Merge 4.6-rc7 into char-misc-testing

This resolves a merge issue with drivers/hv/ring_buffer.c

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

48 files changed, 357 insertions, 162 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 14362a84c78e..3a932501d690 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -394,13 +394,13 @@ struct acpi_data_node {
 
 static inline bool is_acpi_node(struct fwnode_handle *fwnode)
 {
-	return fwnode && (fwnode->type == FWNODE_ACPI
+	return !IS_ERR_OR_NULL(fwnode) && (fwnode->type == FWNODE_ACPI
 		|| fwnode->type == FWNODE_ACPI_DATA);
 }
 
 static inline bool is_acpi_device_node(struct fwnode_handle *fwnode)
 {
-	return fwnode && fwnode->type == FWNODE_ACPI;
+	return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_ACPI;
 }
 
 static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode)
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index e56272c919b5..bf2d34c9d804 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -108,11 +108,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	u32 val;
 
 	preempt_disable();
-	if (unlikely(get_user(val, uaddr) != 0))
+	if (unlikely(get_user(val, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
-	if (val == oldval && unlikely(put_user(newval, uaddr) != 0))
+	if (val == oldval && unlikely(put_user(newval, uaddr) != 0)) {
+		preempt_enable();
 		return -EFAULT;
+	}
 
 	*uval = val;
 	preempt_enable();
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index 461a0558bca4..cebecff536a3 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -39,6 +39,8 @@ static inline bool drm_arch_can_wc_memory(void)
 {
 #if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
 	return false;
+#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
+	return false;
 #else
 	return true;
 #endif
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 21ee41b92e8a..f1d5c5acc8dd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -171,12 +171,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl);
 void bpf_register_map_type(struct bpf_map_type_list *tl);
 
 struct bpf_prog *bpf_prog_get(u32 ufd);
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
-void bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_precharge_memlock(u32 pages);
diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h
index 260d78b587c4..1563265d2097 100644
--- a/include/linux/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -12,9 +12,12 @@
  */
 
 struct ceph_auth_client;
-struct ceph_authorizer;
 struct ceph_msg;
 
+struct ceph_authorizer {
+	void (*destroy)(struct ceph_authorizer *);
+};
+
 struct ceph_auth_handshake {
 	struct ceph_authorizer *authorizer;
 	void *authorizer_buf;
@@ -62,8 +65,6 @@ struct ceph_auth_client_ops {
 				 struct ceph_auth_handshake *auth);
 	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a, size_t len);
-	void (*destroy_authorizer)(struct ceph_auth_client *ac,
-				   struct ceph_authorizer *a);
 	void (*invalidate_authorizer)(struct ceph_auth_client *ac,
 				      int peer_type);
 
@@ -112,8 +113,7 @@ extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac);
 extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
 				       int peer_type,
 				       struct ceph_auth_handshake *auth);
-extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac,
-					 struct ceph_authorizer *a);
+void ceph_auth_destroy_authorizer(struct ceph_authorizer *a);
 extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
 				       int peer_type,
 				       struct ceph_auth_handshake *a);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 4343df806710..cbf460927c42 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -16,7 +16,6 @@ struct ceph_msg;
 struct ceph_snap_context;
 struct ceph_osd_request;
 struct ceph_osd_client;
-struct ceph_authorizer;
 
 /*
  * completion callback for async writepages
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 3e39ae5bc799..5b17de62c962 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -444,6 +444,7 @@ struct cgroup_subsys {
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);
+	void (*post_attach)(void);
 	int (*can_fork)(struct task_struct *task);
 	void (*cancel_fork)(struct task_struct *task);
 	void (*fork)(struct task_struct *task);
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index fea160ee5803..85a868ccb493 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,8 +137,6 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
-extern void cpuset_post_attach_flush(void);
-
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -245,10 +243,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
-static inline void cpuset_post_attach_flush(void)
-{
-}
-
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index e0ee0b3000b2..5871f292b596 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,37 +15,23 @@
 
 #include <linux/errno.h>
 
+struct pts_fs_info;
+
 #ifdef CONFIG_UNIX98_PTYS
 
-int devpts_new_index(struct inode *ptmx_inode);
-void devpts_kill_index(struct inode *ptmx_inode, int idx);
-void devpts_add_ref(struct inode *ptmx_inode);
-void devpts_del_ref(struct inode *ptmx_inode);
+/* Look up a pts fs info and get a ref to it */
+struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
+void devpts_put_ref(struct pts_fs_info *);
+
+int devpts_new_index(struct pts_fs_info *);
+void devpts_kill_index(struct pts_fs_info *, int);
+
 /* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
-		void *priv);
+struct dentry *devpts_pty_new(struct pts_fs_info *, int, void *);
 /* get private structure */
-void *devpts_get_priv(struct inode *pts_inode);
+void *devpts_get_priv(struct dentry *);
 /* unlink */
-void devpts_pty_kill(struct inode *inode);
-
-#else
-
-/* Dummy stubs in the no-pty case */
-static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
-static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline void devpts_add_ref(struct inode *ptmx_inode) { }
-static inline void devpts_del_ref(struct inode *ptmx_inode) { }
-static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
-		dev_t device, int index, void *priv)
-{
-	return ERR_PTR(-EINVAL);
-}
-static inline void *devpts_get_priv(struct inode *pts_inode)
-{
-	return NULL;
-}
-static inline void devpts_pty_kill(struct inode *inode) { }
+void devpts_pty_kill(struct dentry *);
 
