summaryrefslogtreecommitdiff
path: root/tools/include/uapi/linux
diff options
context:
space:
mode:
Diffstat (limited to 'tools/include/uapi/linux')
-rw-r--r--tools/include/uapi/linux/acct.h128
-rw-r--r--tools/include/uapi/linux/bpf.h154
-rw-r--r--tools/include/uapi/linux/btf.h38
-rw-r--r--tools/include/uapi/linux/const.h18
-rw-r--r--tools/include/uapi/linux/fadvise.h22
-rw-r--r--tools/include/uapi/linux/fs.h1
-rw-r--r--tools/include/uapi/linux/fscrypt.h1
-rw-r--r--tools/include/uapi/linux/if_link.h2
-rw-r--r--tools/include/uapi/linux/if_tun.h4
-rw-r--r--tools/include/uapi/linux/if_xdp.h1
-rw-r--r--tools/include/uapi/linux/kvm.h30
-rw-r--r--tools/include/uapi/linux/module_signature.h41
-rw-r--r--tools/include/uapi/linux/mount.h14
-rw-r--r--tools/include/uapi/linux/netdev.h14
-rw-r--r--tools/include/uapi/linux/openat2.h43
-rw-r--r--tools/include/uapi/linux/rtnetlink.h1
-rw-r--r--tools/include/uapi/linux/stddef.h26
-rw-r--r--tools/include/uapi/linux/taskstats.h291
-rw-r--r--tools/include/uapi/linux/userfaultfd.h54
19 files changed, 822 insertions, 61 deletions
diff --git a/tools/include/uapi/linux/acct.h b/tools/include/uapi/linux/acct.h
new file mode 100644
index 000000000000..1e2382ed4fd5
--- /dev/null
+++ b/tools/include/uapi/linux/acct.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * BSD Process Accounting for Linux - Definitions
+ *
+ * Author: Marco van Wieringen (mvw@planets.elm.net)
+ *
+ * This header file contains the definitions needed to implement
+ * BSD-style process accounting. The kernel accounting code and all
+ * user-level programs that try to do something useful with the
+ * process accounting log must include this file.
+ *
+ * Copyright (C) 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V.
+ *
+ */
+
+#ifndef _UAPI_LINUX_ACCT_H
+#define _UAPI_LINUX_ACCT_H
+
+#include <linux/types.h>
+
+#include <asm/param.h>
+#include <asm/byteorder.h>
+
+/*
+ * comp_t is a 16-bit "floating" point number with a 3-bit base 8
+ * exponent and a 13-bit fraction.
+ * comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction
+ * (leading 1 not stored).
+ * See linux/kernel/acct.c for the specific encoding systems used.
+ */
+
+typedef __u16 comp_t;
+typedef __u32 comp2_t;
+
+/*
+ * accounting file record
+ *
+ * This structure contains all of the information written out to the
+ * process accounting file whenever a process exits.
+ */
+
+#define ACCT_COMM 16
+
+struct acct
+{
+ char ac_flag; /* Flags */
+ char ac_version; /* Always set to ACCT_VERSION */
+ /* for binary compatibility back until 2.0 */
+ __u16 ac_uid16; /* LSB of Real User ID */
+ __u16 ac_gid16; /* LSB of Real Group ID */
+ __u16 ac_tty; /* Control Terminal */
+ /* __u32 range means times from 1970 to 2106 */
+ __u32 ac_btime; /* Process Creation Time */
+ comp_t ac_utime; /* User Time */
+ comp_t ac_stime; /* System Time */
+ comp_t ac_etime; /* Elapsed Time */
+ comp_t ac_mem; /* Average Memory Usage */
+ comp_t ac_io; /* Chars Transferred */
+ comp_t ac_rw; /* Blocks Read or Written */
+ comp_t ac_minflt; /* Minor Pagefaults */
+ comp_t ac_majflt; /* Major Pagefaults */
+ comp_t ac_swaps; /* Number of Swaps */
+/* m68k had no padding here. */
+#if !defined(CONFIG_M68K) || !defined(__KERNEL__)
+ __u16 ac_ahz; /* AHZ */
+#endif
+ __u32 ac_exitcode; /* Exitcode */
+ char ac_comm[ACCT_COMM + 1]; /* Command Name */
+ __u8 ac_etime_hi; /* Elapsed Time MSB */
+ __u16 ac_etime_lo; /* Elapsed Time LSB */
+ __u32 ac_uid; /* Real User ID */
+ __u32 ac_gid; /* Real Group ID */
+};
+
+struct acct_v3
+{
+ char ac_flag; /* Flags */
+ char ac_version; /* Always set to ACCT_VERSION */
+ __u16 ac_tty; /* Control Terminal */
+ __u32 ac_exitcode; /* Exitcode */
+ __u32 ac_uid; /* Real User ID */
+ __u32 ac_gid; /* Real Group ID */
+ __u32 ac_pid; /* Process ID */
+ __u32 ac_ppid; /* Parent Process ID */
+ /* __u32 range means times from 1970 to 2106 */
+ __u32 ac_btime; /* Process Creation Time */
+#ifdef __KERNEL__
+ __u32 ac_etime; /* Elapsed Time */
+#else
+ float ac_etime; /* Elapsed Time */
+#endif
+ comp_t ac_utime; /* User Time */
+ comp_t ac_stime; /* System Time */
+ comp_t ac_mem; /* Average Memory Usage */
+ comp_t ac_io; /* Chars Transferred */
+ comp_t ac_rw; /* Blocks Read or Written */
+ comp_t ac_minflt; /* Minor Pagefaults */
+ comp_t ac_majflt; /* Major Pagefaults */
+ comp_t ac_swaps; /* Number of Swaps */
+ char ac_comm[ACCT_COMM]; /* Command Name */
+};
+
+/*
+ * accounting flags
+ */
+ /* bit set when the process/task ... */
+#define AFORK 0x01 /* ... executed fork, but did not exec */
+#define ASU 0x02 /* ... used super-user privileges */
+#define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */
+#define ACORE 0x08 /* ... dumped core */
+#define AXSIG 0x10 /* ... was killed by a signal */
+#define AGROUP 0x20 /* ... was the last task of the process (task group) */
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+#define ACCT_BYTEORDER 0x80 /* accounting file is big endian */
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+#define ACCT_BYTEORDER 0x00 /* accounting file is little endian */
+#else
+#error unspecified endianness
+#endif
+
+#ifndef __KERNEL__
+#define ACCT_VERSION 2
+#define AHZ (HZ)
+#endif /* __KERNEL */
+
+
+#endif /* _UAPI_LINUX_ACCT_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 5e38b4887de6..732b35cc08d1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -994,6 +994,7 @@ enum bpf_cmd {
BPF_PROG_STREAM_READ_BY_FD,
BPF_PROG_ASSOC_STRUCT_OPS,
__MAX_BPF_CMD,
+ BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */
};
enum bpf_map_type {
@@ -1046,6 +1047,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_CGRP_STORAGE,
BPF_MAP_TYPE_ARENA,
BPF_MAP_TYPE_INSN_ARRAY,
+ BPF_MAP_TYPE_RHASH,
__MAX_BPF_MAP_TYPE
};
@@ -1154,6 +1156,9 @@ enum bpf_attach_type {
BPF_TRACE_KPROBE_SESSION,
BPF_TRACE_UPROBE_SESSION,
BPF_TRACE_FSESSION,
+ BPF_TRACE_FENTRY_MULTI,
+ BPF_TRACE_FEXIT_MULTI,
+ BPF_TRACE_FSESSION_MULTI,
__MAX_BPF_ATTACH_TYPE
};
@@ -1178,6 +1183,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_UPROBE_MULTI = 12,
BPF_LINK_TYPE_NETKIT = 13,
BPF_LINK_TYPE_SOCKMAP = 14,
+ BPF_LINK_TYPE_TRACING_MULTI = 15,
__MAX_BPF_LINK_TYPE,
};
@@ -1321,7 +1327,11 @@ enum {
* BPF_TRACE_UPROBE_MULTI attach type to create return probe.
