Merge remote-tracking branch 'torvalds/master' into perf-tools-next

To pick up fixes that went thru perf-tools for v6.7 and to get in sync
with upstream to check for drift in the copies of headers, etc.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

13 files changed, 1092 insertions, 20 deletions

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index abe087c53b4b..756b013fb832 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -71,7 +71,7 @@ __SYSCALL(__NR_fremovexattr, sys_fremovexattr)
 #define __NR_getcwd 17
 __SYSCALL(__NR_getcwd, sys_getcwd)
 #define __NR_lookup_dcookie 18
-__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+__SYSCALL(__NR_lookup_dcookie, sys_ni_syscall)
 #define __NR_eventfd2 19
 __SYSCALL(__NR_eventfd2, sys_eventfd2)
 #define __NR_epoll_create1 20
@@ -816,15 +816,21 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
-
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
-
 #define __NR_fchmodat2 452
 __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_map_shadow_stack 453
+__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 #undef __NR_syscalls
-#define __NR_syscalls 453
+#define __NR_syscalls 457
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 794c1d857677..de723566c5ae 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1134,6 +1134,26 @@ extern "C" {
 #define DRM_IOCTL_MODE_PAGE_FLIP	DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
 #define DRM_IOCTL_MODE_DIRTYFB		DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
 
+/**
+ * DRM_IOCTL_MODE_CREATE_DUMB - Create a new dumb buffer object.
+ *
+ * KMS dumb buffers provide a very primitive way to allocate a buffer object
+ * suitable for scanout and map it for software rendering. KMS dumb buffers are
+ * not suitable for hardware-accelerated rendering nor video decoding. KMS dumb
+ * buffers are not suitable to be displayed on any other device than the KMS
+ * device where they were allocated from. Also see
+ * :ref:`kms_dumb_buffer_objects`.
+ *
+ * The IOCTL argument is a struct drm_mode_create_dumb.
+ *
+ * User-space is expected to create a KMS dumb buffer via this IOCTL, then add
+ * it as a KMS framebuffer via &DRM_IOCTL_MODE_ADDFB and map it via
+ * &DRM_IOCTL_MODE_MAP_DUMB.
+ *
+ * &DRM_CAP_DUMB_BUFFER indicates whether this IOCTL is supported.
+ * &DRM_CAP_DUMB_PREFERRED_DEPTH and &DRM_CAP_DUMB_PREFER_SHADOW indicate
+ * driver preferences for dumb buffers.
+ */
 #define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
 #define DRM_IOCTL_MODE_MAP_DUMB    DRM_IOWR(0xB3, struct drm_mode_map_dumb)
 #define DRM_IOCTL_MODE_DESTROY_DUMB    DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7000e5910a1d..218edb0a96f8 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -38,13 +38,13 @@ extern "C" {
  */
 
 /**
- * DOC: uevents generated by i915 on it's device node
+ * DOC: uevents generated by i915 on its device node
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
- *	event from the gpu l3 cache. Additional information supplied is ROW,
+ *	event from the GPU L3 cache. Additional information supplied is ROW,
  *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
- *	track of these events and if a specific cache-line seems to have a
- *	persistent error remap it with the l3 remapping tool supplied in
+ *	track of these events, and if a specific cache-line seems to have a
+ *	persistent error, remap it with the L3 remapping tool supplied in
  *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8790b3962e4b..0f6cdf52b1da 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -932,7 +932,14 @@ enum bpf_map_type {
 	 */
 	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
+	/* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs
+	 * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE +
+	 * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE
+	 * deprecated.
+	 */
+	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
 	BPF_MAP_TYPE_SK_STORAGE,
@@ -1040,6 +1047,13 @@ enum bpf_attach_type {
 	BPF_TCX_INGRESS,
 	BPF_TCX_EGRESS,
 	BPF_TRACE_UPROBE_MULTI,
+	BPF_CGROUP_UNIX_CONNECT,
+	BPF_CGROUP_UNIX_SENDMSG,
+	BPF_CGROUP_UNIX_RECVMSG,
+	BPF_CGROUP_UNIX_GETPEERNAME,
+	BPF_CGROUP_UNIX_GETSOCKNAME,
+	BPF_NETKIT_PRIMARY,
+	BPF_NETKIT_PEER,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1059,6 +1073,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_NETFILTER = 10,
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
+	BPF_LINK_TYPE_NETKIT = 13,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1644,6 +1659,13 @@ union bpf_attr {
 				__u32		flags;
 				__u32		pid;
 			} uprobe_multi;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} netkit;
 		};
 	} link_create;
 
@@ -1962,7 +1984,9 @@ union bpf_attr {
  * 		performed again, if the helper is used in combination with
  * 		direct packet access.
  * 	Return
- * 		0 on success, or a negative error in case of failure.
+ * 		0 on success, or a negative error in case of failure. Positive
+ * 		error indicates a potential drop or congestion in the target
+ * 		device. The particular positive error codes are not defined.
  *
  * u64 bpf_get_current_pid_tgid(void)
  * 	Description
@@ -2695,8 +2719,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
@@ -2934,8 +2958,8 @@ union bpf_attr {
  * 		*bpf_socket* should be one of the following:
  *
  * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
- * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
- * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**,
+ *		  **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**.
  *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the same set of *optname*\ s that is supported by
@@ -3255,6 +3279,11 @@ union bpf_attr {
  *			and *params*->smac will not be set as output. A common
  *			use case is to call **bpf_redirect_neigh**\ () after
  *			doing **bpf_fib_lookup**\ ().
+ *		**BPF_FIB_LOOKUP_SRC**
+ *			Derive and set source IP addr in *params*->ipv{4,6}_src
+ *			for the nexthop. If the src addr cannot be derived,
+ *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
+ *			case, *params*->dmac and *params*->smac are not set either.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -5087,6 +5116,8 @@ union bpf_attr {
  *		**BPF_F_TIMER_ABS**
  *			Start the timer in absolute expire value instead of the
  *			default relative one.
+ *		**BPF_F_TIMER_CPU_PIN**
+ *			Timer will be pinned to the CPU of the caller.
  *
  *	Return
  *		0 on success.
@@ -6523,6 +6554,7 @@ struct bpf_link_info {
 			__aligned_u64 addrs;
 			__u32 count; /* in/out: kprobe_multi function count */
 			__u32 flags;
+			__u64 missed;
 		} kprobe_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
@@ -6538,6 +6570,7 @@ struct bpf_link_info {
 					__u32 name_len;
 					__u32 offset; /* offset from func_name */
 					__u64 addr;
+					__u64 missed;
 				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
 				struct {
 					__aligned_u64 tp_name;   /* in/out */
@@ -6553,6 +6586,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} tcx;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} netkit;
 	};
 } __attribute__((aligned(8)));
 
