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

Cross-merge networking fixes after downstream PR.

Conflicts:

net/dsa/port.c
  9945c1fb03a3 ("net: dsa: fix older DSA drivers using phylink")
  a88dd7538461 ("net: dsa: remove legacy_pre_march2020 detection")
https://lore.kernel.org/all/20230731102254.2c9868ca@canb.auug.org.au/

net/xdp/xsk.c
  3c5b4d69c358 ("net: annotate data-races around sk->sk_mark")
  b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
https://lore.kernel.org/all/20230731102631.39988412@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  37b61cda9c16 ("bnxt: don't handle XDP in netpoll")
  2b56b3d99241 ("eth: bnxt: handle invalid Tx completions more gracefully")
https://lore.kernel.org/all/20230801101708.1dc7faac@canb.auug.org.au/

Adjacent changes:

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
  62da08331f1a ("net/mlx5e: Set proper IPsec source port in L4 selector")
  fbd517549c32 ("net/mlx5e: Add function to get IPsec offload namespace")

drivers/net/ethernet/sfc/selftest.c
  55c1528f9b97 ("sfc: fix field-spanning memcpy in selftest")
  ae9d445cd41f ("sfc: Miscellaneous comment removals")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

21 files changed, 154 insertions, 49 deletions

diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 20c93f08c993..95a1d214108a 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -38,7 +38,7 @@ static inline long find_zero(unsigned long mask)
 	return (mask >> 8) ? byte : byte + 1;
 }
 
-static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
 {
 	unsigned long rhs = val | c->low_bits;
 	*data = rhs;
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 4863b0f8299e..375737fd6c36 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -368,11 +368,6 @@ static inline void drm_fb_helper_deferred_io(struct fb_info *info,
 {
 }
 
-static inline int drm_fb_helper_defio_init(struct drm_fb_helper *fb_helper)
-{
-	return -ENODEV;
-}
-
 static inline void drm_fb_helper_set_suspend(struct drm_fb_helper *fb_helper,
 					     bool suspend)
 {
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 0d2e2a38b92d..f10fb87d49db 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -175,8 +175,8 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 
 /**
  * cpumask_first_and - return the first cpu from *srcp1 & *srcp2
- * @src1p: the first input
- * @src2p: the second input
+ * @srcp1: the first input
+ * @srcp2: the second input
  *
  * Returns >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
@@ -1197,6 +1197,10 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
 /**
  * cpumap_print_list_to_buf  - copies the cpumask into the buffer as
  *	comma-separated list of cpus
+ * @buf: the buffer to copy into
+ * @mask: the cpumask to copy
+ * @off: in the string from which we are copying, we copy to @buf
+ * @count: the maximum number of bytes to print
  *
  * Everything is same with the above cpumap_print_bitmask_to_buf()
  * except the print format.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ce156c7704ee..aad9cf8876b5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -684,7 +684,6 @@ void __init
 ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 
 /* defined in arch */
-extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
@@ -859,9 +858,6 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 }
 #endif
 
-/* May be defined in arch */
-extern int ftrace_arch_read_dyn_info(char *buf, int size);
-
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
 extern void ftrace_module_enable(struct module *mod);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2dd73e4f3d8e..406ab9ea818f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -641,8 +641,14 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
  */
 static inline bool vma_start_read(struct vm_area_struct *vma)
 {
-	/* Check before locking. A race might cause false locked result. */
-	if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
+	/*
+	 * Check before locking. A race might cause false locked result.
+	 * We can use READ_ONCE() for the mm_lock_seq here, and don't need
+	 * ACQUIRE semantics, because this is just a lockless check whose result
+	 * we don't rely on for anything - the mm_lock_seq read against which we
+	 * need ordering is below.
+	 */
+	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq))
 		return false;
 
 	if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
@@ -653,8 +659,13 @@ static inline bool vma_start_read(struct vm_area_struct *vma)
 	 * False unlocked result is impossible because we modify and check
 	 * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
 	 * modification invalidates all existing locks.
+	 *
+	 * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
+	 * racing with vma_end_write_all(), we only start reading from the VMA
+	 * after it has been unlocked.
+	 * This pairs with RELEASE semantics in vma_end_write_all().
 	 */
-	if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
+	if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) {
 		up_read(&vma->vm_lock->lock);
 		return false;
 	}
@@ -676,7 +687,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
 	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
 	 * mm->mm_lock_seq can't be concurrently modified.
 	 */
-	*mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
+	*mm_lock_seq = vma->vm_mm->mm_lock_seq;
 	return (vma->vm_lock_seq == *mm_lock_seq);
 }
 