*/
enum {
- BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+ /* Get return uprobe. */
+ BPF_F_UPROBE_MULTI_RETURN = (1U << 0),
+
+ /* Get path from provided path_fd. */
+ BPF_F_UPROBE_MULTI_PATH_FD = (1U << 1),
};
/* link_create.netfilter.flags used in LINK_CREATE command for
@@ -1500,6 +1510,13 @@ struct bpf_stack_build_id {
};
};
+struct bpf_common_attr {
+ __aligned_u64 log_buf;
+ __u32 log_size;
+ __u32 log_level;
+ __u32 log_true_size;
+};
+
#define BPF_OBJ_NAME_LEN 16U
enum {
@@ -1537,6 +1554,11 @@ union bpf_attr {
*
* BPF_MAP_TYPE_ARENA - contains the address where user space
* is going to mmap() the arena. It has to be page aligned.
+ *
+ * BPF_MAP_TYPE_RHASH - initial table size hint
+ * (nelem_hint). 0 = use rhashtable default. Must be
+ * <= min(max_entries, U16_MAX). Upper 32 bits reserved,
+ * must be zero.
*/
__u64 map_extra;
@@ -1846,6 +1868,7 @@ union bpf_attr {
__u32 cnt;
__u32 flags;
__u32 pid;
+ __u32 path_fd;
} uprobe_multi;
struct {
union {
@@ -1861,6 +1884,11 @@ union bpf_attr {
};
__u64 expected_revision;
} cgroup;
+ struct {
+ __aligned_u64 ids;
+ __aligned_u64 cookies;
+ __u32 cnt;
+ } tracing_multi;
};
} link_create;
@@ -3010,8 +3038,34 @@ union bpf_attr {
*
* * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
* **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
- * Indicate the new IP header version after decapsulating the outer
- * IP header. Used when the inner and outer IP versions are different.
+ * Indicate the new IP header version after decapsulating the
+ * outer IP header. Used when the inner and outer IP versions
+ * are different. These flags only trigger a protocol change
+ * without clearing any tunnel-specific GSO flags.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_L4_GRE**:
+ * Clear GRE tunnel GSO flags (SKB_GSO_GRE and SKB_GSO_GRE_CSUM)
+ * when decapsulating a GRE tunnel.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_L4_UDP**:
+ * Clear UDP tunnel GSO flags (SKB_GSO_UDP_TUNNEL and
+ * SKB_GSO_UDP_TUNNEL_CSUM) when decapsulating a UDP tunnel.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_IPXIP4**:
+ * Clear IPIP/SIT tunnel GSO flag (SKB_GSO_IPXIP4) when decapsulating
+ * a tunnel with an outer IPv4 header (IPv4-in-IPv4 or IPv6-in-IPv4).
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_IPXIP6**:
+ * Clear IPv6 encapsulation tunnel GSO flag (SKB_GSO_IPXIP6) when
+ * decapsulating a tunnel with an outer IPv6 header (IPv6-in-IPv6
+ * or IPv4-in-IPv6).
+ *
+ * When using the decapsulation flags above, the skb->encapsulation
+ * flag is automatically cleared if all tunnel-specific GSO flags
+ * (SKB_GSO_UDP_TUNNEL, SKB_GSO_UDP_TUNNEL_CSUM, SKB_GSO_GRE,
+ * SKB_GSO_GRE_CSUM, SKB_GSO_IPXIP4, SKB_GSO_IPXIP6) have been
+ * removed from the packet. This handles cases where all tunnel
+ * layers have been decapsulated.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
@@ -3504,6 +3558,47 @@ union bpf_attr {
* Use the mark present in *params*->mark for the fib lookup.
* This option should not be used with BPF_FIB_LOOKUP_DIRECT,
* as it only has meaning for full lookups.
+ * **BPF_FIB_LOOKUP_VLAN**
+ * If the fib lookup resolves to a VLAN device whose
+ * parent is a real (non-VLAN) device, set
+ * *params*->h_vlan_proto and *params*->h_vlan_TCI from
+ * the VLAN device and replace *params*->ifindex with the
+ * parent's ifindex. *params*->h_vlan_TCI carries the VID
+ * only, with PCP and DEI bits zero; a consumer wanting to
+ * set egress priority writes PCP itself. *params*->smac is
+ * the VLAN device's own address, which can differ from the
+ * parent's. Only the immediate parent is resolved; if it
+ * is itself a VLAN device (QinQ) or in another namespace,
+ * the egress cannot be reduced to a physical device plus
+ * one tag and the lookup returns
+ * **BPF_FIB_LKUP_RET_VLAN_FAILURE** with *params*->ifindex
+ * left at the input. To obtain the VLAN device's own
+ * ifindex, repeat the lookup without
+ * **BPF_FIB_LOOKUP_VLAN**, re-initializing *params*
+ * first: output fields overwrite the inputs they share
+ * storage with. The swap and the vlan fields
+ * are written only on success; other output fields keep
+ * the helper's existing behaviour, so a frag-needed result
+ * still reports the route mtu in *params*->mtu_result.
+ * This flag is only valid for XDP programs; tc programs
+ * receive -EINVAL since they can redirect to the VLAN
+ * device directly.