 #endif
 
diff --git a/include/linux/hash.h b/include/linux/hash.h
index 1afde47e1528..79c52fa81cac 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -32,12 +32,28 @@
 #error Wordsize not 32 or 64
 #endif
 
+/*
+ * The above primes are actively bad for hashing, since they are
+ * too sparse. The 32-bit one is mostly ok, the 64-bit one causes
+ * real problems. Besides, the "prime" part is pointless for the
+ * multiplicative hash.
+ *
+ * Although a random odd number will do, it turns out that the golden
+ * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
+ * properties.
+ *
+ * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2.
+ * (See Knuth vol 3, section 6.4, exercise 9.)
+ */
+#define GOLDEN_RATIO_32 0x61C88647
+#define GOLDEN_RATIO_64 0x61C8864680B583EBull
+
 static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
-#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
-	hash = hash * GOLDEN_RATIO_PRIME_64;
+#if BITS_PER_LONG == 64
+	hash = hash * GOLDEN_RATIO_64;
 #else
 	/*  Sigh, gcc can't optimise this alone like it does for 32 bits. */
 	u64 n = hash;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7008623e24b1..d7b9e5346fba 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -152,6 +152,7 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 }
 
 struct page *get_huge_zero_page(void);
+void put_huge_zero_page(void);
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
@@ -208,6 +209,10 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+static inline void put_huge_zero_page(void)
+{
+	BUILD_BUG();
+}
 
 static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmd, int flags)
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index d5569734f672..548fd535fd02 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -28,6 +28,11 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_mac_header(skb);
 }
 
+static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
+{
+	return (struct ethhdr *)skb_inner_mac_header(skb);
+}
+
 int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
 
 extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index d026b190c530..d10ef06971b5 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -196,9 +196,11 @@ struct lock_list {
  * We record lock dependency chains, so that we can cache them:
  */
 struct lock_chain {
-	u8				irq_context;
-	u8				depth;
-	u16				base;
+	/* see BUILD_BUG_ON()s in lookup_chain_cache() */
+	unsigned int			irq_context :  2,
+					depth       :  6,
+					base	    : 24;
+	/* 4 byte hole */
 	struct hlist_node		entry;
 	u64				chain_key;
 };
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8541a913f6a3..d1f904c8b2cb 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -828,6 +828,11 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
+enum mlx4_pci_status {
+	MLX4_PCI_STATUS_DISABLED,
+	MLX4_PCI_STATUS_ENABLED,
+};
+
 struct mlx4_dev_persistent {
 	struct pci_dev	       *pdev;
 	struct mlx4_dev	       *dev;
@@ -841,6 +846,8 @@ struct mlx4_dev_persistent {
 	u8		state;
 	struct mutex	interface_state_mutex; /* protect SW state */
 	u8	interface_state;
+	struct mutex		pci_status_mutex; /* sync pci state */
+	enum mlx4_pci_status	pci_status;
 };
 
 struct mlx4_dev {
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 8156e3c9239c..b3575f392492 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -392,6 +392,17 @@ enum {
 	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
 };
 
+enum {
+	/*
+	 * Max wqe size for rdma read is 512 bytes, so this
+	 * limits our max_sge_rd as the wqe needs to fit:
+	 * - ctrl segment (16 bytes)
+	 * - rdma segment (16 bytes)
+	 * - scatter elements (16 bytes each)
+	 */
+	MLX5_MAX_SGE_RD	= (512 - 16 - 16) / 16
+};
+
 struct mlx5_inbox_hdr {
 	__be16		opcode;
 	u8		rsvd[4];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index dcd5ac8d3b14..369c837d40f5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -519,8 +519,9 @@ enum mlx5_device_state {
 };
 
 enum mlx5_interface_state {
-	MLX5_INTERFACE_STATE_DOWN,
-	MLX5_INTERFACE_STATE_UP,
+	MLX5_INTERFACE_STATE_DOWN = BIT(0),
+	MLX5_INTERFACE_STATE_UP = BIT(1),
+	MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2),
 };
 
 enum mlx5_pci_status {
@@ -544,7 +545,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
-	enum mlx5_interface_state interface_state;
+	unsigned long		intf_state;
 	void			(*event) (struct mlx5_core_dev *dev,
 					  enum mlx5_dev_event event,
 					  unsigned long param);
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index a1d145abd4eb..b30250ab7604 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -54,9 +54,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status);
 