@@ -6951,6 +6988,7 @@ enum {
 	BPF_FIB_LOOKUP_OUTPUT  = (1U << 1),
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
+	BPF_FIB_LOOKUP_SRC     = (1U << 4),
 };
 
 enum {
@@ -6963,6 +7001,7 @@ enum {
 	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
 	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
 	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_FIB_LKUP_RET_NO_SRC_ADDR,  /* failed to derive IP src addr */
 };
 
 struct bpf_fib_lookup {
@@ -6997,6 +7036,9 @@ struct bpf_fib_lookup {
 		__u32	rt_metric;
 	};
 
+	/* input: source address to consider for lookup
+	 * output: source address result from lookup
+	 */
 	union {
 		__be32		ipv4_src;
 		__u32		ipv6_src[4];  /* in6_addr; network order */
@@ -7298,9 +7340,11 @@ struct bpf_core_relo {
  * Flags to control bpf_timer_start() behaviour.
  *     - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
  *       relative to current time.
+ *     - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller.
  */
 enum {
 	BPF_F_TIMER_ABS = (1ULL << 0),
+	BPF_F_TIMER_CPU_PIN = (1ULL << 1),
 };
 
 /* BPF numbers iterator state */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index b7b56871029c..da43810b7485 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -305,4 +305,63 @@ typedef int __bitwise __kernel_rwf_t;
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
 			 RWF_APPEND)
 
+/* Pagemap ioctl */
+#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
+
+/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
+#define PAGE_IS_WPALLOWED	(1 << 0)
+#define PAGE_IS_WRITTEN		(1 << 1)
+#define PAGE_IS_FILE		(1 << 2)
+#define PAGE_IS_PRESENT		(1 << 3)
+#define PAGE_IS_SWAPPED		(1 << 4)
+#define PAGE_IS_PFNZERO		(1 << 5)
+#define PAGE_IS_HUGE		(1 << 6)
+
+/*
+ * struct page_region - Page region with flags
+ * @start:	Start of the region
+ * @end:	End of the region (exclusive)
+ * @categories:	PAGE_IS_* category bitmask for the region
+ */
+struct page_region {
+	__u64 start;
+	__u64 end;
+	__u64 categories;
+};
+
+/* Flags for PAGEMAP_SCAN ioctl */
+#define PM_SCAN_WP_MATCHING	(1 << 0)	/* Write protect the pages matched. */
+#define PM_SCAN_CHECK_WPASYNC	(1 << 1)	/* Abort the scan when a non-WP-enabled page is found. */
+
+/*
+ * struct pm_scan_arg - Pagemap ioctl argument
+ * @size:		Size of the structure
+ * @flags:		Flags for the IOCTL
+ * @start:		Starting address of the region
+ * @end:		Ending address of the region
+ * @walk_end		Address where the scan stopped (written by kernel).
+ *			walk_end == end (address tags cleared) informs that the scan completed on entire range.
+ * @vec:		Address of page_region struct array for output
+ * @vec_len:		Length of the page_region struct array
+ * @max_pages:		Optional limit for number of returned pages (0 = disabled)
+ * @category_inverted:	PAGE_IS_* categories which values match if 0 instead of 1
+ * @category_mask:	Skip pages for which any category doesn't match
+ * @category_anyof_mask: Skip pages for which no category matches
+ * @return_mask:	PAGE_IS_* categories that are to be reported in `page_region`s returned
+ */
+struct pm_scan_arg {
+	__u64 size;
+	__u64 flags;
+	__u64 start;
+	__u64 end;
+	__u64 walk_end;
+	__u64 vec;
+	__u64 vec_len;
+	__u64 max_pages;
+	__u64 category_inverted;
+	__u64 category_mask;
+	__u64 category_anyof_mask;
+	__u64 return_mask;
+};
+
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index fd1fb0d5389d..7a8f4c290187 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -71,7 +71,8 @@ struct fscrypt_policy_v2 {
 	__u8 contents_encryption_mode;
 	__u8 filenames_encryption_mode;
 	__u8 flags;
-	__u8 __reserved[4];
+	__u8 log2_data_unit_size;
+	__u8 __reserved[3];
 	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
 };
 
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 39e659c83cfd..a0aa05a28cf2 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -211,6 +211,9 @@ struct rtnl_link_stats {
  * @rx_nohandler: Number of packets received on the interface
  *   but dropped by the networking stack because the device is
  *   not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ *   in destination MAC address.
  */
 struct rtnl_link_stats64 {
 	__u64	rx_packets;
@@ -243,6 +246,23 @@ struct rtnl_link_stats64 {
 	__u64	rx_compressed;
 	__u64	tx_compressed;
 	__u64	rx_nohandler;
+
+	__u64	rx_otherhost_dropped;
+};
+
+/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
+ * for struct rtnl_link_stats64.
+ */
+struct rtnl_hw_stats64 {
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -350,7 +370,13 @@ enum {
 	IFLA_GRO_MAX_SIZE,
 	IFLA_TSO_MAX_SIZE,
 	IFLA_TSO_MAX_SEGS,
+	IFLA_ALLMULTI,		/* Allmulti count: > 0 means acts ALLMULTI */
+
+	IFLA_DEVLINK_PORT,
 