+ * **BPF_FIB_LOOKUP_VLAN_INPUT**
+ * Treat *params*->h_vlan_proto and *params*->h_vlan_TCI
+ * as an input VLAN tag and run the lookup as if ingress
+ * had happened on the VLAN subinterface carrying that tag
+ * on *params*->ifindex. The VID is the low 12 bits of
+ * *params*->h_vlan_TCI; *params*->h_vlan_proto must be
+ * ETH_P_8021Q or ETH_P_8021AD in network byte order, else
+ * **-EINVAL**. If *params*->ifindex is itself a VLAN
+ * device, its inner (QinQ) subinterface is matched; for a
+ * bond or team, pass the master's ifindex. An unmatched
+ * tag, a down device, or one in another namespace returns
+ * **BPF_FIB_LKUP_RET_NOT_FWDED**, mirroring real ingress.
+ * A VID of 0 is looked up literally, so do not set this
+ * flag for priority-tagged frames. Cannot be combined with
+ * **BPF_FIB_LOOKUP_TBID** or **BPF_FIB_LOOKUP_OUTPUT**
+ * (returns **-EINVAL**).
*
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
@@ -4645,7 +4740,9 @@ union bpf_attr {
* Description
* Discard reserved ring buffer sample, pointed to by *data*.
* If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
- * of new data availability is sent.
+ * of new data availability is sent. Discarded records remain in
+ * the ring buffer until consumed by user space, so a later submit
+ * using adaptive wakeup might not wake up the consumer.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
@@ -4664,6 +4761,7 @@ union bpf_attr {
* * **BPF_RB_RING_SIZE**: The size of ring buffer.
* * **BPF_RB_CONS_POS**: Consumer position (can wrap around).
* * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around).
+ * * **BPF_RB_OVERWRITE_POS**: Overwrite position (can wrap around).
*
* Data returned is just a momentary snapshot of actual values
* and could be inaccurate, so this facility should be used to
@@ -5049,17 +5147,19 @@ union bpf_attr {
* Description
* Redirect the packet to another net device of index *ifindex*.
* This helper is somewhat similar to **bpf_redirect**\ (), except
- * that the redirection happens to the *ifindex*' peer device and
- * the netns switch takes place from ingress to ingress without
- * going through the CPU's backlog queue.
+ * that the redirection happens to the *ifindex*' peer device. If
+ * *flags* is 0, the netns switch takes place from ingress to
+ * ingress without going through the CPU's backlog queue. If the
+ * **BPF_F_EGRESS** flag is provided then redirection happens in
+ * the egress direction of the peer device.
*
* *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
* the netns switch.
*
- * The *flags* argument is reserved and must be 0. The helper is
- * currently only supported for tc BPF program types at the
- * ingress hook and for veth and netkit target device types. The
- * peer device must reside in a different network namespace.
+ * If the *flags* argument is 0, the helper is currently only
+ * supported for tc BPF program types at the ingress hook and for
+ * veth and netkit target device types. The peer device must reside
+ * in a different network namespace.
* Return
* The helper returns **TC_ACT_REDIRECT** on success or
* **TC_ACT_SHOT** on error.
@@ -6209,7 +6309,7 @@ enum {
};
/* BPF_FUNC_skb_adjust_room flags. */
-enum {
+enum bpf_adj_room_flags {
BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1),
BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
@@ -6219,6 +6319,10 @@ enum {
BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7),
BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8),
+ BPF_F_ADJ_ROOM_DECAP_L4_GRE = (1ULL << 9),
+ BPF_F_ADJ_ROOM_DECAP_L4_UDP = (1ULL << 10),
+ BPF_F_ADJ_ROOM_DECAP_IPXIP4 = (1ULL << 11),
+ BPF_F_ADJ_ROOM_DECAP_IPXIP6 = (1ULL << 12),
};
enum {
@@ -6306,9 +6410,10 @@ enum {
/* Flags for bpf_redirect and bpf_redirect_map helpers */
enum {
BPF_F_INGRESS = (1ULL << 0), /* used for skb path */
+ BPF_F_EGRESS = (1ULL << 1), /* used for skb path */
BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */
BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */
-#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
+#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_EGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
};
#define __bpf_md_ptr(type, name) \
@@ -6696,6 +6801,7 @@ struct bpf_prog_info {
__u32 verified_insns;
__u32 attach_btf_obj_id;
__u32 attach_btf_id;
+ __u32 :32;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -6717,6 +6823,7 @@ struct bpf_map_info {
__u64 map_extra;
__aligned_u64 hash;
__u32 hash_size;
+ __u32 :32;
} __attribute__((aligned(8)));
struct bpf_btf_info {
@@ -6808,6 +6915,15 @@ struct bpf_link_info {
__u32 pid;
} uprobe_multi;
struct {
+ __u32 attach_type;
+ __u32 count; /* in/out: tracing_multi target count */
+ __u32 btf_obj_id;
+ __u32 :32;
+ __aligned_u64 ids;
+ __aligned_u64 addrs;
+ __aligned_u64 cookies;
+ } tracing_multi;
+ struct {
__u32 type; /* enum bpf_perf_event_type */
__u32 :32;
union {
@@ -7234,6 +7350,7 @@ enum {
TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */
SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */
+
};
enum {
@@ -7294,6 +7411,8 @@ enum {
BPF_FIB_LOOKUP_TBID = (1U << 3),
BPF_FIB_LOOKUP_SRC = (1U << 4),
BPF_FIB_LOOKUP_MARK = (1U << 5),
+ BPF_FIB_LOOKUP_VLAN = (1U << 6),
+ BPF_FIB_LOOKUP_VLAN_INPUT = (1U << 7),
};
enum {
@@ -7307,6 +7426,7 @@ enum {
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 */
+ BPF_FIB_LKUP_RET_VLAN_FAILURE, /* VLAN egress, parent unresolvable */
};
struct bpf_fib_lookup {
@@ -7360,7 +7480,13 @@ struct bpf_fib_lookup {
union {
struct {
- /* output */
+ /*
+ * output with BPF_FIB_LOOKUP_VLAN: set from the
+ * resolved egress VLAN device (see the flag); zeroed
+ * on other successful lookups. input with
+ * BPF_FIB_LOOKUP_VLAN_INPUT: the VLAN tag to scope
+ * the lookup by.
+ */
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
};
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 266d4ffa6c07..618167cab4e6 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -8,6 +8,16 @@
#define BTF_MAGIC 0xeB9F
#define BTF_VERSION 1
+/*
+ * BTF layout section consists of a struct btf_layout for each known
+ * kind at BTF encoding time.
