;
-
-	if (file->f_mode & FMODE_ATOMIC_POS) {
+	if (file && (file->f_mode & FMODE_ATOMIC_POS)) {
 		if (file_count(file) > 1) {
 			v |= FDPUT_POS_UNLOCK;
 			mutex_lock(&file->f_pos_lock);
 		}
 	}
-	return v | (unsigned long)file;
+	return v;
 }
 
 /*

fs/mount.h

@@ -19,13 +19,13 @@ struct mnt_pcp {
 };
 
 struct mountpoint {
-	struct list_head m_hash;
+	struct hlist_node m_hash;
 	struct dentry *m_dentry;
 	int m_count;
 };
 
 struct mount {
-	struct list_head mnt_hash;
+	struct hlist_node mnt_hash;
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;

fs/namei.c

@@ -1109,7 +1109,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			return false;
 
 		if (!d_mountpoint(path->dentry))
-			break;
+			return true;
 
 		mounted = __lookup_mnt(path->mnt, path->dentry);
 		if (!mounted)
@@ -1125,20 +1125,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		 */
 		*inode = path->dentry->d_inode;
 	}
-	return true;
-}
-
-static void follow_mount_rcu(struct nameidata *nd)
-{
-	while (d_mountpoint(nd->path.dentry)) {
-		struct mount *mounted;
-		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
-		if (!mounted)
-			break;
-		nd->path.mnt = &mounted->mnt;
-		nd->path.dentry = mounted->mnt.mnt_root;
-		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-	}
+	return read_seqretry(&mount_lock, nd->m_seq);
 }
 
 static int follow_dotdot_rcu(struct nameidata *nd)
@@ -1166,7 +1153,17 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			break;
 		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 	}
-	follow_mount_rcu(nd);
+	while (d_mountpoint(nd->path.dentry)) {
+		struct mount *mounted;
+		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
+		if (!mounted)
+			break;
+		nd->path.mnt = &mounted->mnt;
+		nd->path.dentry = mounted->mnt.mnt_root;
+		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+		if (!read_seqretry(&mount_lock, nd->m_seq))
+			goto failed;
+	}
 	nd->inode = nd->path.dentry->d_inode;
 	return 0;
 

fs/namespace.c

@@ -23,11 +23,34 @@
 #include <linux/uaccess.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
+#include <linux/bootmem.h>
 #include "pnode.h"
 #include "internal.h"
 
-#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
-#define HASH_SIZE (1UL << HASH_SHIFT)
+static unsigned int m_hash_mask __read_mostly;
+static unsigned int m_hash_shift __read_mostly;
+static unsigned int mp_hash_mask __read_mostly;
+static unsigned int mp_hash_shift __read_mostly;
+
+static __initdata unsigned long mhash_entries;
+static int __init set_mhash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mhash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mhash_entries=", set_mhash_entries);
+
+static __initdata unsigned long mphash_entries;
+static int __init set_mphash_entries(char *str)
+{
+	if (!str)
+		return 0;
+	mphash_entries = simple_strtoul(str, &str, 0);
+	return 1;
+}
+__setup("mphash_entries=", set_mphash_entries);
 
 static int event;
 static DEFINE_IDA(mnt_id_ida);
@@ -36,8 +59,8 @@ static DEFINE_SPINLOCK(mnt_id_lock);
 static int mnt_id_start = 0;
 static int mnt_group_start = 1;
 
-static struct list_head *mount_hashtable __read_mostly;
-static struct list_head *mountpoint_hashtable __read_mostly;
+static struct hlist_head *mount_hashtable __read_mostly;
+static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
 static DECLARE_RWSEM(namespace_sem);
 
@@ -55,12 +78,19 @@ EXPORT_SYMBOL_GPL(fs_kobj);
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
-static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
+static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
 {
 	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
 	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
-	tmp = tmp + (tmp >> HASH_SHIFT);
-	return tmp & (HASH_SIZE - 1);
+	tmp = tmp + (tmp >> m_hash_shift);
+	return &mount_hashtable[tmp & m_hash_mask];
+}
+
+static inline struct hlist_head *mp_hash(struct dentry *dentry)
+{
+	unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
+	tmp = tmp + (tmp >> mp_hash_shift);
+	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
 /*
@@ -187,7 +217,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		mnt->mnt_writers = 0;
 #endif
 
-		INIT_LIST_HEAD(&mnt->mnt_hash);
+		INIT_HLIST_NODE(&mnt->mnt_hash);
 		INIT_LIST_HEAD(&mnt->mnt_child);
 		INIT_LIST_HEAD(&mnt->mnt_mounts);
 		INIT_LIST_HEAD(&mnt->mnt_list);
@@ -575,10 +605,10 @@ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
  */
 struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
+	struct hlist_head *head = m_hash(mnt, dentry);
 	struct mount *p;
 
-	list_for_each_entry_rcu(p, head, mnt_hash)
+	hlist_for_each_entry_rcu(p, head, mnt_hash)
 		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
 			return p;
 	return NULL;
@@ -590,13 +620,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
  */
 struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
 {
-	struct list_head *head = mount_hashtable + hash(mnt, dentry);
-	struct mount *p;
-
-	list_for_each_entry_reverse(p, head, mnt_hash)
-		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
-			return p;
-	return NULL;
+	struct mount *p, *res;
+	res = p = __lookup_mnt(mnt, dentry);
+	if (!p)
+		goto out;
+	hlist_for_each_entry_continue(p, mnt_hash) {
+		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
+			break;
+		res = p;
+	}
+out:
+	return res;
 }
 
 /*
@@ -633,11 +667,11 @@ struct vfsmount *lookup_mnt(struct path *path)
 
 static struct mountpoint *new_mountpoint(struct dentry *dentry)
 {
-	struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
+	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
 	int ret;
 
-	list_for_each_entry(mp, chain, m_hash) {
+	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
 			/* might be worth a WARN_ON() */
 			if (d_unlinked(dentry))
@@ -659,7 +693,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
-	list_add(&mp->m_hash, chain);
+	hlist_add_head(&mp->m_hash, chain);
 	return mp;
 }
 