+	IFLA_GSO_IPV4_MAX_SIZE,
+	IFLA_GRO_IPV4_MAX_SIZE,
+	IFLA_DPLL_PIN,
 	__IFLA_MAX
 };
 
@@ -539,6 +565,12 @@ enum {
 	IFLA_BRPORT_MRP_IN_OPEN,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
 	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
+	IFLA_BRPORT_LOCKED,
+	IFLA_BRPORT_MAB,
+	IFLA_BRPORT_MCAST_N_GROUPS,
+	IFLA_BRPORT_MCAST_MAX_GROUPS,
+	IFLA_BRPORT_NEIGH_VLAN_SUPPRESS,
+	IFLA_BRPORT_BACKUP_NHID,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -716,7 +748,79 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
+/* Tunnel RTM header */
+struct tunnel_msg {
+	__u8 family;
+	__u8 flags;
+	__u16 reserved2;
+	__u32 ifindex;
+};
+
+/* netkit section */
+enum netkit_action {
+	NETKIT_NEXT	= -1,
+	NETKIT_PASS	= 0,
+	NETKIT_DROP	= 2,
+	NETKIT_REDIRECT	= 7,
+};
+
+enum netkit_mode {
+	NETKIT_L2,
+	NETKIT_L3,
+};
+
+enum {
+	IFLA_NETKIT_UNSPEC,
+	IFLA_NETKIT_PEER_INFO,
+	IFLA_NETKIT_PRIMARY,
+	IFLA_NETKIT_POLICY,
+	IFLA_NETKIT_PEER_POLICY,
+	IFLA_NETKIT_MODE,
+	__IFLA_NETKIT_MAX,
+};
+#define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
+
 /* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS	0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+	VNIFILTER_ENTRY_STATS_UNSPEC,
+	VNIFILTER_ENTRY_STATS_RX_BYTES,
+	VNIFILTER_ENTRY_STATS_RX_PKTS,
+	VNIFILTER_ENTRY_STATS_RX_DROPS,
+	VNIFILTER_ENTRY_STATS_RX_ERRORS,
+	VNIFILTER_ENTRY_STATS_TX_BYTES,
+	VNIFILTER_ENTRY_STATS_TX_PKTS,
+	VNIFILTER_ENTRY_STATS_TX_DROPS,
+	VNIFILTER_ENTRY_STATS_TX_ERRORS,
+	VNIFILTER_ENTRY_STATS_PAD,
+	__VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_ENTRY_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY_START,
+	VXLAN_VNIFILTER_ENTRY_END,
+	VXLAN_VNIFILTER_ENTRY_GROUP,
+	VXLAN_VNIFILTER_ENTRY_GROUP6,
+	VXLAN_VNIFILTER_ENTRY_STATS,
+	__VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY,
+	__VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
+
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -748,6 +852,8 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
+	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
+	IFLA_VXLAN_LOCALBYPASS,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -781,6 +887,7 @@ enum {
 	IFLA_GENEVE_LABEL,
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
+	IFLA_GENEVE_INNER_PROTO_INHERIT,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -826,6 +933,8 @@ enum {
 	IFLA_GTP_FD1,
 	IFLA_GTP_PDP_HASHSIZE,
 	IFLA_GTP_ROLE,
+	IFLA_GTP_CREATE_SOCKETS,
+	IFLA_GTP_RESTART_COUNT,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1162,6 +1271,17 @@ enum {
 
 #define IFLA_STATS_FILTER_BIT(ATTR)	(1 << (ATTR - 1))
 
+enum {
+	IFLA_STATS_GETSET_UNSPEC,
+	IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with
+				 * a filter mask for the corresponding group.
+				 */
+	IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */
+	__IFLA_STATS_GETSET_MAX,
+};
+
+#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1)
+
 /* These are embedded into IFLA_STATS_LINK_XSTATS:
  * [IFLA_STATS_LINK_XSTATS]
  * -> [LINK_XSTATS_TYPE_xxx]
@@ -1179,10 +1299,21 @@ enum {
 enum {
 	IFLA_OFFLOAD_XSTATS_UNSPEC,
 	IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO,	/* HW stats info. A nest */
+	IFLA_OFFLOAD_XSTATS_L3_STATS,	/* struct rtnl_hw_stats64 */
 	__IFLA_OFFLOAD_XSTATS_MAX
 };
 #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
 
+enum {
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC,
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST,		/* u8 */
+	IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED,		/* u8 */
+	__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX,
+};
+#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \
+	(__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1)
+
 /* XDP section */
 