+ */
+struct btf_layout {
+ __u8 info_sz; /* size of singular element after btf_type */
+ __u8 elem_sz; /* size of each of btf_vlen(t) elements */
+ __u16 flags; /* currently unused */
+};
+
struct btf_header {
__u16 magic;
__u8 version;
@@ -19,22 +29,26 @@ struct btf_header {
__u32 type_len; /* length of type section */
__u32 str_off; /* offset of string section */
__u32 str_len; /* length of string section */
+ __u32 layout_off; /* offset of layout section */
+ __u32 layout_len; /* length of layout section */
};
-/* Max # of type identifier */
-#define BTF_MAX_TYPE 0x000fffff
-/* Max offset into the string section */
-#define BTF_MAX_NAME_OFFSET 0x00ffffff
-/* Max # of struct/union/enum members or func args */
-#define BTF_MAX_VLEN 0xffff
+enum btf_max {
+ /* Max possible kind */
+ BTF_MAX_KIND = 0x0000007f,
+ /* Max # of type identifier */
+ BTF_MAX_TYPE = 0x000fffff,
+ /* Max offset into the string section */
+ BTF_MAX_NAME_OFFSET = 0x00ffffff,
+ /* Max # of struct/union/enum members or func args */
+ BTF_MAX_VLEN = 0x00ffffff,
+};
struct btf_type {
__u32 name_off;
/* "info" bits arrangement
- * bits 0-15: vlen (e.g. # of struct's members)
- * bits 16-23: unused
- * bits 24-28: kind (e.g. int, ptr, array...etc)
- * bits 29-30: unused
+ * bits 0-23: vlen (e.g. # of struct's members)
+ * bits 24-30: kind (e.g. int, ptr, array...etc)
* bit 31: kind_flag, currently used by
* struct, union, enum, fwd, enum64,
* decl_tag and type_tag
@@ -53,8 +67,8 @@ struct btf_type {
};
};
-#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
-#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x7f)
+#define BTF_INFO_VLEN(info) ((info) & 0xffffff)
#define BTF_INFO_KFLAG(info) ((info) >> 31)
enum {
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index b8f629ef135f..565f309b9df8 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -50,4 +50,22 @@
#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+/*
+ * Divide positive or negative dividend by positive or negative divisor
+ * and round to closest integer. Result is undefined for negative
+ * divisors if the dividend variable type is unsigned and for negative
+ * dividends if the divisor variable type is unsigned.
+ */
+#define __KERNEL_DIV_ROUND_CLOSEST(x, divisor) \
+({ \
+ __typeof__(x) __x = x; \
+ __typeof__(divisor) __d = divisor; \
+ \
+ (((__typeof__(x))-1) > 0 || \
+ ((__typeof__(divisor))-1) > 0 || \
+ (((__x) > 0) == ((__d) > 0))) ? \
+ (((__x) + ((__d) / 2)) / (__d)) : \
+ (((__x) - ((__d) / 2)) / (__d)); \
+})
+
#endif /* _UAPI_LINUX_CONST_H */
diff --git a/tools/include/uapi/linux/fadvise.h b/tools/include/uapi/linux/fadvise.h
deleted file mode 100644
index 0862b87434c2..000000000000
--- a/tools/include/uapi/linux/fadvise.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef FADVISE_H_INCLUDED
-#define FADVISE_H_INCLUDED
-
-#define POSIX_FADV_NORMAL 0 /* No further special treatment. */
-#define POSIX_FADV_RANDOM 1 /* Expect random page references. */
-#define POSIX_FADV_SEQUENTIAL 2 /* Expect sequential page references. */
-#define POSIX_FADV_WILLNEED 3 /* Will need these pages. */
-
-/*
- * The advise values for POSIX_FADV_DONTNEED and POSIX_ADV_NOREUSE
- * for s390-64 differ from the values for the rest of the world.
- */
-#if defined(__s390x__)
-#define POSIX_FADV_DONTNEED 6 /* Don't need these pages. */
-#define POSIX_FADV_NOREUSE 7 /* Data will be accessed once. */
-#else
-#define POSIX_FADV_DONTNEED 4 /* Don't need these pages. */
-#define POSIX_FADV_NOREUSE 5 /* Data will be accessed once. */
-#endif
-
-#endif /* FADVISE_H_INCLUDED */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 24ddf7bc4f25..f0a26309b6d5 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -364,6 +364,7 @@ typedef int __bitwise __kernel_rwf_t;
#define PAGE_IS_HUGE (1 << 6)
#define PAGE_IS_SOFT_DIRTY (1 << 7)
#define PAGE_IS_GUARD (1 << 8)
+#define PAGE_IS_ACCESSED (1 << 9)
/*
* struct page_region - Page region with flags
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 3aff99f2696a..84507280b3ea 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -30,7 +30,6 @@
#define FSCRYPT_MODE_SM4_CTS 8
#define FSCRYPT_MODE_ADIANTUM 9
#define FSCRYPT_MODE_AES_256_HCTR2 10
-/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
/*
* Legacy policy version; ad-hoc KDF and no key verification.
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 7e46ca4cd31b..757ce5e9426e 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -1526,6 +1526,8 @@ enum {
IFLA_BOND_MISSED_MAX,
IFLA_BOND_NS_IP6_TARGET,
IFLA_BOND_COUPLED_CONTROL,
+ IFLA_BOND_BROADCAST_NEIGH,
+ IFLA_BOND_LACP_STRICT,
__IFLA_BOND_MAX,
};
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
index 2ec07de1d73b..2c85525704c1 100644
--- a/tools/include/uapi/linux/if_tun.h
+++ b/tools/include/uapi/linux/if_tun.h
@@ -67,6 +67,10 @@
#define IFF_TAP 0x0002
#define IFF_NAPI 0x0010
#define IFF_NAPI_FRAGS 0x0020
+/* Stop the queue instead of dropping when the internal ring is full, so an
+ * attached qdisc applies backpressure instead of being bypassed.