@@ -670,7 +704,7 @@ static void put_mountpoint(struct mountpoint *mp)
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
-		list_del(&mp->m_hash);
+		hlist_del(&mp->m_hash);
 		kfree(mp);
 	}
 }
@@ -712,7 +746,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
-	list_del_init(&mnt->mnt_hash);
+	hlist_del_init_rcu(&mnt->mnt_hash);
 	put_mountpoint(mnt->mnt_mp);
 	mnt->mnt_mp = NULL;
 }
@@ -739,15 +773,14 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-			hash(&parent->mnt, mp->m_dentry));
+	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt)
+static void commit_tree(struct mount *mnt, struct mount *shadows)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -762,8 +795,11 @@ static void commit_tree(struct mount *mnt)
 
 	list_splice(&head, n->list.prev);
 
-	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-				hash(&parent->mnt, mnt->mnt_mountpoint));
+	if (shadows)
+		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+	else
+		hlist_add_head_rcu(&mnt->mnt_hash,
+				m_hash(&parent->mnt, mnt->mnt_mountpoint));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 	touch_mnt_namespace(n);
 }
@@ -1153,26 +1189,28 @@ int may_umount(struct vfsmount *mnt)
 
 EXPORT_SYMBOL(may_umount);
 
-static LIST_HEAD(unmounted);	/* protected by namespace_sem */
+static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 
 static void namespace_unlock(void)
 {
 	struct mount *mnt;
-	LIST_HEAD(head);
+	struct hlist_head head = unmounted;
 
-	if (likely(list_empty(&unmounted))) {
+	if (likely(hlist_empty(&head))) {
 		up_write(&namespace_sem);
 		return;
 	}
 
-	list_splice_init(&unmounted, &head);
+	head.first->pprev = &head.first;
+	INIT_HLIST_HEAD(&unmounted);
+
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
 
-	while (!list_empty(&head)) {
-		mnt = list_first_entry(&head, struct mount, mnt_hash);
-		list_del_init(&mnt->mnt_hash);
+	while (!hlist_empty(&head)) {
+		mnt = hlist_entry(head.first, struct mount, mnt_hash);
+		hlist_del_init(&mnt->mnt_hash);
 		if (mnt->mnt_ex_mountpoint.mnt)
 			path_put(&mnt->mnt_ex_mountpoint);
 		mntput(&mnt->mnt);
@@ -1193,16 +1231,19 @@ static inline void namespace_lock(void)
  */
 void umount_tree(struct mount *mnt, int how)
 {
-	LIST_HEAD(tmp_list);
+	HLIST_HEAD(tmp_list);
 	struct mount *p;
+	struct mount *last = NULL;
 
-	for (p = mnt; p; p = next_mnt(p, mnt))
-		list_move(&p->mnt_hash, &tmp_list);
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		hlist_del_init_rcu(&p->mnt_hash);
+		hlist_add_head(&p->mnt_hash, &tmp_list);
+	}
 
 	if (how)
 		propagate_umount(&tmp_list);
 
-	list_for_each_entry(p, &tmp_list, mnt_hash) {
+	hlist_for_each_entry(p, &tmp_list, mnt_hash) {
 		list_del_init(&p->mnt_expire);
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
@@ -1220,8 +1261,13 @@ void umount_tree(struct mount *mnt, int how)
 			p->mnt_mp = NULL;
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
+		last = p;
+	}
+	if (last) {
+		last->mnt_hash.next = unmounted.first;
+		unmounted.first = tmp_list.first;
+		unmounted.first->pprev = &unmounted.first;
 	}
-	list_splice(&tmp_list, &unmounted);
 }
 
 static void shrink_submounts(struct mount *mnt);
@@ -1605,24 +1651,23 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			struct mountpoint *dest_mp,
 			struct path *parent_path)
 {
-	LIST_HEAD(tree_list);
+	HLIST_HEAD(tree_list);
 	struct mount *child, *p;
+	struct hlist_node *n;
 	int err;
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
 			goto out;
-	}
-	err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
-	if (err)
-		goto out_cleanup_ids;
-
-	lock_mount_hash();
-
-	if (IS_MNT_SHARED(dest_mnt)) {
+		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		if (err)
+			goto out_cleanup_ids;
+		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
+	} else {
+		lock_mount_hash();
 	}
 	if (parent_path) {
 		detach_mnt(source_mnt, parent_path);
@@ -1630,20 +1675,22 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt);
+		commit_tree(source_mnt, NULL);
 	}
 
-	list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
-		list_del_init(&child->mnt_hash);
-		commit_tree(child);
+	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
+		struct mount *q;
+		hlist_del_init(&child->mnt_hash);
+		q = __lookup_mnt_last(&child->mnt_parent->mnt,
+				      child->mnt_mountpoint);
+		commit_tree(child, q);
 	}
 	unlock_mount_hash();
 
 	return 0;
 
  out_cleanup_ids:
-	if (IS_MNT_SHARED(dest_mnt))
-		cleanup_group_ids(source_mnt, NULL);
+	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
 }
@@ -2777,18 +2824,24 @@ void __init mnt_init(void)
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
-	mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
-	mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
+	mount_hashtable = alloc_large_system_hash("Mount-cache",
+				sizeof(struct hlist_head),
+				mhash_entries, 19,
+				0,
+				&m_hash_shift, &m_hash_mask, 0, 0);
+	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
+				sizeof(struct hlist_head),
+				mphash_entries, 19,
+				0,
+				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE);
-
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u < HASH_SIZE; u++)
-		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
+	for (u = 0; u <= m_hash_mask; u++)
+		INIT_HLIST_HEAD(&mount_hashtable[u]);
+	for (u = 0; u <= mp_hash_mask; u++)
+		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
 
 	kernfs_init();
 

fs/nfsd/vfs.c

@@ -449,6 +449,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	fh_lock(fhp);
 	host_err = notify_change(dentry, iap, NULL);
 	fh_unlock(fhp);
+	err = nfserrno(host_err);
 
 out_put_write_access:
 	if (size_change)

fs/ocfs2/stackglue.c

@@ -346,7 +346,9 @@ int ocfs2_cluster_connect(const char *stack_name,
 
 	strlcpy(new_conn->cc_name, group, GROUP_NAME_MAX + 1);
 	new_conn->cc_namelen = grouplen;
-	strlcpy(new_conn->cc_cluster_name, cluster_name, CLUSTER_NAME_MAX + 1);
+	if (cluster_name_len)
+		strlcpy(new_conn->cc_cluster_name, cluster_name,
+			CLUSTER_NAME_MAX + 1);
 	new_conn->cc_cluster_name_len = cluster_name_len;
 	new_conn->cc_recovery_handler = recovery_handler;
 	new_conn->cc_recovery_data = recovery_data;