@@ -688,7 +699,13 @@ static inline void vma_start_write(struct vm_area_struct *vma)
 		return;
 
 	down_write(&vma->vm_lock->lock);
-	vma->vm_lock_seq = mm_lock_seq;
+	/*
+	 * We should use WRITE_ONCE() here because we can have concurrent reads
+	 * from the early lockless pessimistic check in vma_start_read().
+	 * We don't really care about the correctness of that early check, but
+	 * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
+	 */
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 }
 
@@ -702,7 +719,7 @@ static inline bool vma_try_start_write(struct vm_area_struct *vma)
 	if (!down_write_trylock(&vma->vm_lock->lock))
 		return false;
 
-	vma->vm_lock_seq = mm_lock_seq;
+	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
 	up_write(&vma->vm_lock->lock);
 	return true;
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index de10fc797c8e..5e74ce4a28cd 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -514,6 +514,20 @@ struct vm_area_struct {
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Can only be written (using WRITE_ONCE()) while holding both:
+	 *  - mmap_lock (in write mode)
+	 *  - vm_lock->lock (in write mode)
+	 * Can be read reliably while holding one of:
+	 *  - mmap_lock (in read or write mode)
+	 *  - vm_lock->lock (in read or write mode)
+	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+	 * while holding nothing (except RCU to keep the VMA struct allocated).
+	 *
+	 * This sequence counter is explicitly allowed to overflow; sequence
+	 * counter reuse can only lead to occasional unnecessary use of the
+	 * slowpath.
+	 */
 	int vm_lock_seq;
 	struct vma_lock *vm_lock;
 
@@ -679,6 +693,20 @@ struct mm_struct {
 					  * by mmlist_lock
 					  */
 #ifdef CONFIG_PER_VMA_LOCK
+		/*
+		 * This field has lock-like semantics, meaning it is sometimes
+		 * accessed with ACQUIRE/RELEASE semantics.
+		 * Roughly speaking, incrementing the sequence number is
+		 * equivalent to releasing locks on VMAs; reading the sequence
+		 * number can be part of taking a read lock on a VMA.
+		 *
+		 * Can be modified under write mmap_lock using RELEASE
+		 * semantics.
+		 * Can be read with no other protection when holding write
+		 * mmap_lock.
+		 * Can be read with ACQUIRE semantics if not holding write
+		 * mmap_lock.
+		 */
 		int mm_lock_seq;
 #endif
 
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index aab8f1b28d26..e05e167dbd16 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -76,8 +76,14 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 static inline void vma_end_write_all(struct mm_struct *mm)
 {
 	mmap_assert_write_locked(mm);
-	/* No races during update due to exclusive mmap_lock being held */
-	WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+	/*
+	 * Nobody can concurrently modify mm->mm_lock_seq due to exclusive
+	 * mmap_lock being held.
+	 * We need RELEASE semantics here to ensure that preceding stores into
+	 * the VMA take effect before we unlock it with this store.
+	 * Pairs with ACQUIRE semantics in vma_start_read().
+	 */
+	smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
 }
 #else
 static inline void vma_end_write_all(struct mm_struct *mm) {}
diff --git a/include/linux/nls.h b/include/linux/nls.h
index 499e486b3722..e0bf8367b274 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -47,7 +47,7 @@ enum utf16_endian {
 /* nls_base.c */
 extern int __register_nls(struct nls_table *, struct module *);
 extern int unregister_nls(struct nls_table *);
-extern struct nls_table *load_nls(char *);
+extern struct nls_table *load_nls(const char *charset);
 extern void unload_nls(struct nls_table *);
 extern struct nls_table *load_nls_default(void);
 #define register_nls(nls) __register_nls((nls), THIS_MODULE)
diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h
index dd42d16945d0..d9642c6cf852 100644
--- a/include/linux/pm_wakeirq.h
+++ b/include/linux/pm_wakeirq.h
@@ -10,8 +10,6 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq);
 extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq);
 extern void dev_pm_clear_wake_irq(struct device *dev);
-extern void dev_pm_enable_wake_irq(struct device *dev);
-extern void dev_pm_disable_wake_irq(struct device *dev);
 
 #else	/* !CONFIG_PM */
 
@@ -34,13 +32,5 @@ static inline void dev_pm_clear_wake_irq(struct device *dev)
 {
 }
 
-static inline void dev_pm_enable_wake_irq(struct device *dev)
-{
-}
-
-static inline void dev_pm_disable_wake_irq(struct device *dev)
-{
-}
-
 #endif	/* CONFIG_PM */
 #endif	/* _LINUX_PM_WAKEIRQ_H */
diff --git a/include/linux/spi/corgi_lcd.h b/include/linux/spi/corgi_lcd.h
index 0b857616919c..fc6c1515dc54 100644
--- a/include/linux/spi/corgi_lcd.h
+++ b/include/linux/spi/corgi_lcd.h
@@ -15,4 +15,6 @@ struct corgi_lcd_platform_data {
 	void (*kick_battery)(void);
 };
 