+ */
+#define IFF_BACKPRESSURE 0x0080
#define IFF_NO_PI 0x1000
/* This flag has no real effect */
#define IFF_ONE_QUEUE 0x2000
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 23a062781468..50d67df78911 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -149,6 +149,7 @@ struct xsk_tx_metadata {
__u16 csum_start;
/* Offset from csum_start where checksum should be stored. */
__u16 csum_offset;
+ __u32 reserved;
/* XDP_TXMD_FLAGS_LAUNCH_TIME */
/* Launch time in nanosecond against the PTP HW Clock */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 65500f5db379..419011097fa8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -11,9 +11,14 @@
#include <linux/const.h>
#include <linux/types.h>
#include <linux/compiler.h>
+#include <linux/stddef.h>
#include <linux/ioctl.h>
#include <asm/kvm.h>
+#ifdef __KERNEL__
+#include <linux/kvm_types.h>
+#endif
+
#define KVM_API_VERSION 12
/*
@@ -538,7 +543,7 @@ struct kvm_coalesced_mmio {
struct kvm_coalesced_mmio_ring {
__u32 first, last;
- struct kvm_coalesced_mmio coalesced_mmio[];
+ __DECLARE_FLEX_ARRAY(struct kvm_coalesced_mmio, coalesced_mmio);
};
#define KVM_COALESCED_MMIO_MAX \
@@ -588,7 +593,7 @@ struct kvm_clear_dirty_log {
/* for KVM_SET_SIGNAL_MASK */
struct kvm_signal_mask {
__u32 len;
- __u8 sigset[];
+ __DECLARE_FLEX_ARRAY(__u8, sigset);
};
/* for KVM_TPR_ACCESS_REPORTING */
@@ -699,6 +704,11 @@ struct kvm_enable_cap {
#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK 0xffULL
#define KVM_VM_TYPE_ARM_IPA_SIZE(x) \
((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+
+#define KVM_VM_TYPE_ARM_PROTECTED (1UL << 31)
+#define KVM_VM_TYPE_ARM_MASK (KVM_VM_TYPE_ARM_IPA_SIZE_MASK | \
+ KVM_VM_TYPE_ARM_PROTECTED)
+
/*
* ioctls for /dev/kvm fds:
*/
@@ -985,6 +995,8 @@ struct kvm_enable_cap {
#define KVM_CAP_ARM_SEA_TO_USER 245
#define KVM_CAP_S390_USER_OPEREXEC 246
#define KVM_CAP_S390_KEYOP 247
+#define KVM_CAP_S390_VSIE_ESAMODE 248
+#define KVM_CAP_S390_HPAGE_2G 249
struct kvm_irq_routing_irqchip {
__u32 irqchip;
@@ -1047,7 +1059,7 @@ struct kvm_irq_routing_entry {
struct kvm_irq_routing {
__u32 nr;
__u32 flags;
- struct kvm_irq_routing_entry entries[];
+ __DECLARE_FLEX_ARRAY(struct kvm_irq_routing_entry, entries);
};
#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
@@ -1138,7 +1150,7 @@ struct kvm_dirty_tlb {
struct kvm_reg_list {
__u64 n; /* number of regs */
- __u64 reg[];
+ __DECLARE_FLEX_ARRAY(__u64, reg);
};
struct kvm_one_reg {
@@ -1220,6 +1232,10 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC
KVM_DEV_TYPE_LOONGARCH_PCHPIC,
#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC
+ KVM_DEV_TYPE_LOONGARCH_DMSINTC,
+#define KVM_DEV_TYPE_LOONGARCH_DMSINTC KVM_DEV_TYPE_LOONGARCH_DMSINTC
+ KVM_DEV_TYPE_ARM_VGIC_V5,
+#define KVM_DEV_TYPE_ARM_VGIC_V5 KVM_DEV_TYPE_ARM_VGIC_V5
KVM_DEV_TYPE_MAX,
@@ -1601,7 +1617,11 @@ struct kvm_stats_desc {
__u16 size;
__u32 offset;
__u32 bucket_size;
- char name[];
+#ifdef __KERNEL__
+ char name[KVM_STATS_NAME_SIZE];
+#else
+ __DECLARE_FLEX_ARRAY(char, name);
+#endif
};
#define KVM_GET_STATS_FD _IO(KVMIO, 0xce)
diff --git a/tools/include/uapi/linux/module_signature.h b/tools/include/uapi/linux/module_signature.h
new file mode 100644
index 000000000000..634c9f1c8fc2
--- /dev/null
+++ b/tools/include/uapi/linux/module_signature.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Module signature handling.
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _UAPI_LINUX_MODULE_SIGNATURE_H
+#define _UAPI_LINUX_MODULE_SIGNATURE_H
+
+#include <linux/types.h>
+
+/* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */
+#define MODULE_SIGNATURE_MARKER "~Module signature appended~\n"
+
+enum module_signature_type {
+ MODULE_SIGNATURE_TYPE_PKCS7 = 2, /* Signature in PKCS#7 message */
+};
+
+/*
+ * Module signature information block.
+ *
+ * The constituents of the signature section are, in order:
+ *
+ * - Signer's name
+ * - Key identifier
+ * - Signature data
+ * - Information block
+ */
+struct module_signature {
+ __u8 algo; /* Public-key crypto algorithm [0] */
+ __u8 hash; /* Digest algorithm [0] */
+ __u8 id_type; /* Key identifier type [enum module_signature_type] */
+ __u8 signer_len; /* Length of signer's name [0] */
+ __u8 key_id_len; /* Length of key identifier [0] */
+ __u8 __pad[3];
+ __be32 sig_len; /* Length of signature data */
+};
+
+#endif /* _UAPI_LINUX_MODULE_SIGNATURE_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 7fa67c2031a5..2204708dbf7a 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -61,7 +61,8 @@
/*
* open_tree() flags.
*/
-#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLONE (1 << 0) /* Clone the target tree and attach the clone */
+#define OPEN_TREE_NAMESPACE (1 << 1) /* Clone the target tree into a new mount namespace */
#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */
/*
@@ -109,6 +110,7 @@ enum fsconfig_command {
* fsmount() flags.
*/
#define FSMOUNT_CLOEXEC 0x00000001
+#define FSMOUNT_NAMESPACE 0x00000002 /* Create the mount in a new mount namespace */
/*
* Mount attributes.