fs/pnode.c

@@ -220,14 +220,14 @@ static struct mount *get_source(struct mount *dest,
  * @tree_list : list of heads of trees to be attached.
  */
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
-		    struct mount *source_mnt, struct list_head *tree_list)
+		    struct mount *source_mnt, struct hlist_head *tree_list)
 {
 	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	struct mount *m, *child;
 	int ret = 0;
 	struct mount *prev_dest_mnt = dest_mnt;
 	struct mount *prev_src_mnt  = source_mnt;
-	LIST_HEAD(tmp_list);
+	HLIST_HEAD(tmp_list);
 
 	for (m = propagation_next(dest_mnt, dest_mnt); m;
 			m = propagation_next(m, dest_mnt)) {
@@ -246,27 +246,29 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		child = copy_tree(source, source->mnt.mnt_root, type);
 		if (IS_ERR(child)) {
 			ret = PTR_ERR(child);
-			list_splice(tree_list, tmp_list.prev);
+			tmp_list = *tree_list;
+			tmp_list.first->pprev = &tmp_list.first;
+			INIT_HLIST_HEAD(tree_list);
 			goto out;
 		}
 
 		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
 			mnt_set_mountpoint(m, dest_mp, child);
-			list_add_tail(&child->mnt_hash, tree_list);
+			hlist_add_head(&child->mnt_hash, tree_list);
 		} else {
 			/*
 			 * This can happen if the parent mount was bind mounted
 			 * on some subdirectory of a shared/slave mount.
 			 */
-			list_add_tail(&child->mnt_hash, &tmp_list);
+			hlist_add_head(&child->mnt_hash, &tmp_list);
 		}
 		prev_dest_mnt = m;
 		prev_src_mnt  = child;
 	}
 out:
 	lock_mount_hash();
-	while (!list_empty(&tmp_list)) {
-		child = list_first_entry(&tmp_list, struct mount, mnt_hash);
+	while (!hlist_empty(&tmp_list)) {
+		child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
 		umount_tree(child, 0);
 	}
 	unlock_mount_hash();
@@ -338,8 +340,10 @@ static void __propagate_umount(struct mount *mnt)
 		 * umount the child only if the child has no
 		 * other children
 		 */
-		if (child && list_empty(&child->mnt_mounts))
-			list_move_tail(&child->mnt_hash, &mnt->mnt_hash);
+		if (child && list_empty(&child->mnt_mounts)) {
+			hlist_del_init_rcu(&child->mnt_hash);
+			hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash);
+		}
 	}
 }
 
@@ -350,11 +354,11 @@ static void __propagate_umount(struct mount *mnt)
  *
  * vfsmount lock must be held for write
  */
-int propagate_umount(struct list_head *list)
+int propagate_umount(struct hlist_head *list)
 {
 	struct mount *mnt;
 
-	list_for_each_entry(mnt, list, mnt_hash)
+	hlist_for_each_entry(mnt, list, mnt_hash)
 		__propagate_umount(mnt);
 	return 0;
 }

fs/pnode.h

@@ -36,8 +36,8 @@ static inline void set_mnt_shared(struct mount *mnt)
 
 void change_mnt_propagation(struct mount *, int);
 int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
-		struct list_head *);
-int propagate_umount(struct list_head *);
+		struct hlist_head *);
+int propagate_umount(struct hlist_head *);
 int propagate_mount_busy(struct mount *, int);
 void mnt_release_group_id(struct mount *);
 int get_dominating_id(struct mount *mnt, const struct path *root);

fs/read_write.c

@@ -307,7 +307,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		unsigned int, whence)
 {
 	int retval;
-	struct fd f = fdget(fd);
+	struct fd f = fdget_pos(fd);
 	loff_t offset;
 
 	if (!f.file)
@@ -327,7 +327,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 			retval = 0;
 	}
 out_putf:
-	fdput(f);
+	fdput_pos(f);
 	return retval;
 }
 #endif

include/linux/bitops.h

@@ -196,6 +196,21 @@ static inline unsigned long __ffs64(u64 word)
 
 #ifdef __KERNEL__
 
+#ifndef set_mask_bits
+#define set_mask_bits(ptr, _mask, _bits)	\
+({								\
+	const typeof(*ptr) mask = (_mask), bits = (_bits);	\
+	typeof(*ptr) old, new;					\
+								\
+	do {							\
+		old = ACCESS_ONCE(*ptr);			\
+		new = (old & ~mask) | bits;			\
+	} while (cmpxchg(ptr, old, new) != old);		\
+								\
+	new;							\
+})
+#endif
+
 #ifndef find_last_bit
 /**
  * find_last_bit - find the last set bit in a memory region

include/linux/netdev_features.h

@@ -163,4 +163,11 @@ enum {
 /* changeable features with no special hardware requirements */
 #define NETIF_F_SOFT_FEATURES	(NETIF_F_GSO | NETIF_F_GRO)
 
+#define NETIF_F_VLAN_FEATURES	(NETIF_F_HW_VLAN_CTAG_FILTER | \
+				 NETIF_F_HW_VLAN_CTAG_RX | \
+				 NETIF_F_HW_VLAN_CTAG_TX | \
+				 NETIF_F_HW_VLAN_STAG_FILTER | \
+				 NETIF_F_HW_VLAN_STAG_RX | \
+				 NETIF_F_HW_VLAN_STAG_TX)
+
 #endif	/* _LINUX_NETDEV_FEATURES_H */

include/linux/netdevice.h

@@ -3014,7 +3014,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
 {
 	return __skb_gso_segment(skb, features, true);
 }
-__be16 skb_network_protocol(struct sk_buff *skb);
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth);
 
 static inline bool can_checksum_protocol(netdev_features_t features,
 					 __be16 protocol)

include/linux/skbuff.h

@@ -2451,8 +2451,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 		    unsigned int flags);
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
-void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from,
-		  int len, int hlen);
+int skb_zerocopy(struct sk_buff *to, struct sk_buff *from,
+		 int len, int hlen);
 void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
 int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
 void skb_scrub_packet(struct sk_buff *skb, bool xnet);

include/linux/usb/usbnet.h

@@ -30,7 +30,7 @@ struct usbnet {
 	struct driver_info	*driver_info;
 	const char		*driver_name;
 	void			*driver_priv;
-	wait_queue_head_t	*wait;
+	wait_queue_head_t	wait;
 	struct mutex		phy_mutex;
 	unsigned char		suspend_count;
 	unsigned char		pkt_cnt, pkt_err;

include/net/if_inet6.h

@@ -31,8 +31,10 @@
 #define IF_PREFIX_AUTOCONF	0x02
 
 enum {
+	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
 	INET6_IFADDR_STATE_POSTDAD,
+	INET6_IFADDR_STATE_ERRDAD,
 	INET6_IFADDR_STATE_UP,
 	INET6_IFADDR_STATE_DEAD,
 };
@@ -58,7 +60,7 @@ struct inet6_ifaddr {
 	unsigned long		cstamp;	/* created timestamp */
 	unsigned long		tstamp; /* updated timestamp */
 