 #define XDP_FLAGS_UPDATE_IF_NOEXIST	(1U << 0)
@@ -1281,4 +1412,14 @@ enum {
 
 #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
 
+/* DSA section */
+
+enum {
+	IFLA_DSA_UNSPEC,
+	IFLA_DSA_MASTER,
+	__IFLA_DSA_MAX,
+};
+
+#define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/io_uring.h b/tools/include/uapi/linux/io_uring.h
new file mode 100644
index 000000000000..f1c16f817742
--- /dev/null
+++ b/tools/include/uapi/linux/io_uring.h
@@ -0,0 +1,757 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
+/*
+ * Header file for the io_uring interface.
+ *
+ * Copyright (C) 2019 Jens Axboe
+ * Copyright (C) 2019 Christoph Hellwig
+ */
+#ifndef LINUX_IO_URING_H
+#define LINUX_IO_URING_H
+
+#include <linux/fs.h>
+#include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+#include <linux/time_types.h>
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+ * IO submission data structure (Submission Queue Entry)
+ */
+struct io_uring_sqe {
+	__u8	opcode;		/* type of operation for this sqe */
+	__u8	flags;		/* IOSQE_ flags */
+	__u16	ioprio;		/* ioprio for the request */
+	__s32	fd;		/* file descriptor to do IO on */
+	union {
+		__u64	off;	/* offset into file */
+		__u64	addr2;
+		struct {
+			__u32	cmd_op;
+			__u32	__pad1;
+		};
+	};
+	union {
+		__u64	addr;	/* pointer to buffer or iovecs */
+		__u64	splice_off_in;
+		struct {
+			__u32	level;
+			__u32	optname;
+		};
+	};
+	__u32	len;		/* buffer size or number of iovecs */
+	union {
+		__kernel_rwf_t	rw_flags;
+		__u32		fsync_flags;
+		__u16		poll_events;	/* compatibility */
+		__u32		poll32_events;	/* word-reversed for BE */
+		__u32		sync_range_flags;
+		__u32		msg_flags;
+		__u32		timeout_flags;
+		__u32		accept_flags;
+		__u32		cancel_flags;
+		__u32		open_flags;
+		__u32		statx_flags;
+		__u32		fadvise_advice;
+		__u32		splice_flags;
+		__u32		rename_flags;
+		__u32		unlink_flags;
+		__u32		hardlink_flags;
+		__u32		xattr_flags;
+		__u32		msg_ring_flags;
+		__u32		uring_cmd_flags;
+		__u32		waitid_flags;
+		__u32		futex_flags;
+	};
+	__u64	user_data;	/* data to be passed back at completion time */
+	/* pack this to avoid bogus arm OABI complaints */
+	union {
+		/* index into fixed buffers, if used */
+		__u16	buf_index;
+		/* for grouped buffer selection */
+		__u16	buf_group;
+	} __attribute__((packed));
+	/* personality to use, if used */
+	__u16	personality;
+	union {
+		__s32	splice_fd_in;
+		__u32	file_index;
+		__u32	optlen;
+		struct {
+			__u16	addr_len;
+			__u16	__pad3[1];
+		};
+	};
+	union {
+		struct {
+			__u64	addr3;
+			__u64	__pad2[1];
+		};
+		__u64	optval;
+		/*
+		 * If the ring is initialized with IORING_SETUP_SQE128, then
+		 * this field is used for 80 bytes of arbitrary command data
+		 */
+		__u8	cmd[0];
+	};
+};
+
+/*
+ * If sqe->file_index is set to this for opcodes that instantiate a new
+ * direct descriptor (like openat/openat2/accept), then io_uring will allocate
+ * an available direct descriptor instead of having the application pass one
+ * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE
+ * if the space is full.
+ */
+#define IORING_FILE_INDEX_ALLOC		(~0U)
+
+enum {
+	IOSQE_FIXED_FILE_BIT,
+	IOSQE_IO_DRAIN_BIT,
+	IOSQE_IO_LINK_BIT,
+	IOSQE_IO_HARDLINK_BIT,
+	IOSQE_ASYNC_BIT,
+	IOSQE_BUFFER_SELECT_BIT,
+	IOSQE_CQE_SKIP_SUCCESS_BIT,
+};
+
+/*
+ * sqe->flags
+ */
+/* use fixed fileset */
+#define IOSQE_FIXED_FILE	(1U << IOSQE_FIXED_FILE_BIT)
+/* issue after inflight IO */
+#define IOSQE_IO_DRAIN		(1U << IOSQE_IO_DRAIN_BIT)
+/* links next sqe */
+#define IOSQE_IO_LINK		(1U << IOSQE_IO_LINK_BIT)
+/* like LINK, but stronger */
+#define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
+/* always go async */
+#define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT	(1U << IOSQE_BUFFER_SELECT_BIT)
+/* don't post CQE if request succeeded */
+#define IOSQE_CQE_SKIP_SUCCESS	(1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
+
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL	(1U << 0)	/* io_context is polled */
+#define IORING_SETUP_SQPOLL	(1U << 1)	/* SQ poll thread */
+#define IORING_SETUP_SQ_AFF	(1U << 2)	/* sq_thread_cpu is valid */
+#define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
+#define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
+#define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
+#define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
+#define IORING_SETUP_SUBMIT_ALL	(1U << 7)	/* continue submit on error */
+/*
+ * Cooperative task running. When requests complete, they often require
+ * forcing the submitter to transition to the kernel to complete. If this
+ * flag is set, work will be done when the task transitions anyway, rather
+ * than force an inter-processor interrupt reschedule. This avoids interrupting
+ * a task running in userspace, and saves an IPI.
+ */
+#define IORING_SETUP_COOP_TASKRUN	(1U << 8)
+/*
+ * If COOP_TASKRUN is set, get notified if task work is available for
+ * running and a kernel transition would be needed to run it. This sets
+ * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
+ */
+#define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
+#define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */
+#define IORING_SETUP_CQE32		(1U << 11) /* CQEs are 32 byte */
+/*
+ * Only one task is allowed to submit requests
+ */
+#define IORING_SETUP_SINGLE_ISSUER	(1U << 12)
+
+/*
+ * Defer running task work to get events.
+ * Rather than running bits of task work whenever the task transitions
+ * try to do it just before it is needed.
+ */
+#define IORING_SETUP_DEFER_TASKRUN	(1U << 13)
+
+/*
+ * Application provides the memory for the rings