+void corgi_lcd_limit_intensity(int limit);
+
 #endif /* __LINUX_SPI_CORGI_LCD_H */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 87837094d549..dee66ade89a0 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -301,14 +301,14 @@ int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
 #ifdef CONFIG_THERMAL
 struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
 		void *, struct thermal_zone_device_ops *,
-		struct thermal_zone_params *, int, int);
+		const struct thermal_zone_params *, int, int);
 
 void thermal_zone_device_unregister(struct thermal_zone_device *);
 
 struct thermal_zone_device *
 thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int, int,
 					void *, struct thermal_zone_device_ops *,
-					struct thermal_zone_params *, int, int);
+					const struct thermal_zone_params *, int, int);
 
 void *thermal_zone_device_priv(struct thermal_zone_device *tzd);
 const char *thermal_zone_device_type(struct thermal_zone_device *tzd);
@@ -348,7 +348,7 @@ void thermal_zone_device_critical(struct thermal_zone_device *tz);
 static inline struct thermal_zone_device *thermal_zone_device_register(
 	const char *type, int trips, int mask, void *devdata,
 	struct thermal_zone_device_ops *ops,
-	struct thermal_zone_params *tzp,
+	const struct thermal_zone_params *tzp,
 	int passive_delay, int polling_delay)
 { return ERR_PTR(-ENODEV); }
 static inline void thermal_zone_device_unregister(
diff --git a/include/net/gro.h b/include/net/gro.h
index 75efa6fb8441..88644b3ca660 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -452,6 +452,49 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb,
 		gro_normal_list(napi);
 }
 
+/* This function is the alternative of 'inet_iif' and 'inet_sdif'
+ * functions in case we can not rely on fields of IPCB.
+ *
+ * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized.
+ * The caller must hold the RCU read lock.
+ */
+static inline void inet_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif)
+{
+	*iif = inet_iif(skb) ?: skb->dev->ifindex;
+	*sdif = 0;
+
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(skb->dev)) {
+		struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev);
+
+		*sdif = *iif;
+		*iif = master ? master->ifindex : 0;
+	}
+#endif
+}
+
+/* This function is the alternative of 'inet6_iif' and 'inet6_sdif'
+ * functions in case we can not rely on fields of IP6CB.
+ *
+ * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized.
+ * The caller must hold the RCU read lock.
+ */
+static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif)
+{
+	/* using skb->dev->ifindex because skb_dst(skb) is not initialized */
+	*iif = skb->dev->ifindex;
+	*sdif = 0;
+
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(skb->dev)) {
+		struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev);
+
+		*sdif = *iif;
+		*iif = master ? master->ifindex : 0;
+	}
+#endif
+}
+
 extern struct list_head offload_base;
 
 #endif /* _NET_IPV6_GRO_H */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index caa20a905531..0bb32bfc6183 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -107,11 +107,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 
 static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 {
-	if (!sk->sk_mark &&
-	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
+	u32 mark = READ_ONCE(sk->sk_mark);
+
+	if (!mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
 		return skb->mark;
 
-	return sk->sk_mark;
+	return mark;
 }
 
 static inline int inet_request_bound_dev_if(const struct sock *sk,
diff --git a/include/net/ip.h b/include/net/ip.h
index 50d435855ae2..332521170d9b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 {
 	ipcm_init(ipcm);
 
-	ipcm->sockc.mark = inet->sk.sk_mark;
+	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
 	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
diff --git a/include/net/route.h b/include/net/route.h
index d8d150155195..d9ca98d2366f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -168,7 +168,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
 						   __be16 dport, __be16 sport,
 						   __u8 proto, __u8 tos, int oif)
 {
-	flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
+	flowi4_init_output(fl4, oif, sk ? READ_ONCE(sk->sk_mark) : 0, tos,
 			   RT_SCOPE_UNIVERSE, proto,
 			   sk ? inet_sk_flowi_flags(sk) : 0,
 			   daddr, saddr, dport, sport, sock_net_uid(net, sk));
@@ -301,7 +301,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 	if (inet_sk(sk)->transparent)
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
-	flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk),
+	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
 			   src, dport, sport, sk->sk_uid);
 }
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 1648240c9668..6a9f8a5f387c 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -556,12 +556,12 @@ static inline void vxlan_flag_attr_error(int attrtype,
 }
 
 static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh,
-					    int hash,
+					    u32 hash,
 					    struct vxlan_rdst *rdst)
 {
 	struct fib_nh_common *nhc;
 