-	struct timer_list	dad_timer;
+	struct delayed_work	dad_work;
 
 	struct inet6_dev	*idev;
 	struct rt6_info		*rt;

kernel/audit.c

@@ -608,9 +608,19 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 	int err = 0;
 
 	/* Only support the initial namespaces for now. */
+	/*
+	 * We return ECONNREFUSED because it tricks userspace into thinking
+	 * that audit was not configured into the kernel.  Lots of users
+	 * configure their PAM stack (because that's what the distro does)
+	 * to reject login if unable to send messages to audit.  If we return
+	 * ECONNREFUSED the PAM stack thinks the kernel does not have audit
+	 * configured in and will let login proceed.  If we return EPERM
+	 * userspace will reject all logins.  This should be removed when we
+	 * support non init namespaces!!
+	 */
 	if ((current_user_ns() != &init_user_ns) ||
 	    (task_active_pid_ns(current) != &init_pid_ns))
-		return -EPERM;
+		return -ECONNREFUSED;
 
 	switch (msg_type) {
 	case AUDIT_LIST:

kernel/time/timekeeping.c

@@ -1435,7 +1435,8 @@ void update_wall_time(void)
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	if (clock_set)
-		clock_was_set();
+		/* Have to call _delayed version, since in irq context*/
+		clock_was_set_delayed();
 }
 
 /**

kernel/trace/trace.c

@@ -1600,15 +1600,31 @@ void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
+static struct ring_buffer *temp_buffer;
+
 struct ring_buffer_event *
 trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 			  struct ftrace_event_file *ftrace_file,
 			  int type, unsigned long len,
 			  unsigned long flags, int pc)
 {
+	struct ring_buffer_event *entry;
+
 	*current_rb = ftrace_file->tr->trace_buffer.buffer;
-	return trace_buffer_lock_reserve(*current_rb,
+	entry = trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
+	/*
+	 * If tracing is off, but we have triggers enabled
+	 * we still need to look at the event data. Use the temp_buffer
+	 * to store the trace event for the tigger to use. It's recusive
+	 * safe and will not be recorded anywhere.
+	 */
+	if (!entry && ftrace_file->flags & FTRACE_EVENT_FL_TRIGGER_COND) {
+		*current_rb = temp_buffer;
+		entry = trace_buffer_lock_reserve(*current_rb,
+						  type, len, flags, pc);
+	}
+	return entry;
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
@@ -6494,11 +6510,16 @@ __init static int tracer_alloc_buffers(void)
 
 	raw_spin_lock_init(&global_trace.start_lock);
 
+	/* Used for event triggers */
+	temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE);
+	if (!temp_buffer)
+		goto out_free_cpumask;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_cpumask;
+		goto out_free_temp_buffer;
 	}
 
 	if (global_trace.buffer_disabled)
@@ -6540,6 +6561,8 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_temp_buffer:
+	ring_buffer_free(temp_buffer);
 out_free_cpumask:
 	free_percpu(global_trace.trace_buffer.data);
 #ifdef CONFIG_TRACER_MAX_TRACE

lib/random32.c

@@ -244,8 +244,19 @@ static void __prandom_reseed(bool late)
 	static bool latch = false;
 	static DEFINE_SPINLOCK(lock);
 
+	/* Asking for random bytes might result in bytes getting
+	 * moved into the nonblocking pool and thus marking it
+	 * as initialized. In this case we would double back into
+	 * this function and attempt to do a late reseed.
+	 * Ignore the pointless attempt to reseed again if we're
+	 * already waiting for bytes when the nonblocking pool
+	 * got initialized.
+	 */
+
 	/* only allow initial seeding (late == false) once */
-	spin_lock_irqsave(&lock, flags);
+	if (!spin_trylock_irqsave(&lock, flags))
+		return;
+
 	if (latch && !late)
 		goto out;
 	latch = true;

net/8021q/vlan.c

@@ -307,9 +307,11 @@ static void vlan_sync_address(struct net_device *dev,
 static void vlan_transfer_features(struct net_device *dev,
 				   struct net_device *vlandev)
 {
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
 	vlandev->gso_max_size = dev->gso_max_size;
 
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+	if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
 		vlandev->hard_header_len = dev->hard_header_len;
 	else
 		vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;

net/8021q/vlan_dev.c

@@ -578,6 +578,9 @@ static int vlan_dev_init(struct net_device *dev)
 
 	dev->features |= real_dev->vlan_features | NETIF_F_LLTX;
 	dev->gso_max_size = real_dev->gso_max_size;
+	if (dev->features & NETIF_F_VLAN_FEATURES)
+		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
+
 
 	/* ipv6 shared card related stuff */
 	dev->dev_id = real_dev->dev_id;
@@ -592,7 +595,8 @@ static int vlan_dev_init(struct net_device *dev)
 #endif
 
 	dev->needed_headroom = real_dev->needed_headroom;
-	if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
+	if (vlan_hw_offload_capable(real_dev->features,
+				    vlan_dev_priv(dev)->vlan_proto)) {
 		dev->header_ops      = &vlan_passthru_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
 	} else {

net/bridge/br_device.c

@@ -49,14 +49,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
-	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
-		goto out;
-
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);
 	skb_pull(skb, ETH_HLEN);
 