+ */
+#define IORING_SETUP_NO_MMAP		(1U << 14)
+
+/*
+ * Register the ring fd in itself for use with
+ * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather
+ * than an fd.
+ */
+#define IORING_SETUP_REGISTERED_FD_ONLY	(1U << 15)
+
+/*
+ * Removes indirection through the SQ index array.
+ */
+#define IORING_SETUP_NO_SQARRAY		(1U << 16)
+
+enum io_uring_op {
+	IORING_OP_NOP,
+	IORING_OP_READV,
+	IORING_OP_WRITEV,
+	IORING_OP_FSYNC,
+	IORING_OP_READ_FIXED,
+	IORING_OP_WRITE_FIXED,
+	IORING_OP_POLL_ADD,
+	IORING_OP_POLL_REMOVE,
+	IORING_OP_SYNC_FILE_RANGE,
+	IORING_OP_SENDMSG,
+	IORING_OP_RECVMSG,
+	IORING_OP_TIMEOUT,
+	IORING_OP_TIMEOUT_REMOVE,
+	IORING_OP_ACCEPT,
+	IORING_OP_ASYNC_CANCEL,
+	IORING_OP_LINK_TIMEOUT,
+	IORING_OP_CONNECT,
+	IORING_OP_FALLOCATE,
+	IORING_OP_OPENAT,
+	IORING_OP_CLOSE,
+	IORING_OP_FILES_UPDATE,
+	IORING_OP_STATX,
+	IORING_OP_READ,
+	IORING_OP_WRITE,
+	IORING_OP_FADVISE,
+	IORING_OP_MADVISE,
+	IORING_OP_SEND,
+	IORING_OP_RECV,
+	IORING_OP_OPENAT2,
+	IORING_OP_EPOLL_CTL,
+	IORING_OP_SPLICE,
+	IORING_OP_PROVIDE_BUFFERS,
+	IORING_OP_REMOVE_BUFFERS,
+	IORING_OP_TEE,
+	IORING_OP_SHUTDOWN,
+	IORING_OP_RENAMEAT,
+	IORING_OP_UNLINKAT,
+	IORING_OP_MKDIRAT,
+	IORING_OP_SYMLINKAT,
+	IORING_OP_LINKAT,
+	IORING_OP_MSG_RING,
+	IORING_OP_FSETXATTR,
+	IORING_OP_SETXATTR,
+	IORING_OP_FGETXATTR,
+	IORING_OP_GETXATTR,
+	IORING_OP_SOCKET,
+	IORING_OP_URING_CMD,
+	IORING_OP_SEND_ZC,
+	IORING_OP_SENDMSG_ZC,
+	IORING_OP_READ_MULTISHOT,
+	IORING_OP_WAITID,
+	IORING_OP_FUTEX_WAIT,
+	IORING_OP_FUTEX_WAKE,
+	IORING_OP_FUTEX_WAITV,
+
+	/* this goes last, obviously */
+	IORING_OP_LAST,
+};
+
+/*
+ * sqe->uring_cmd_flags		top 8bits aren't available for userspace
+ * IORING_URING_CMD_FIXED	use registered buffer; pass this flag
+ *				along with setting sqe->buf_index.
+ */
+#define IORING_URING_CMD_FIXED	(1U << 0)
+#define IORING_URING_CMD_MASK	IORING_URING_CMD_FIXED
+
+
+/*
+ * sqe->fsync_flags
+ */
+#define IORING_FSYNC_DATASYNC	(1U << 0)
+
+/*
+ * sqe->timeout_flags
+ */
+#define IORING_TIMEOUT_ABS		(1U << 0)
+#define IORING_TIMEOUT_UPDATE		(1U << 1)
+#define IORING_TIMEOUT_BOOTTIME		(1U << 2)
+#define IORING_TIMEOUT_REALTIME		(1U << 3)
+#define IORING_LINK_TIMEOUT_UPDATE	(1U << 4)
+#define IORING_TIMEOUT_ETIME_SUCCESS	(1U << 5)
+#define IORING_TIMEOUT_MULTISHOT	(1U << 6)
+#define IORING_TIMEOUT_CLOCK_MASK	(IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
+#define IORING_TIMEOUT_UPDATE_MASK	(IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
+/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED	(1U << 31) /* the last bit of __u32 */
+
+/*
+ * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the
+ * command flags for POLL_ADD are stored in sqe->len.
+ *
+ * IORING_POLL_ADD_MULTI	Multishot poll. Sets IORING_CQE_F_MORE if
+ *				the poll handler will continue to report
+ *				CQEs on behalf of the same SQE.
+ *
+ * IORING_POLL_UPDATE		Update existing poll request, matching
+ *				sqe->addr as the old user_data field.
+ *
+ * IORING_POLL_LEVEL		Level triggered poll.
+ */
+#define IORING_POLL_ADD_MULTI	(1U << 0)
+#define IORING_POLL_UPDATE_EVENTS	(1U << 1)
+#define IORING_POLL_UPDATE_USER_DATA	(1U << 2)
+#define IORING_POLL_ADD_LEVEL		(1U << 3)
+
+/*
+ * ASYNC_CANCEL flags.
+ *
+ * IORING_ASYNC_CANCEL_ALL	Cancel all requests that match the given key
+ * IORING_ASYNC_CANCEL_FD	Key off 'fd' for cancelation rather than the
+ *				request 'user_data'
+ * IORING_ASYNC_CANCEL_ANY	Match any request
+ * IORING_ASYNC_CANCEL_FD_FIXED	'fd' passed in is a fixed descriptor
+ * IORING_ASYNC_CANCEL_USERDATA	Match on user_data, default for no other key
+ * IORING_ASYNC_CANCEL_OP	Match request based on opcode
+ */
+#define IORING_ASYNC_CANCEL_ALL	(1U << 0)
+#define IORING_ASYNC_CANCEL_FD	(1U << 1)
+#define IORING_ASYNC_CANCEL_ANY	(1U << 2)
+#define IORING_ASYNC_CANCEL_FD_FIXED	(1U << 3)
+#define IORING_ASYNC_CANCEL_USERDATA	(1U << 4)
+#define IORING_ASYNC_CANCEL_OP	(1U << 5)
+
+/*
+ * send/sendmsg and recv/recvmsg flags (sqe->ioprio)
+ *
+ * IORING_RECVSEND_POLL_FIRST	If set, instead of first attempting to send
+ *				or receive and arm poll if that yields an
+ *				-EAGAIN result, arm poll upfront and skip
+ *				the initial transfer attempt.
+ *
+ * IORING_RECV_MULTISHOT	Multishot recv. Sets IORING_CQE_F_MORE if
+ *				the handler will continue to report
+ *				CQEs on behalf of the same SQE.
+ *
+ * IORING_RECVSEND_FIXED_BUF	Use registered buffers, the index is stored in
+ *				the buf_index field.
+ *
+ * IORING_SEND_ZC_REPORT_USAGE
+ *				If set, SEND[MSG]_ZC should report
+ *				the zerocopy usage in cqe.res
+ *				for the IORING_CQE_F_NOTIF cqe.
+ *				0 is reported if zerocopy was actually possible.
+ *				IORING_NOTIF_USAGE_ZC_COPIED if data was copied
+ *				(at least partially).
+ */
+#define IORING_RECVSEND_POLL_FIRST	(1U << 0)
+#define IORING_RECV_MULTISHOT		(1U << 1)
+#define IORING_RECVSEND_FIXED_BUF	(1U << 2)
+#define IORING_SEND_ZC_REPORT_USAGE	(1U << 3)
+
+/*
+ * cqe.res for IORING_CQE_F_NOTIF if
+ * IORING_SEND_ZC_REPORT_USAGE was requested
+ *
+ * It should be treated as a flag, all other
+ * bits of cqe.res should be treated as reserved!
+ */
+#define IORING_NOTIF_USAGE_ZC_COPIED    (1U << 31)
+
+/*
+ * accept flags stored in sqe->ioprio
+ */
+#define IORING_ACCEPT_MULTISHOT	(1U << 0)
+
+/*
+ * IORING_OP_MSG_RING command types, stored in sqe->addr
+ */
+enum {
+	IORING_MSG_DATA,	/* pass sqe->len as 'res' and off as user_data */
+	IORING_MSG_SEND_FD,	/* send a registered fd to another ring */
+};
+
+/*
+ * IORING_OP_MSG_RING flags (sqe->msg_ring_flags)
+ *