-	nhc = nexthop_path_fdb_result(nh, hash);
+	nhc = nexthop_path_fdb_result(nh, hash >> 1);
 	if (unlikely(!nhc))
 		return false;
 
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
index fc3001483e62..a5ef84944a06 100644
--- a/include/soc/tegra/mc.h
+++ b/include/soc/tegra/mc.h
@@ -175,6 +175,9 @@ struct tegra_mc_icc_ops {
 	int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak);
 };
 
+struct icc_node *tegra_mc_icc_xlate(struct of_phandle_args *spec, void *data);
+extern const struct tegra_mc_icc_ops tegra_mc_icc_ops;
+
 struct tegra_mc_ops {
 	/*
 	 * @probe: Callback to set up SoC-specific bits of the memory controller. This is called
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index b80fcc9ea525..f85743ef6e7d 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -51,13 +51,13 @@ enum blk_zone_type {
  *
  * The Zone Condition state machine in the ZBC/ZAC standards maps the above
  * deinitions as:
- *   - ZC1: Empty         | BLK_ZONE_EMPTY
+ *   - ZC1: Empty         | BLK_ZONE_COND_EMPTY
  *   - ZC2: Implicit Open | BLK_ZONE_COND_IMP_OPEN
  *   - ZC3: Explicit Open | BLK_ZONE_COND_EXP_OPEN
- *   - ZC4: Closed        | BLK_ZONE_CLOSED
- *   - ZC5: Full          | BLK_ZONE_FULL
- *   - ZC6: Read Only     | BLK_ZONE_READONLY
- *   - ZC7: Offline       | BLK_ZONE_OFFLINE
+ *   - ZC4: Closed        | BLK_ZONE_COND_CLOSED
+ *   - ZC5: Full          | BLK_ZONE_COND_FULL
+ *   - ZC6: Read Only     | BLK_ZONE_COND_READONLY
+ *   - ZC7: Offline       | BLK_ZONE_COND_OFFLINE
  *
  * Conditions 0x5 to 0xC are reserved by the current ZBC/ZAC spec and should
  * be considered invalid.
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 75506f157340..c7082cc60d21 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -713,9 +713,11 @@ enum {
 	TCA_FLOWER_KEY_CFM_OPT_UNSPEC,
 	TCA_FLOWER_KEY_CFM_MD_LEVEL,
 	TCA_FLOWER_KEY_CFM_OPCODE,
-	TCA_FLOWER_KEY_CFM_OPT_MAX,
+	__TCA_FLOWER_KEY_CFM_OPT_MAX,
 };
 
+#define TCA_FLOWER_KEY_CFM_OPT_MAX (__TCA_FLOWER_KEY_CFM_OPT_MAX - 1)
+
 #define TCA_FLOWER_MASK_FLAGS_RANGE	(1 << 0) /* Range-based match */
 
 /* Match-all classifier */
diff --git a/include/uapi/xen/evtchn.h b/include/uapi/xen/evtchn.h
index 7fbf732f168f..aef2b75f3413 100644
--- a/include/uapi/xen/evtchn.h
+++ b/include/uapi/xen/evtchn.h
@@ -101,4 +101,13 @@ struct ioctl_evtchn_restrict_domid {
 	domid_t domid;
 };
 
+/*
+ * Bind statically allocated @port.
+ */
+#define IOCTL_EVTCHN_BIND_STATIC			\
+	_IOC(_IOC_NONE, 'E', 7, sizeof(struct ioctl_evtchn_bind))
+struct ioctl_evtchn_bind {
+	unsigned int port;
+};
+
 #endif /* __LINUX_PUBLIC_EVTCHN_H__ */
diff --git a/include/xen/events.h b/include/xen/events.h
index ac1281c5ead6..95970a2f7695 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -69,7 +69,7 @@ int xen_set_irq_priority(unsigned irq, unsigned priority);
 /*
  * Allow extra references to event channels exposed to userspace by evtchn
  */
-int evtchn_make_refcounted(evtchn_port_t evtchn);
+int evtchn_make_refcounted(evtchn_port_t evtchn, bool is_static);
 int evtchn_get(evtchn_port_t evtchn);
 void evtchn_put(evtchn_port_t evtchn);
 
@@ -141,4 +141,13 @@ void xen_init_IRQ(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
+static inline void xen_evtchn_close(evtchn_port_t port)
+{
+	struct evtchn_close close;
+
+	close.port = port;
+	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
+		BUG();
+}
+
 #endif	/* _XEN_EVENTS_H */