+	if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid))
+		goto out;
+
 	if (is_broadcast_ether_addr(dest))
 		br_flood_deliver(br, skb, false);
 	else if (is_multicast_ether_addr(dest)) {

net/bridge/br_input.c

@@ -29,6 +29,7 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
 	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
+	struct net_port_vlans *pv;
 
 	u64_stats_update_begin(&brstats->syncp);
 	brstats->rx_packets++;
@@ -39,18 +40,18 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	 * packet is allowed except in promisc modue when someone
 	 * may be running packet capture.
 	 */
+	pv = br_get_vlan_info(br);
 	if (!(brdev->flags & IFF_PROMISC) &&
-	    !br_allowed_egress(br, br_get_vlan_info(br), skb)) {
+	    !br_allowed_egress(br, pv, skb)) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
 
-	skb = br_handle_vlan(br, br_get_vlan_info(br), skb);
-	if (!skb)
-		return NET_RX_DROP;
-
 	indev = skb->dev;
 	skb->dev = brdev;
+	skb = br_handle_vlan(br, pv, skb);
+	if (!skb)
+		return NET_RX_DROP;
 
 	return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL,
 		       netif_receive_skb);

net/bridge/br_vlan.c

@@ -119,22 +119,6 @@ static void __vlan_flush(struct net_port_vlans *v)
 	kfree_rcu(v, rcu);
 }
 
-/* Strip the tag from the packet.  Will return skb with tci set 0.  */
-static struct sk_buff *br_vlan_untag(struct sk_buff *skb)
-{
-	if (skb->protocol != htons(ETH_P_8021Q)) {
-		skb->vlan_tci = 0;
-		return skb;
-	}
-
-	skb->vlan_tci = 0;
-	skb = vlan_untag(skb);
-	if (skb)
-		skb->vlan_tci = 0;
-
-	return skb;
-}
-
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *pv,
 			       struct sk_buff *skb)
@@ -144,13 +128,27 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 	if (!br->vlan_enabled)
 		goto out;
 
+	/* Vlan filter table must be configured at this point.  The
+	 * only exception is the bridge is set in promisc mode and the
+	 * packet is destined for the bridge device.  In this case
+	 * pass the packet as is.
+	 */
+	if (!pv) {
+		if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) {
+			goto out;
+		} else {
+			kfree_skb(skb);
+			return NULL;
+		}
+	}
+
 	/* At this point, we know that the frame was filtered and contains
 	 * a valid vlan id.  If the vlan id is set in the untagged bitmap,
 	 * send untagged; otherwise, send tagged.
 	 */
 	br_vlan_get_tag(skb, &vid);
 	if (test_bit(vid, pv->untagged_bitmap))
-		skb = br_vlan_untag(skb);
+		skb->vlan_tci = 0;
 
 out:
 	return skb;
@@ -174,6 +172,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	if (!v)
 		return false;
 
+	/* If vlan tx offload is disabled on bridge device and frame was
+	 * sent from vlan device on the bridge device, it does not have
+	 * HW accelerated vlan tag.
+	 */
+	if (unlikely(!vlan_tx_tag_present(skb) &&
+		     (skb->protocol == htons(ETH_P_8021Q) ||
+		      skb->protocol == htons(ETH_P_8021AD)))) {
+		skb = vlan_untag(skb);
+		if (unlikely(!skb))
+			return false;
+	}
+
 	err = br_vlan_get_tag(skb, vid);
 	if (!*vid) {
 		u16 pvid = br_get_pvid(v);

net/core/dev.c

@@ -2286,7 +2286,7 @@ out:
 }
 EXPORT_SYMBOL(skb_checksum_help);
 
-__be16 skb_network_protocol(struct sk_buff *skb)
+__be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
 	__be16 type = skb->protocol;
 	int vlan_depth = ETH_HLEN;
@@ -2313,6 +2313,8 @@ __be16 skb_network_protocol(struct sk_buff *skb)
 		vlan_depth += VLAN_HLEN;
 	}
 
+	*depth = vlan_depth;
+
 	return type;
 }
 
@@ -2326,12 +2328,13 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_offload *ptype;
-	__be16 type = skb_network_protocol(skb);
+	int vlan_depth = skb->mac_len;
+	__be16 type = skb_network_protocol(skb, &vlan_depth);
 
 	if (unlikely(!type))
 		return ERR_PTR(-EINVAL);
 
-	__skb_pull(skb, skb->mac_len);
+	__skb_pull(skb, vlan_depth);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, &offload_base, list) {
@@ -2498,8 +2501,10 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 					    const struct net_device *dev,
 					    netdev_features_t features)
 {
+	int tmp;
+
 	if (skb->ip_summed != CHECKSUM_NONE &&
-	    !can_checksum_protocol(features, skb_network_protocol(skb))) {
+	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
 		features &= ~NETIF_F_ALL_CSUM;
 	} else if (illegal_highdma(dev, skb)) {
 		features &= ~NETIF_F_SG;

net/core/skbuff.c

@@ -2127,25 +2127,31 @@ EXPORT_SYMBOL_GPL(skb_zerocopy_headlen);
  *
  *	The `hlen` as calculated by skb_zerocopy_headlen() specifies the
  *	headroom in the `to` buffer.
+ *
+ *	Return value:
+ *	0: everything is OK
+ *	-ENOMEM: couldn't orphan frags of @from due to lack of memory
+ *	-EFAULT: skb_copy_bits() found some problem with skb geometry
  */
-void
-skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+int
+skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
 {
 	int i, j = 0;
 	int plen = 0; /* length of skb->head fragment */
+	int ret;
 	struct page *page;
 	unsigned int offset;
 
 	BUG_ON(!from->head_frag && !hlen);
 
 	/* dont bother with small payloads */
-	if (len <= skb_tailroom(to)) {
-		skb_copy_bits(from, 0, skb_put(to, len), len);
-		return;
-	}
+	if (len <= skb_tailroom(to))
+		return skb_copy_bits(from, 0, skb_put(to, len), len);
 
 	if (hlen) {
-		skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+		if (unlikely(ret))
+			return ret;
 		len -= hlen;
 	} else {
 		plen = min_t(int, skb_headlen(from), len);
@@ -2163,6 +2169,11 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
 	to->len += len + plen;
 	to->data_len += len + plen;
 
+	if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+		skb_tx_error(from);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
 		if (!len)
 			break;
@@ -2173,6 +2184,8 @@ skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
 		j++;
 	}
 	skb_shinfo(to)->nr_frags = j;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(skb_zerocopy);
 
@@ -2866,8 +2879,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	int err = -ENOMEM;
 	int i = 0;
 	int pos;
+	int dummy;
 