@@ -197,7 +199,10 @@ struct statmount {
*/
struct mnt_id_req {
__u32 size;
- __u32 spare;
+ union {
+ __u32 mnt_ns_fd;
+ __u32 mnt_fd;
+ };
__u64 mnt_id;
__u64 param;
__u64 mnt_ns_id;
@@ -232,4 +237,9 @@ struct mnt_id_req {
#define LSMT_ROOT 0xffffffffffffffff /* root mount */
#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */
+/*
+ * @flag bits for statmount(2)
+ */
+#define STATMOUNT_BY_FD 0x00000001U /* want mountinfo for given fd */
+
#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index e0b579a1df4f..35ff083221c7 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -97,6 +97,8 @@ enum {
};
enum {
+ NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1,
+
__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
};
@@ -160,6 +162,7 @@ enum {
NETDEV_A_QUEUE_DMABUF,
NETDEV_A_QUEUE_IO_URING,
NETDEV_A_QUEUE_XSK,
+ NETDEV_A_QUEUE_LEASE,
__NETDEV_A_QUEUE_MAX,
NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
@@ -203,10 +206,20 @@ enum {
};
enum {
+ NETDEV_A_LEASE_IFINDEX = 1,
+ NETDEV_A_LEASE_QUEUE,
+ NETDEV_A_LEASE_NETNS_ID,
+
+ __NETDEV_A_LEASE_MAX,
+ NETDEV_A_LEASE_MAX = (__NETDEV_A_LEASE_MAX - 1)
+};
+
+enum {
NETDEV_A_DMABUF_IFINDEX = 1,
NETDEV_A_DMABUF_QUEUES,
NETDEV_A_DMABUF_FD,
NETDEV_A_DMABUF_ID,
+ NETDEV_A_DMABUF_RX_PAGE_SIZE,
__NETDEV_A_DMABUF_MAX,
NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
@@ -228,6 +241,7 @@ enum {
NETDEV_CMD_BIND_RX,
NETDEV_CMD_NAPI_SET,
NETDEV_CMD_BIND_TX,
+ NETDEV_CMD_QUEUE_CREATE,
__NETDEV_CMD_MAX,
NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 000000000000..4759c471676c
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_OPENAT2_H
+#define _LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+ __u64 flags;
+ __u64 mode;
+ __u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings
+ (includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style
+ "magic-links". */
+#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks
+ (implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like
+ "..", symlinks, and absolute
+ paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
+ be scoped inside the dirfd
+ (similar to chroot(2)). */
+#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be
+ completed through cached lookup. May
+ return -EAGAIN if that's not
+ possible. */
+
+#endif /* _LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/rtnetlink.h b/tools/include/uapi/linux/rtnetlink.h
index dab9493c791b..27265fd31e5f 100644
--- a/tools/include/uapi/linux/rtnetlink.h
+++ b/tools/include/uapi/linux/rtnetlink.h
@@ -840,6 +840,7 @@ enum {
#define RTEXT_FILTER_CFM_CONFIG (1 << 5)
#define RTEXT_FILTER_CFM_STATUS (1 << 6)
#define RTEXT_FILTER_MST (1 << 7)
+#define RTEXT_FILTER_NAME_ONLY (1 << 8)
/* End of information exported to user level */
diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
index c53cde425406..457498259494 100644
--- a/tools/include/uapi/linux/stddef.h
+++ b/tools/include/uapi/linux/stddef.h
@@ -3,7 +3,6 @@
#define _LINUX_STDDEF_H
-
#ifndef __always_inline
#define __always_inline __inline__
#endif
@@ -36,6 +35,11 @@
struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
} ATTRS
+#ifdef __cplusplus
+/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
+#define __DECLARE_FLEX_ARRAY(T, member) \
+ T member[0]
+#else
/**
* __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
*
@@ -52,3 +56,23 @@
TYPE NAME[]; \
}
#endif
+
+#ifndef __counted_by
+#define __counted_by(m)
+#endif
+
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
+#ifndef __counted_by_ptr
+#define __counted_by_ptr(m)
+#endif
+
+#define __kernel_nonstring
+
+#endif /* _LINUX_STDDEF_H */
diff --git a/tools/include/uapi/linux/taskstats.h b/tools/include/uapi/linux/taskstats.h
new file mode 100644
index 000000000000..3ae25f3ce067
--- /dev/null
+++ b/tools/include/uapi/linux/taskstats.h
@@ -0,0 +1,291 @@
+/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */
+/* taskstats.h - exporting per-task statistics
+ *
+ * Copyright (C) Shailabh Nagar, IBM Corp. 2006
+ * (C) Balbir Singh, IBM Corp. 2006
+ * (C) Jay Lan, SGI, 2006
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#ifndef _LINUX_TASKSTATS_H
+#define _LINUX_TASKSTATS_H
+
+#include <linux/types.h>
+#include <linux/time_types.h>
+
+/* Format for per-task data returned to userland when
+ * - a task exits
+ * - listener requests stats for a task
+ *
+ * The struct is versioned. Newer versions should only add fields to
+ * the bottom of the struct to maintain backward compatibility.
+ *
+ *
+ * To add new fields
+ * a) bump up TASKSTATS_VERSION
+ * b) add comment indicating new version number at end of struct
+ * c) add new fields after version comment; maintain 64-bit alignment
+ */
+
+
+#define TASKSTATS_VERSION 17
+#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
+ * in linux/sched.h */
+
+struct taskstats {
+
+ /* The version number of this struct. This field is always set to
+ * TAKSTATS_VERSION, which is defined in <linux/taskstats.h>.
+ * Each time the struct is changed, the value should be incremented.
+ */
+ __u16 version;
+ __u32 ac_exitcode; /* Exit status */
+
+ /* The accounting flags of a task as defined in <linux/acct.h>
+ * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP.
+ * (AGROUP since version 12).
+ */
+ __u8 ac_flag; /* Record flags */
+ __u8 ac_nice; /* task_nice */
+
+ /* Delay accounting fields start
+ *
+ * All values, until comment "Delay accounting fields end" are
+ * available only if delay accounting is enabled, even though the last
+ * few fields are not delays
+ *
+ * xxx_count is the number of delay values recorded
+ * xxx_delay_total is the corresponding cumulative delay in nanoseconds
+ *
+ * xxx_delay_total wraps around to zero on overflow
+ * xxx_count incremented regardless of overflow
+ */
+
+ /* Delay waiting for cpu, while runnable
+ * count, delay_total NOT updated atomically
+ */
+ __u64 cpu_count __attribute__((aligned(8)));
+ __u64 cpu_delay_total;
+
+ /* Following four fields atomically updated using task->delays->lock */
+
+ /* Delay waiting for synchronous block I/O to complete
+ * does not account for delays in I/O submission
+ */
+ __u64 blkio_count;
+ __u64 blkio_delay_total;
+
+ /* Delay waiting for page fault I/O (swap in only) */
+ __u64 swapin_count;
+ __u64 swapin_delay_total;
+
+ /* cpu "wall-clock" running time
+ * On some architectures, value will adjust for cpu time stolen
+ * from the kernel in involuntary waits due to virtualization.
+ * Value is cumulative, in nanoseconds, without a corresponding count
+ * and wraps around to zero silently on overflow
+ */
+ __u64 cpu_run_real_total;
+
+ /* cpu "virtual" running time
+ * Uses time intervals seen by the kernel i.e. no adjustment
+ * for kernel's involuntary waits due to virtualization.
+ * Value is cumulative, in nanoseconds, without a corresponding count
+ * and wraps around to zero silently on overflow
+ */
+ __u64 cpu_run_virtual_total;
+ /* Delay accounting fields end */
+ /* version 1 ends here */
+
+ /* Basic Accounting Fields start */
+ char ac_comm[TS_COMM_LEN]; /* Command name */
+ __u8 ac_sched __attribute__((aligned(8)));
+ /* Scheduling discipline */
+ __u8 ac_pad[3];
+ __u32 ac_uid __attribute__((aligned(8)));
+ /* User ID */
+ __u32 ac_gid; /* Group ID */
+ __u32 ac_pid; /* Process ID */
+ __u32 ac_ppid; /* Parent process ID */
+ /* __u32 range means times from 1970 to 2106 */
+ __u32 ac_btime; /* Begin time [sec since 1970] */
+ __u64 ac_etime __attribute__((aligned(8)));
+ /* Elapsed time [usec] */
+ __u64 ac_utime; /* User CPU time [usec] */
+ __u64 ac_stime; /* SYstem CPU time [usec] */
+ __u64 ac_minflt; /* Minor Page Fault Count */
+ __u64 ac_majflt; /* Major Page Fault Count */
+ /* Basic Accounting Fields end */
+
+ /* Extended accounting fields start */
+ /* Accumulated RSS usage in duration of a task, in MBytes-usecs.