+ * IORING_MSG_RING_CQE_SKIP	Don't post a CQE to the target ring. Not
+ *				applicable for IORING_MSG_DATA, obviously.
+ */
+#define IORING_MSG_RING_CQE_SKIP	(1U << 0)
+/* Pass through the flags from sqe->file_index to cqe->flags */
+#define IORING_MSG_RING_FLAGS_PASS	(1U << 1)
+
+/*
+ * IO completion data structure (Completion Queue Entry)
+ */
+struct io_uring_cqe {
+	__u64	user_data;	/* sqe->data submission passed back */
+	__s32	res;		/* result code for this event */
+	__u32	flags;
+
+	/*
+	 * If the ring is initialized with IORING_SETUP_CQE32, then this field
+	 * contains 16-bytes of padding, doubling the size of the CQE.
+	 */
+	__u64 big_cqe[];
+};
+
+/*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER	If set, the upper 16 bits are the buffer ID
+ * IORING_CQE_F_MORE	If set, parent SQE will generate more CQE entries
+ * IORING_CQE_F_SOCK_NONEMPTY	If set, more data to read after socket recv
+ * IORING_CQE_F_NOTIF	Set for notification CQEs. Can be used to distinct
+ * 			them from sends.
+ */
+#define IORING_CQE_F_BUFFER		(1U << 0)
+#define IORING_CQE_F_MORE		(1U << 1)
+#define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
+#define IORING_CQE_F_NOTIF		(1U << 3)
+
+enum {
+	IORING_CQE_BUFFER_SHIFT		= 16,
+};
+
+/*
+ * Magic offsets for the application to mmap the data it needs
+ */
+#define IORING_OFF_SQ_RING		0ULL
+#define IORING_OFF_CQ_RING		0x8000000ULL
+#define IORING_OFF_SQES			0x10000000ULL
+#define IORING_OFF_PBUF_RING		0x80000000ULL
+#define IORING_OFF_PBUF_SHIFT		16
+#define IORING_OFF_MMAP_MASK		0xf8000000ULL
+
+/*
+ * Filled with the offset for mmap(2)
+ */
+struct io_sqring_offsets {
+	__u32 head;
+	__u32 tail;
+	__u32 ring_mask;
+	__u32 ring_entries;
+	__u32 flags;
+	__u32 dropped;
+	__u32 array;
+	__u32 resv1;
+	__u64 user_addr;
+};
+
+/*
+ * sq_ring->flags
+ */
+#define IORING_SQ_NEED_WAKEUP	(1U << 0) /* needs io_uring_enter wakeup */
+#define IORING_SQ_CQ_OVERFLOW	(1U << 1) /* CQ ring is overflown */
+#define IORING_SQ_TASKRUN	(1U << 2) /* task should enter the kernel */
+
+struct io_cqring_offsets {
+	__u32 head;
+	__u32 tail;
+	__u32 ring_mask;
+	__u32 ring_entries;
+	__u32 overflow;
+	__u32 cqes;
+	__u32 flags;
+	__u32 resv1;
+	__u64 user_addr;
+};
+
+/*
+ * cq_ring->flags
+ */
+
+/* disable eventfd notifications */
+#define IORING_CQ_EVENTFD_DISABLED	(1U << 0)
+
+/*
+ * io_uring_enter(2) flags
+ */
+#define IORING_ENTER_GETEVENTS		(1U << 0)
+#define IORING_ENTER_SQ_WAKEUP		(1U << 1)
+#define IORING_ENTER_SQ_WAIT		(1U << 2)
+#define IORING_ENTER_EXT_ARG		(1U << 3)
+#define IORING_ENTER_REGISTERED_RING	(1U << 4)
+
+/*
+ * Passed in for io_uring_setup(2). Copied back with updated info on success
+ */
+struct io_uring_params {
+	__u32 sq_entries;
+	__u32 cq_entries;
+	__u32 flags;
+	__u32 sq_thread_cpu;
+	__u32 sq_thread_idle;
+	__u32 features;
+	__u32 wq_fd;
+	__u32 resv[3];
+	struct io_sqring_offsets sq_off;
+	struct io_cqring_offsets cq_off;
+};
+
+/*
+ * io_uring_params->features flags
+ */
+#define IORING_FEAT_SINGLE_MMAP		(1U << 0)
+#define IORING_FEAT_NODROP		(1U << 1)
+#define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
+#define IORING_FEAT_RW_CUR_POS		(1U << 3)
+#define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
+#define IORING_FEAT_FAST_POLL		(1U << 5)
+#define IORING_FEAT_POLL_32BITS 	(1U << 6)
+#define IORING_FEAT_SQPOLL_NONFIXED	(1U << 7)
+#define IORING_FEAT_EXT_ARG		(1U << 8)
+#define IORING_FEAT_NATIVE_WORKERS	(1U << 9)
+#define IORING_FEAT_RSRC_TAGS		(1U << 10)
+#define IORING_FEAT_CQE_SKIP		(1U << 11)
+#define IORING_FEAT_LINKED_FILE		(1U << 12)
+#define IORING_FEAT_REG_REG_RING	(1U << 13)
+
+/*
+ * io_uring_register(2) opcodes and arguments
+ */
+enum {
+	IORING_REGISTER_BUFFERS			= 0,
+	IORING_UNREGISTER_BUFFERS		= 1,
+	IORING_REGISTER_FILES			= 2,
+	IORING_UNREGISTER_FILES			= 3,
+	IORING_REGISTER_EVENTFD			= 4,
+	IORING_UNREGISTER_EVENTFD		= 5,
+	IORING_REGISTER_FILES_UPDATE		= 6,
+	IORING_REGISTER_EVENTFD_ASYNC		= 7,
+	IORING_REGISTER_PROBE			= 8,
+	IORING_REGISTER_PERSONALITY		= 9,
+	IORING_UNREGISTER_PERSONALITY		= 10,
+	IORING_REGISTER_RESTRICTIONS		= 11,
+	IORING_REGISTER_ENABLE_RINGS		= 12,
+
+	/* extended with tagging */
+	IORING_REGISTER_FILES2			= 13,
+	IORING_REGISTER_FILES_UPDATE2		= 14,
+	IORING_REGISTER_BUFFERS2		= 15,
+	IORING_REGISTER_BUFFERS_UPDATE		= 16,
+
+	/* set/clear io-wq thread affinities */
+	IORING_REGISTER_IOWQ_AFF		= 17,
+	IORING_UNREGISTER_IOWQ_AFF		= 18,
+
+	/* set/get max number of io-wq workers */
+	IORING_REGISTER_IOWQ_MAX_WORKERS	= 19,
+
+	/* register/unregister io_uring fd with the ring */
+	IORING_REGISTER_RING_FDS		= 20,
+	IORING_UNREGISTER_RING_FDS		= 21,
+
+	/* register ring based provide buffer group */
+	IORING_REGISTER_PBUF_RING		= 22,
+	IORING_UNREGISTER_PBUF_RING		= 23,
+
+	/* sync cancelation API */
+	IORING_REGISTER_SYNC_CANCEL		= 24,
+
+	/* register a range of fixed file slots for automatic slot allocation */
+	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
+
+	/* this goes last */
+	IORING_REGISTER_LAST,
+
+	/* flag added to the opcode to use a registered ring fd */
+	IORING_REGISTER_USE_REGISTERED_RING	= 1U << 31
+};
+
+/* io-wq worker categories */
+enum {
+	IO_WQ_BOUND,
+	IO_WQ_UNBOUND,
+};
+
+/* deprecated, see struct io_uring_rsrc_update */
+struct io_uring_files_update {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 /* __s32 * */ fds;
+};
+
+/*
+ * Register a fully sparse file space, rather than pass in an array of all
+ * -1 file descriptors.
+ */
+#define IORING_RSRC_REGISTER_SPARSE	(1U << 0)
+
+struct io_uring_rsrc_register {
+	__u32 nr;
+	__u32 flags;
+	__u64 resv2;