-	proto = skb_network_protocol(head_skb);
+	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 

net/ipv4/gre_demux.c

@@ -182,6 +182,14 @@ static int gre_cisco_rcv(struct sk_buff *skb)
 	int i;
 	bool csum_err = false;
 
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
+		/* Looped back packet, drop it! */
+		if (rt_is_output_route(skb_rtable(skb)))
+			goto drop;
+	}
+#endif
+
 	if (parse_gre_header(skb, &tpi, &csum_err) < 0)
 		goto drop;
 

net/ipv4/ip_tunnel.c

@@ -416,9 +416,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
-		/* Looped back packet, drop it! */
-		if (rt_is_output_route(skb_rtable(skb)))
-			goto drop;
 		tunnel->dev->stats.multicast++;
 		skb->pkt_type = PACKET_BROADCAST;
 	}

net/ipv4/ip_tunnel_core.c

@@ -108,6 +108,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	nf_reset(skb);
 	secpath_reset(skb);
 	skb_clear_hash_if_not_l4(skb);
+	skb_dst_drop(skb);
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
 	skb->pkt_type = PACKET_HOST;

net/ipv4/tcp_ipv4.c

@@ -2628,7 +2628,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 {
 	__be32 dest, src;
 	__u16 destp, srcp;
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest  = tw->tw_daddr;
 	src   = tw->tw_rcv_saddr;

net/ipv6/addrconf.c

@@ -133,10 +133,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev);
 static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE];
 static DEFINE_SPINLOCK(addrconf_hash_lock);
 
-static void addrconf_verify(unsigned long);
+static void addrconf_verify(void);
+static void addrconf_verify_rtnl(void);
+static void addrconf_verify_work(struct work_struct *);
 
-static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0);
-static DEFINE_SPINLOCK(addrconf_verify_lock);
+static struct workqueue_struct *addrconf_wq;
+static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);
 
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp);
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp);
@@ -151,7 +153,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 						  u32 flags, u32 noflags);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
-static void addrconf_dad_timer(unsigned long data);
+static void addrconf_dad_work(struct work_struct *w);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
 static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
@@ -247,9 +249,9 @@ static void addrconf_del_rs_timer(struct inet6_dev *idev)
 		__in6_dev_put(idev);
 }
 
-static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
 {
-	if (del_timer(&ifp->dad_timer))
+	if (cancel_delayed_work(&ifp->dad_work))
 		__in6_ifa_put(ifp);
 }
 
@@ -261,12 +263,12 @@ static void addrconf_mod_rs_timer(struct inet6_dev *idev,
 	mod_timer(&idev->rs_timer, jiffies + when);
 }
 
-static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
-				   unsigned long when)
+static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
+				   unsigned long delay)
 {
-	if (!timer_pending(&ifp->dad_timer))
+	if (!delayed_work_pending(&ifp->dad_work))
 		in6_ifa_hold(ifp);
-	mod_timer(&ifp->dad_timer, jiffies + when);
+	mod_delayed_work(addrconf_wq, &ifp->dad_work, delay);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -751,8 +753,9 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 
 	in6_dev_put(ifp->idev);
 
-	if (del_timer(&ifp->dad_timer))
-		pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
+	if (cancel_delayed_work(&ifp->dad_work))
+		pr_notice("delayed DAD work was pending while freeing ifa=%p\n",
+			  ifp);
 
 	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
 		pr_warn("Freeing alive inet6 address %p\n", ifp);
@@ -849,8 +852,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 
 	spin_lock_init(&ifa->lock);
 	spin_lock_init(&ifa->state_lock);
-	setup_timer(&ifa->dad_timer, addrconf_dad_timer,
-		    (unsigned long)ifa);
+	INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
 	INIT_HLIST_NODE(&ifa->addr_lst);
 	ifa->scope = scope;
 	ifa->prefix_len = pfxlen;
@@ -990,6 +992,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP;
 	unsigned long expires;
 
+	ASSERT_RTNL();
+
 	spin_lock_bh(&ifp->state_lock);
 	state = ifp->state;
 	ifp->state = INET6_IFADDR_STATE_DEAD;
@@ -1021,7 +1025,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	write_unlock_bh(&ifp->idev->lock);
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	ipv6_ifa_notify(RTM_DELADDR, ifp);
 
@@ -1604,7 +1608,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 {
 	if (ifp->flags&IFA_F_PERMANENT) {
 		spin_lock_bh(&ifp->lock);
-		addrconf_del_dad_timer(ifp);
+		addrconf_del_dad_work(ifp);
 		ifp->flags |= IFA_F_TENTATIVE;
 		if (dad_failed)
 			ifp->flags |= IFA_F_DADFAILED;
@@ -1625,20 +1629,21 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
-	} else
+	} else {
 		ipv6_del_addr(ifp);
+	}
 }
 
 static int addrconf_dad_end(struct inet6_ifaddr *ifp)
 {
 	int err = -ENOENT;
 
-	spin_lock(&ifp->state_lock);
+	spin_lock_bh(&ifp->state_lock);
 	if (ifp->state == INET6_IFADDR_STATE_DAD) {
 		ifp->state = INET6_IFADDR_STATE_POSTDAD;
 		err = 0;
 	}
-	spin_unlock(&ifp->state_lock);
+	spin_unlock_bh(&ifp->state_lock);
 
 	return err;
 }
@@ -1671,7 +1676,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		}
 	}
 
-	addrconf_dad_stop(ifp, 1);
+	spin_lock_bh(&ifp->state_lock);
+	/* transition from _POSTDAD to _ERRDAD */
+	ifp->state = INET6_IFADDR_STATE_ERRDAD;
+	spin_unlock_bh(&ifp->state_lock);
+
+	addrconf_mod_dad_work(ifp, 0);
 }
 
 /* Join to solicited addr multicast group. */
@@ -1680,6 +1690,8 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1691,6 +1703,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
+	ASSERT_RTNL();
+
 	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1701,6 +1715,9 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
+
+	ASSERT_RTNL();
+
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1712,6 +1729,9 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
+
+	ASSERT_RTNL();
+
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -2271,11 +2291,13 @@ ok:
 				return;
 			}
 
-			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			update_lft = 0;
 			create = 1;
+			spin_lock_bh(&ifp->lock);
+			ifp->flags |= IFA_F_MANAGETEMPADDR;
 			ifp->cstamp = jiffies;
 			ifp->tokenized = tokenized;
+			spin_unlock_bh(&ifp->lock);
 			addrconf_dad_start(ifp);
 		}
 