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port);
-void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port);
-void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
 
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index bd93e6323603..301da4a5e6bf 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -45,6 +45,8 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				     u16 vport, u8 *addr);
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev,
 				      u16 vport, u8 *addr);
+int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
+int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a55e5be0894f..864d7221de84 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1031,6 +1031,8 @@ static inline bool page_mapped(struct page *page)
 	page = compound_head(page);
 	if (atomic_read(compound_mapcount_ptr(page)) >= 0)
 		return true;
+	if (PageHuge(page))
+		return false;
 	for (i = 0; i < hpage_nr_pages(page); i++) {
 		if (atomic_read(&page[i]._mapcount) >= 0)
 			return true;
@@ -1138,6 +1140,8 @@ struct zap_details {
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		pte_t pte);
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd);
 
 int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size);
diff --git a/include/linux/net.h b/include/linux/net.h
index 49175e4ced11..f840d77c6c31 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -246,7 +246,15 @@ do {								\
 	net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG)
+#define net_dbg_ratelimited(fmt, ...)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
+	    net_ratelimit())						\
+		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+} while (0)
+#elif defined(DEBUG)
 #define net_dbg_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
 #else
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8395308a2445..b3c46b019ac1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4004,7 +4004,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
-	netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
+	netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT;
 
 	/* check flags correspondence */
 	BUILD_BUG_ON(SKB_GSO_TCPV4   != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
diff --git a/include/linux/of.h b/include/linux/of.h
index 7fcb681baadf..31758036787c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -133,7 +133,7 @@ void of_core_init(void);
 
 static inline bool is_of_node(struct fwnode_handle *fwnode)
 {
-	return fwnode && fwnode->type == FWNODE_OF;
+	return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF;
 }
 
 static inline struct device_node *to_of_node(struct fwnode_handle *fwnode)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f4ed4f1b0c77..6b052aa7b5b7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -517,6 +517,27 @@ static inline int PageTransCompound(struct page *page)
 }
 
 /*
+ * PageTransCompoundMap is the same as PageTransCompound, but it also
+ * guarantees the primary MMU has the entire compound page mapped
+ * through pmd_trans_huge, which in turn guarantees the secondary MMUs
+ * can also map the entire compound page. This allows the secondary
+ * MMUs to call get_user_pages() only once for each compound page and
+ * to immediately map the entire compound page with a single secondary
+ * MMU fault. If there will be a pmd split later, the secondary MMUs
+ * will get an update through the MMU notifier invalidation through
+ * split_huge_pmd().
+ *
+ * Unlike PageTransCompound, this is safe to be called only while
+ * split_huge_pmd() cannot run from under us, like if protected by the
+ * MMU notifier, otherwise it may result in page->_mapcount < 0 false
+ * positives.
+ */
+static inline int PageTransCompoundMap(struct page *page)
+{
+	return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0;
+}
+
+/*
  * PageTransTail returns true for both transparent huge pages
  * and hugetlbfs pages, so it should only be called when it's known
  * that hugetlbfs pages aren't involved.
@@ -559,6 +580,7 @@ static inline int TestClearPageDoubleMap(struct page *page)
 #else
 TESTPAGEFLAG_FALSE(TransHuge)
 TESTPAGEFLAG_FALSE(TransCompound)
+TESTPAGEFLAG_FALSE(TransCompoundMap)
 TESTPAGEFLAG_FALSE(TransTail)
 TESTPAGEFLAG_FALSE(DoubleMap)
 	TESTSETFLAG_FALSE(DoubleMap)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 004b8133417d..932ec74909c6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1111,6 +1111,7 @@ void pci_unlock_rescan_remove(void);
 /* Vital product data routines */
 ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
+int pci_set_vpd_size(struct pci_dev *dev, size_t len);
 
 /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */
 resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 1c33dd7da4a7..4ae95f7e8597 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -98,6 +98,45 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
+
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the end of the specified hlist_nulls,
+ * while permitting racing traversals.  NOTE: tail insertion requires
+ * list traversal.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
+	     i = hlist_nulls_next_rcu(i))
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2b83359c19ca..0a4cd4703f40 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -533,6 +533,10 @@ static inline swp_entry_t get_swap_page(void)
 #ifdef CONFIG_MEMCG
 static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 {
+	/* Cgroup2 doesn't have per-cgroup swappiness */
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return vm_swappiness;
+
 	/* root ? */
 	if (mem_cgroup_disabled() || !memcg->css.parent)
 		return vm_swappiness;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a55d0523f75d..1b8a5a7876ce 100644
--- a/