+	__aligned_u64 data;
+	__aligned_u64 tags;
+};
+
+struct io_uring_rsrc_update {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 data;
+};
+
+struct io_uring_rsrc_update2 {
+	__u32 offset;
+	__u32 resv;
+	__aligned_u64 data;
+	__aligned_u64 tags;
+	__u32 nr;
+	__u32 resv2;
+};
+
+/* Skip updating fd indexes set to this value in the fd table */
+#define IORING_REGISTER_FILES_SKIP	(-2)
+
+#define IO_URING_OP_SUPPORTED	(1U << 0)
+
+struct io_uring_probe_op {
+	__u8 op;
+	__u8 resv;
+	__u16 flags;	/* IO_URING_OP_* flags */
+	__u32 resv2;
+};
+
+struct io_uring_probe {
+	__u8 last_op;	/* last opcode supported */
+	__u8 ops_len;	/* length of ops[] array below */
+	__u16 resv;
+	__u32 resv2[3];
+	struct io_uring_probe_op ops[];
+};
+
+struct io_uring_restriction {
+	__u16 opcode;
+	union {
+		__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
+		__u8 sqe_op;      /* IORING_RESTRICTION_SQE_OP */
+		__u8 sqe_flags;   /* IORING_RESTRICTION_SQE_FLAGS_* */
+	};
+	__u8 resv;
+	__u32 resv2[3];
+};
+
+struct io_uring_buf {
+	__u64	addr;
+	__u32	len;
+	__u16	bid;
+	__u16	resv;
+};
+
+struct io_uring_buf_ring {
+	union {
+		/*
+		 * To avoid spilling into more pages than we need to, the
+		 * ring tail is overlaid with the io_uring_buf->resv field.
+		 */
+		struct {
+			__u64	resv1;
+			__u32	resv2;
+			__u16	resv3;
+			__u16	tail;
+		};
+		__DECLARE_FLEX_ARRAY(struct io_uring_buf, bufs);
+	};
+};
+
+/*
+ * Flags for IORING_REGISTER_PBUF_RING.
+ *
+ * IOU_PBUF_RING_MMAP:	If set, kernel will allocate the memory for the ring.
+ *			The application must not set a ring_addr in struct
+ *			io_uring_buf_reg, instead it must subsequently call
+ *			mmap(2) with the offset set as:
+ *			IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT)
+ *			to get a virtual mapping for the ring.
+ */
+enum {
+	IOU_PBUF_RING_MMAP	= 1,
+};
+
+/* argument for IORING_(UN)REGISTER_PBUF_RING */
+struct io_uring_buf_reg {
+	__u64	ring_addr;
+	__u32	ring_entries;
+	__u16	bgid;
+	__u16	flags;
+	__u64	resv[3];
+};
+
+/*
+ * io_uring_restriction->opcode values
+ */
+enum {
+	/* Allow an io_uring_register(2) opcode */
+	IORING_RESTRICTION_REGISTER_OP		= 0,
+
+	/* Allow an sqe opcode */
+	IORING_RESTRICTION_SQE_OP		= 1,
+
+	/* Allow sqe flags */
+	IORING_RESTRICTION_SQE_FLAGS_ALLOWED	= 2,
+
+	/* Require sqe flags (these flags must be set on each submission) */
+	IORING_RESTRICTION_SQE_FLAGS_REQUIRED	= 3,
+
+	IORING_RESTRICTION_LAST
+};
+
+struct io_uring_getevents_arg {
+	__u64	sigmask;
+	__u32	sigmask_sz;
+	__u32	pad;
+	__u64	ts;
+};
+
+/*
+ * Argument for IORING_REGISTER_SYNC_CANCEL
+ */
+struct io_uring_sync_cancel_reg {
+	__u64				addr;
+	__s32				fd;
+	__u32				flags;
+	struct __kernel_timespec	timeout;
+	__u8				opcode;
+	__u8				pad[7];
+	__u64				pad2[3];
+};
+
+/*
+ * Argument for IORING_REGISTER_FILE_ALLOC_RANGE
+ * The range is specified as [off, off + len)
+ */
+struct io_uring_file_index_range {
+	__u32	off;
+	__u32	len;
+	__u64	resv;
+};
+
+struct io_uring_recvmsg_out {
+	__u32 namelen;
+	__u32 controllen;
+	__u32 payloadlen;
+	__u32 flags;
+};
+
+/*
+ * Argument for IORING_OP_URING_CMD when file is a socket
+ */
+enum {
+	SOCKET_URING_OP_SIOCINQ		= 0,
+	SOCKET_URING_OP_SIOCOUTQ,
+	SOCKET_URING_OP_GETSOCKOPT,
+	SOCKET_URING_OP_SETSOCKOPT,
+};
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f089ab290978..211b86de35ac 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -264,6 +264,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_SBI        35
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
+#define KVM_EXIT_LOONGARCH_IOCSR  38
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -336,6 +337,13 @@ struct kvm_run {
 			__u32 len;
 			__u8  is_write;
 		} mmio;
+		/* KVM_EXIT_LOONGARCH_IOCSR */
+		struct {
+			__u64 phys_addr;
+			__u8  data[8];
+			__u32 len;
+			__u8  is_write;
+		} iocsr_io;
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -1192,6 +1200,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_COUNTER_OFFSET 227
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1362,6 +1371,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
 #define KVM_REG_RISCV		0x8000000000000000ULL
+#define KVM_REG_LOONGARCH	0x9000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
@@ -1418,9 +1428,16 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define  KVM_DEV_VFIO_GROUP			1
-#define   KVM_DEV_VFIO_GROUP_ADD			1
-#define   KVM_DEV_VFIO_GROUP_DEL			2
+#define  KVM_DEV_VFIO_FILE			1
+
+#define   KVM_DEV_VFIO_FILE_ADD			1
+#define   KVM_DEV_VFIO_FILE_DEL			2
+
+/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */
+#define  KVM_DEV_VFIO_GROUP	KVM_DEV_VFIO_FILE
+
+#define   KVM_DEV_VFIO_GROUP_ADD	KVM_DEV_VFIO_FILE_ADD
+#define   KVM_DEV_VFIO_GROUP_DEL	KVM_DEV_VFIO_FILE_DEL
 #define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
@@ -1555,6 +1572,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
 /* Available with KVM_CAP_COUNTER_OFFSET */
 #define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
+#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO,  0xb6, struct reg_mask_range)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 8eb0d7b758d2..bb242fdcfe6b 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -100,8 +100,9 @@ enum fsconfig_command {
 	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
 	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
 	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
-	FSCONFIG_CMD_CREATE	= 6,	/* Invoke superblock creation */
+	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
 	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
 };
 