@@ -2326,7 +2348,7 @@ ok:
 					 create, now);
 
 			in6_ifa_put(ifp);
-			addrconf_verify(0);
+			addrconf_verify();
 		}
 	}
 	inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
@@ -2475,7 +2497,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
 			manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
 					 true, jiffies);
 		in6_ifa_put(ifp);
-		addrconf_verify(0);
+		addrconf_verify_rtnl();
 		return 0;
 	}
 
@@ -3011,7 +3033,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
 				hlist_del_init_rcu(&ifa->addr_lst);
-				addrconf_del_dad_timer(ifa);
+				addrconf_del_dad_work(ifa);
 				goto restart;
 			}
 		}
@@ -3049,7 +3071,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	while (!list_empty(&idev->addr_list)) {
 		ifa = list_first_entry(&idev->addr_list,
 				       struct inet6_ifaddr, if_list);
-		addrconf_del_dad_timer(ifa);
+		addrconf_del_dad_work(ifa);
 
 		list_del(&ifa->if_list);
 
@@ -3148,10 +3170,10 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
 		rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1);
 
 	ifp->dad_probes = idev->cnf.dad_transmits;
-	addrconf_mod_dad_timer(ifp, rand_num);
+	addrconf_mod_dad_work(ifp, rand_num);
 }
 
-static void addrconf_dad_start(struct inet6_ifaddr *ifp)
+static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
@@ -3203,25 +3225,68 @@ out:
 	read_unlock_bh(&idev->lock);
 }
 
-static void addrconf_dad_timer(unsigned long data)
+static void addrconf_dad_start(struct inet6_ifaddr *ifp)
 {
-	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
+	bool begin_dad = false;
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
+		ifp->state = INET6_IFADDR_STATE_PREDAD;
+		begin_dad = true;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (begin_dad)
+		addrconf_mod_dad_work(ifp, 0);
+}
+
+static void addrconf_dad_work(struct work_struct *w)
+{
+	struct inet6_ifaddr *ifp = container_of(to_delayed_work(w),
+						struct inet6_ifaddr,
+						dad_work);
 	struct inet6_dev *idev = ifp->idev;
 	struct in6_addr mcaddr;
 
+	enum {
+		DAD_PROCESS,
+		DAD_BEGIN,
+		DAD_ABORT,
+	} action = DAD_PROCESS;
+
+	rtnl_lock();
+
+	spin_lock_bh(&ifp->state_lock);
+	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
+		action = DAD_BEGIN;
+		ifp->state = INET6_IFADDR_STATE_DAD;
+	} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
+		action = DAD_ABORT;
+		ifp->state = INET6_IFADDR_STATE_POSTDAD;
+	}
+	spin_unlock_bh(&ifp->state_lock);
+
+	if (action == DAD_BEGIN) {
+		addrconf_dad_begin(ifp);
+		goto out;
+	} else if (action == DAD_ABORT) {
+		addrconf_dad_stop(ifp, 1);
+		goto out;
+	}
+
 	if (!ifp->dad_probes && addrconf_dad_end(ifp))
 		goto out;
 
-	write_lock(&idev->lock);
+	write_lock_bh(&idev->lock);
 	if (idev->dead || !(idev->if_flags & IF_READY)) {
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 		goto out;
 	}
 
@@ -3232,7 +3297,7 @@ static void addrconf_dad_timer(unsigned long data)
 
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
-		write_unlock(&idev->lock);
+		write_unlock_bh(&idev->lock);
 
 		addrconf_dad_completed(ifp);
 
@@ -3240,16 +3305,17 @@ static void addrconf_dad_timer(unsigned long data)
 	}
 
 	ifp->dad_probes--;
-	addrconf_mod_dad_timer(ifp,
-			       NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
+	addrconf_mod_dad_work(ifp,
+			      NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME));
 	spin_unlock(&ifp->lock);
-	write_unlock(&idev->lock);
+	write_unlock_bh(&idev->lock);
 
 	/* send a neighbour solicitation for our addr */
 	addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
 	ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any);
 out:
 	in6_ifa_put(ifp);
+	rtnl_unlock();
 }
 
 /* ifp->idev must be at least read locked */
@@ -3276,7 +3342,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	struct in6_addr lladdr;
 	bool send_rs, send_mld;
 
-	addrconf_del_dad_timer(ifp);
+	addrconf_del_dad_work(ifp);
 
 	/*
 	 *	Configure the address for reception. Now it is valid.
@@ -3517,23 +3583,23 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
  *	Periodic address status verification
  */
 
-static void addrconf_verify(unsigned long foo)
+static void addrconf_verify_rtnl(void)
 {
 	unsigned long now, next, next_sec, next_sched;
 	struct inet6_ifaddr *ifp;
 	int i;
 
+	ASSERT_RTNL();
+
 	rcu_read_lock_bh();
-	spin_lock(&addrconf_verify_lock);
 	now = jiffies;
 	next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
 
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 
 	for (i = 0; i < IN6_ADDR_HSIZE; i++) {
 restart:
-		hlist_for_each_entry_rcu_bh(ifp,
-					 &inet6_addr_lst[i], addr_lst) {
+		hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) {
 			unsigned long age;
 
 			/* When setting preferred_lft to a value not zero or
@@ -3628,13 +3694,22 @@ restart:
 
 	ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
 	      now, next, next_sec, next_sched);
-
-	addr_chk_timer.expires = next_sched;
-	add_timer(&addr_chk_timer);
-	spin_unlock(&addrconf_verify_lock);
+	mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now);
 	rcu_read_unlock_bh();
 }
 
+static void addrconf_verify_work(struct work_struct *w)
+{
+	rtnl_lock();
+	addrconf_verify_rtnl();
+	rtnl_unlock();
+}
+
+static void addrconf_verify(void)
+{
+	mod_delayed_work(addrconf_wq, &addr_chk_work, 0);
+}
+
 static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
 				     struct in6_addr **peer_pfx)
 {
@@ -3691,6 +3766,8 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 	bool was_managetempaddr;
 	bool had_prefixroute;
 
+	ASSERT_RTNL();
+
 	if (!valid_lft || (prefered_lft > valid_lft))
 		return -EINVAL;
 