+ * The current rss usage is added to this counter every time
+ * a tick is charged to a task's system time. So, at the end we
+ * will have memory usage multiplied by system time. Thus an
+ * average usage per system time unit can be calculated.
+ */
+ __u64 coremem; /* accumulated RSS usage in MB-usec */
+ /* Accumulated virtual memory usage in duration of a task.
+ * Same as acct_rss_mem1 above except that we keep track of VM usage.
+ */
+ __u64 virtmem; /* accumulated VM usage in MB-usec */
+
+ /* High watermark of RSS and virtual memory usage in duration of
+ * a task, in KBytes.
+ */
+ __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */
+ __u64 hiwater_vm; /* High-water VM usage, in KB */
+
+ /* The following four fields are I/O statistics of a task. */
+ __u64 read_char; /* bytes read */
+ __u64 write_char; /* bytes written */
+ __u64 read_syscalls; /* read syscalls */
+ __u64 write_syscalls; /* write syscalls */
+ /* Extended accounting fields end */
+
+#define TASKSTATS_HAS_IO_ACCOUNTING
+ /* Per-task storage I/O accounting starts */
+ __u64 read_bytes; /* bytes of read I/O */
+ __u64 write_bytes; /* bytes of write I/O */
+ __u64 cancelled_write_bytes; /* bytes of cancelled write I/O */
+
+ __u64 nvcsw; /* voluntary_ctxt_switches */
+ __u64 nivcsw; /* nonvoluntary_ctxt_switches */
+
+ /* time accounting for SMT machines */
+ __u64 ac_utimescaled; /* utime scaled on frequency etc */
+ __u64 ac_stimescaled; /* stime scaled on frequency etc */
+ __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
+
+ /* Delay waiting for memory reclaim */
+ __u64 freepages_count;
+ __u64 freepages_delay_total;
+
+
+ /* Delay waiting for thrashing page */
+ __u64 thrashing_count;
+ __u64 thrashing_delay_total;
+
+ /* v10: 64-bit btime to avoid overflow */
+ __u64 ac_btime64; /* 64-bit begin time */
+
+ /* v11: Delay waiting for memory compact */
+ __u64 compact_count;
+ __u64 compact_delay_total;
+
+ /* v12 begin */
+ __u32 ac_tgid; /* thread group ID */
+ /* Thread group walltime up to now. This is total process walltime if
+ * AGROUP flag is set.
+ */
+ __u64 ac_tgetime __attribute__((aligned(8)));
+ /* Lightweight information to identify process binary files.
+ * This leaves userspace to match this to a file system path, using
+ * MAJOR() and MINOR() macros to identify a device and mount point,
+ * the inode to identify the executable file. This is /proc/self/exe
+ * at the end, so matching the most recent exec(). Values are zero
+ * for kernel threads.
+ */
+ __u64 ac_exe_dev; /* program binary device ID */
+ __u64 ac_exe_inode; /* program binary inode number */
+ /* v12 end */
+
+ /* v13: Delay waiting for write-protect copy */
+ __u64 wpcopy_count;
+ __u64 wpcopy_delay_total;
+
+ /* v14: Delay waiting for IRQ/SOFTIRQ */
+ __u64 irq_count;
+ __u64 irq_delay_total;
+
+ /* v15: add Delay max and Delay min */
+
+ /* v16: move Delay max and Delay min to the end of taskstat */
+ __u64 cpu_delay_max;
+ __u64 cpu_delay_min;
+
+ __u64 blkio_delay_max;
+ __u64 blkio_delay_min;
+
+ __u64 swapin_delay_max;
+ __u64 swapin_delay_min;
+
+ __u64 freepages_delay_max;
+ __u64 freepages_delay_min;
+
+ __u64 thrashing_delay_max;
+ __u64 thrashing_delay_min;
+
+ __u64 compact_delay_max;
+ __u64 compact_delay_min;
+
+ __u64 wpcopy_delay_max;
+ __u64 wpcopy_delay_min;
+
+ __u64 irq_delay_max;
+ __u64 irq_delay_min;
+
+ /*v17: delay max timestamp record*/
+ struct __kernel_timespec cpu_delay_max_ts;
+ struct __kernel_timespec blkio_delay_max_ts;
+ struct __kernel_timespec swapin_delay_max_ts;
+ struct __kernel_timespec freepages_delay_max_ts;
+ struct __kernel_timespec thrashing_delay_max_ts;
+ struct __kernel_timespec compact_delay_max_ts;
+ struct __kernel_timespec wpcopy_delay_max_ts;
+ struct __kernel_timespec irq_delay_max_ts;
+};
+
+
+/*
+ * Commands sent from userspace
+ * Not versioned. New commands should only be inserted at the enum's end
+ * prior to __TASKSTATS_CMD_MAX
+ */
+
+enum {
+ TASKSTATS_CMD_UNSPEC = 0, /* Reserved */
+ TASKSTATS_CMD_GET, /* user->kernel request/get-response */
+ TASKSTATS_CMD_NEW, /* kernel->user event */
+ __TASKSTATS_CMD_MAX,
+};
+
+#define TASKSTATS_CMD_MAX (__TASKSTATS_CMD_MAX - 1)
+
+enum {
+ TASKSTATS_TYPE_UNSPEC = 0, /* Reserved */
+ TASKSTATS_TYPE_PID, /* Process id */
+ TASKSTATS_TYPE_TGID, /* Thread group id */
+ TASKSTATS_TYPE_STATS, /* taskstats structure */
+ TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */
+ TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */
+ TASKSTATS_TYPE_NULL, /* contains nothing */
+ __TASKSTATS_TYPE_MAX,
+};
+
+#define TASKSTATS_TYPE_MAX (__TASKSTATS_TYPE_MAX - 1)
+
+enum {
+ TASKSTATS_CMD_ATTR_UNSPEC = 0,
+ TASKSTATS_CMD_ATTR_PID,
+ TASKSTATS_CMD_ATTR_TGID,
+ TASKSTATS_CMD_ATTR_REGISTER_CPUMASK,
+ TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK,
+ __TASKSTATS_CMD_ATTR_MAX,
+};
+
+#define TASKSTATS_CMD_ATTR_MAX (__TASKSTATS_CMD_ATTR_MAX - 1)
+
+/* NETLINK_GENERIC related info */
+
+#define TASKSTATS_GENL_NAME "TASKSTATS"
+#define TASKSTATS_GENL_VERSION 0x1
+
+#endif /* _LINUX_TASKSTATS_H */
diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h
index 4283de22d5b6..c8e99df95219 100644
--- a/tools/include/uapi/linux/userfaultfd.h
+++ b/tools/include/uapi/linux/userfaultfd.h
@@ -25,7 +25,8 @@
#define UFFD_API ((__u64)0xAA)
#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \
UFFDIO_REGISTER_MODE_WP | \
- UFFDIO_REGISTER_MODE_MINOR)
+ UFFDIO_REGISTER_MODE_MINOR | \
+ UFFDIO_REGISTER_MODE_RWP)
#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
UFFD_FEATURE_EVENT_FORK | \
UFFD_FEATURE_EVENT_REMAP | \
@@ -42,10 +43,13 @@
UFFD_FEATURE_WP_UNPOPULATED | \
UFFD_FEATURE_POISON | \
UFFD_FEATURE_WP_ASYNC | \
- UFFD_FEATURE_MOVE)
+ UFFD_FEATURE_MOVE | \
+ UFFD_FEATURE_RWP | \
+ UFFD_FEATURE_RWP_ASYNC)
#define UFFD_API_IOCTLS \
((__u64)1 << _UFFDIO_REGISTER | \
(__u64)1 << _UFFDIO_UNREGISTER | \
+ (__u64)1 << _UFFDIO_SET_MODE | \
(__u64)1 << _UFFDIO_API)
#define UFFD_API_RANGE_IOCTLS \
((__u64)1 << _UFFDIO_WAKE | \
@@ -54,13 +58,15 @@
(__u64)1 << _UFFDIO_MOVE | \
(__u64)1 << _UFFDIO_WRITEPROTECT | \
(__u64)1 << _UFFDIO_CONTINUE | \
- (__u64)1 << _UFFDIO_POISON)
+ (__u64)1 << _UFFDIO_POISON | \
+ (__u64)1 << _UFFDIO_RWPROTECT)
#define UFFD_API_RANGE_IOCTLS_BASIC \
((__u64)1 << _UFFDIO_WAKE | \
(__u64)1 << _UFFDIO_COPY | \
(__u64)1 << _UFFDIO_WRITEPROTECT | \
(__u64)1 << _UFFDIO_CONTINUE | \
- (__u64)1 << _UFFDIO_POISON)
+ (__u64)1 << _UFFDIO_POISON | \
+ (__u64)1 << _UFFDIO_RWPROTECT)
/*
* Valid ioctl command number range with this API is from 0x00 to
@@ -79,6 +85,8 @@
#define _UFFDIO_WRITEPROTECT (0x06)
#define _UFFDIO_CONTINUE (0x07)
#define _UFFDIO_POISON (0x08)
+#define _UFFDIO_RWPROTECT (0x09)
+#define _UFFDIO_SET_MODE (0x0A)
#define _UFFDIO_API (0x3F)
/* userfaultfd ioctl ids */
@@ -103,6 +111,10 @@
struct uffdio_continue)
#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \
struct uffdio_poison)
+#define UFFDIO_RWPROTECT _IOWR(UFFDIO, _UFFDIO_RWPROTECT, \
+ struct uffdio_rwprotect)
+#define UFFDIO_SET_MODE _IOW(UFFDIO, _UFFDIO_SET_MODE, \
+ struct uffdio_set_mode)
/* read() structure */
struct uffd_msg {
@@ -158,6 +170,7 @@ struct uffd_msg {
#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */
#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */
+#define UFFD_PAGEFAULT_FLAG_RWP (1<<3) /* If reason is VM_UFFD_RWP */
struct uffdio_api {
/* userland asks for an API number and the features to enable */
@@ -230,6 +243,18 @@ struct uffdio_api {
*
* UFFD_FEATURE_MOVE indicates that the kernel supports moving an
* existing page contents from userspace.
+ *
+ * UFFD_FEATURE_RWP indicates that the kernel supports
+ * UFFDIO_REGISTER_MODE_RWP for read-write protection tracking.
+ * Pages are made inaccessible via UFFDIO_RWPROTECT and faults
+ * are delivered when the pages are re-accessed.
+ *
+ * UFFD_FEATURE_RWP_ASYNC indicates asynchronous mode for
+ * UFFDIO_REGISTER_MODE_RWP. When set, faults on read-write
+ * protected pages are auto-resolved by the kernel (PTE
+ * permissions restored immediately) without delivering a message
+ * to the userfaultfd handler. Use PAGEMAP_SCAN with inverted
+ * PAGE_IS_ACCESSED to find pages that were not re-accessed.
*/
#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0)
#define UFFD_FEATURE_EVENT_FORK (1<<1)
@@ -248,6 +273,8 @@ struct uffdio_api {
#define UFFD_FEATURE_POISON (1<<14)
#define UFFD_FEATURE_WP_ASYNC (1<<15)
#define UFFD_FEATURE_MOVE (1<<16)
+#define UFFD_FEATURE_RWP (1<<17)
+#define UFFD_FEATURE_RWP_ASYNC (1<<18)
__u64 features;
__u64 ioctls;
@@ -263,6 +290,7 @@ struct uffdio_register {
#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0)
#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1)
#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2)
+#define UFFDIO_REGISTER_MODE_RWP ((__u64)1<<3)
__u64 mode;
/*
@@ -356,6 +384,14 @@ struct uffdio_poison {
__s64 updated;
};
+struct uffdio_rwprotect {
+ struct uffdio_range range;
+ /* !RWP means undo RWP-protection */
+#define UFFDIO_RWPROTECT_MODE_RWP ((__u64)1<<0)
+#define UFFDIO_RWPROTECT_MODE_DONTWAKE ((__u64)1<<1)
+ __u64 mode;
+};
+
struct uffdio_move {
__u64 dst;
__u64 src;
@@ -374,6 +410,16 @@ struct uffdio_move {
__s64 move;
};
+struct uffdio_set_mode {
+ /*
+ * Toggle async mode for features at runtime.
+ * Supported: UFFD_FEATURE_RWP_ASYNC.
+ * Setting a bit in both enable and disable is invalid.
+ */
+ __u64 enable;
+ __u64 disable;
+};
+
/*
* Flags for the userfaultfd(2) system call itself.
*/
generated by cgit v1.2.3 (git 2.0.4) at 2026-09-21 20:02:22 +0000