 /*
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index c1634b95c223..2943a151d4f1 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -38,11 +38,27 @@ enum netdev_xdp_act {
 	NETDEV_XDP_ACT_MASK = 127,
 };
 
+/**
+ * enum netdev_xdp_rx_metadata
+ * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW
+ *   timestamp via bpf_xdp_metadata_rx_timestamp().
+ * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
+ *   hash via bpf_xdp_metadata_rx_hash().
+ */
+enum netdev_xdp_rx_metadata {
+	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
+	NETDEV_XDP_RX_METADATA_HASH = 2,
+
+	/* private: */
+	NETDEV_XDP_RX_METADATA_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 3c36aeade991..370ed14b1ae0 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -283,7 +283,8 @@ struct prctl_mm_map {
 
 /* Memory deny write / execute */
 #define PR_SET_MDWE			65
-# define PR_MDWE_REFUSE_EXEC_GAIN	1
+# define PR_MDWE_REFUSE_EXEC_GAIN	(1UL << 0)
+# define PR_MDWE_NO_INHERIT		(1UL << 1)
 
 #define PR_GET_MDWE			66
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index f5c48b61ab62..649560c685f1 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -219,4 +219,12 @@
  */
 #define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
 
+/* Get the group for the descriptor table including driver & device areas
+ * of a virtqueue: read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group ID of the descriptor table for this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
 #endif