@@ -3756,7 +3833,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
 				 !was_managetempaddr, jiffies);
 	}
 
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 
 	return 0;
 }
@@ -4386,6 +4463,8 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	bool update_rs = false;
 	struct in6_addr ll_addr;
 
+	ASSERT_RTNL();
+
 	if (token == NULL)
 		return -EINVAL;
 	if (ipv6_addr_any(token))
@@ -4434,7 +4513,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	}
 
 	write_unlock_bh(&idev->lock);
-	addrconf_verify(0);
+	addrconf_verify_rtnl();
 	return 0;
 }
 
@@ -4636,6 +4715,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
 
+	if (event)
+		ASSERT_RTNL();
+
 	inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);
 
 	switch (event) {
@@ -5244,6 +5326,12 @@ int __init addrconf_init(void)
 	if (err < 0)
 		goto out_addrlabel;
 
+	addrconf_wq = create_workqueue("ipv6_addrconf");
+	if (!addrconf_wq) {
+		err = -ENOMEM;
+		goto out_nowq;
+	}
+
 	/* The addrconf netdev notifier requires that loopback_dev
 	 * has it's ipv6 private information allocated and setup
 	 * before it can bring up and give link-local addresses
@@ -5274,7 +5362,7 @@ int __init addrconf_init(void)
 
 	register_netdevice_notifier(&ipv6_dev_notf);
 
-	addrconf_verify(0);
+	addrconf_verify();
 
 	rtnl_af_register(&inet6_ops);
 
@@ -5302,6 +5390,8 @@ errout:
 	rtnl_af_unregister(&inet6_ops);
 	unregister_netdevice_notifier(&ipv6_dev_notf);
 errlo:
+	destroy_workqueue(addrconf_wq);
+out_nowq:
 	unregister_pernet_subsys(&addrconf_ops);
 out_addrlabel:
 	ipv6_addr_label_cleanup();
@@ -5337,7 +5427,8 @@ void addrconf_cleanup(void)
 	for (i = 0; i < IN6_ADDR_HSIZE; i++)
 		WARN_ON(!hlist_empty(&inet6_addr_lst[i]));
 	spin_unlock_bh(&addrconf_hash_lock);
-
-	del_timer(&addr_chk_timer);
+	cancel_delayed_work(&addr_chk_work);
 	rtnl_unlock();
+
+	destroy_workqueue(addrconf_wq);
 }

net/netfilter/nfnetlink_queue_core.c

@@ -354,13 +354,16 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 
 	skb = nfnetlink_alloc_skb(net, size, queue->peer_portid,
 				  GFP_ATOMIC);
-	if (!skb)
+	if (!skb) {
+		skb_tx_error(entskb);
 		return NULL;
+	}
 
 	nlh = nlmsg_put(skb, 0, 0,
 			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
 			sizeof(struct nfgenmsg), 0);
 	if (!nlh) {
+		skb_tx_error(entskb);
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -488,13 +491,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		nla->nla_type = NFQA_PAYLOAD;
 		nla->nla_len = nla_attr_size(data_len);
 
-		skb_zerocopy(skb, entskb, data_len, hlen);
+		if (skb_zerocopy(skb, entskb, data_len, hlen))
+			goto nla_put_failure;
 	}
 
 	nlh->nlmsg_len = skb->len;
 	return skb;
 
 nla_put_failure:
+	skb_tx_error(entskb);
 	kfree_skb(skb);
 	net_err_ratelimited("nf_queue: error creating packet message\n");
 	return NULL;

net/openvswitch/datapath.c

@@ -464,7 +464,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	}
 	nla->nla_len = nla_attr_size(skb->len);
 
-	skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	if (err)
+		goto out;
 
 	/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
 	if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
@@ -478,6 +480,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 
 	err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
 out:
+	if (err)
+		skb_tx_error(skb);
 	kfree_skb(nskb);
 	return err;
 }

net/openvswitch/flow.c

@@ -103,30 +103,24 @@ static void stats_read(struct flow_stats *stats,
 void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
 			unsigned long *used, __be16 *tcp_flags)
 {
-	int cpu, cur_cpu;
+	int cpu;
 
 	*used = 0;
 	*tcp_flags = 0;
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
+	local_bh_disable();
 	if (!flow->stats.is_percpu) {
 		stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
 	} else {
-		cur_cpu = get_cpu();
 		for_each_possible_cpu(cpu) {
 			struct flow_stats *stats;
 
-			if (cpu == cur_cpu)
-				local_bh_disable();
-
 			stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
 			stats_read(stats, ovs_stats, used, tcp_flags);
-
-			if (cpu == cur_cpu)
-				local_bh_enable();
 		}
-		put_cpu();
 	}
+	local_bh_enable();
 }
 
 static void stats_reset(struct flow_stats *stats)
@@ -141,25 +135,17 @@ static void stats_reset(struct flow_stats *stats)
 
 void ovs_flow_stats_clear(struct sw_flow *flow)
 {
-	int cpu, cur_cpu;
+	int cpu;
 
+	local_bh_disable();
 	if (!flow->stats.is_percpu) {
 		stats_reset(flow->stats.stat);
 	} else {
-		cur_cpu = get_cpu();
-
 		for_each_possible_cpu(cpu) {
-
-			if (cpu == cur_cpu)
-				local_bh_disable();
-
 			stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
-
-			if (cpu == cur_cpu)
-				local_bh_enable();
 		}
-		put_cpu();
 	}
+	local_bh_enable();
 }
 
 static int check_header(struct sk_buff *skb, int len)

net/unix/af_unix.c

@@ -1787,8 +1787,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}
 
@@ -1913,6 +1916,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct unix_sock *u = unix_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
 	int copied = 0;
+	int noblock = flags & MSG_DONTWAIT;
 	int check_creds = 0;
 	int target;
 	int err = 0;
@@ -1928,7 +1932,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		goto out;
 
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
-	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
+	timeo = sock_rcvtimeo(sk, noblock);
 
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
@@ -1940,8 +1944,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	}
 
 	err = mutex_lock_interruptible(&u->readlock);
-	if (err) {
-		err = sock_intr_errno(timeo);
+	if (unlikely(err)) {
+		/* recvmsg() in non blocking mode is supposed to return -EAGAIN
+		 * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+		 */
+		err = noblock ? -EAGAIN : -ERESTARTSYS;
 		goto out;
 	}