Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 66917a4..77c6be9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -14,6 +14,7 @@
/* Extended instruction set based on top of classic BPF */
/* instruction classes */
+#define BPF_JMP32 0x06 /* jmp mode in word width */
#define BPF_ALU64 0x07 /* alu mode in double word width */
/* ld/ldx fields */
@@ -103,6 +104,9 @@
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
+ BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
+ BPF_BTF_GET_NEXT_ID,
};
enum bpf_map_type {
@@ -127,8 +131,21 @@
BPF_MAP_TYPE_SOCKHASH,
BPF_MAP_TYPE_CGROUP_STORAGE,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+ BPF_MAP_TYPE_QUEUE,
+ BPF_MAP_TYPE_STACK,
+ BPF_MAP_TYPE_SK_STORAGE,
+ BPF_MAP_TYPE_DEVMAP_HASH,
};
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
enum bpf_prog_type {
BPF_PROG_TYPE_UNSPEC,
BPF_PROG_TYPE_SOCKET_FILTER,
@@ -152,6 +169,10 @@
BPF_PROG_TYPE_LWT_SEG6LOCAL,
BPF_PROG_TYPE_LIRC_MODE2,
BPF_PROG_TYPE_SK_REUSEPORT,
+ BPF_PROG_TYPE_FLOW_DISSECTOR,
+ BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+ BPF_PROG_TYPE_CGROUP_SOCKOPT,
};
enum bpf_attach_type {
@@ -172,6 +193,12 @@
BPF_CGROUP_UDP4_SENDMSG,
BPF_CGROUP_UDP6_SENDMSG,
BPF_LIRC_MODE2,
+ BPF_FLOW_DISSECTOR,
+ BPF_CGROUP_SYSCTL,
+ BPF_CGROUP_UDP4_RECVMSG,
+ BPF_CGROUP_UDP6_RECVMSG,
+ BPF_CGROUP_GETSOCKOPT,
+ BPF_CGROUP_SETSOCKOPT,
__MAX_BPF_ATTACH_TYPE
};
@@ -226,8 +253,54 @@
*/
#define BPF_F_STRICT_ALIGNMENT (1U << 0)
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
+ * verifier will allow any alignment whatsoever. On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement. This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT (1U << 1)
+
+/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
+ * Verifier does sub-register def/use analysis and identifies instructions whose
+ * def only matters for low 32-bit, high 32-bit is never referenced later
+ * through implicit zero extension. Therefore verifier notifies JIT back-ends
+ * that it is safe to ignore clearing high 32-bit for these instructions. This
+ * saves some back-ends a lot of code-gen. However such optimization is not
+ * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
+ * hence hasn't used verifier's analysis result. But, we really want to have a
+ * way to be able to verify the correctness of the described optimization on
+ * x86_64 on which testsuites are frequently exercised.
+ *
+ * So, this flag is introduced. Once it is set, verifier will randomize high
+ * 32-bit for those instructions who has been identified as safe to ignore them.
+ * Then, if verifier is not doing correct analysis, such randomization will
+ * regress tests to expose bugs.
+ */
+#define BPF_F_TEST_RND_HI32 (1U << 2)
+
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_STATE_FREQ (1U << 3)
+
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm: map fd map fd
+ * insn[1].imm: 0 offset into value
+ * insn[0].off: 0 0
+ * insn[1].off: 0 0
+ * ldimm64 rewrite: address of map address of map[0]+offset
+ * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
+ */
#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_VALUE 2
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function
@@ -238,6 +311,7 @@
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
+#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */
/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0)
@@ -251,18 +325,28 @@
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE (1U << 2)
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE (1U << 0)
-
#define BPF_OBJ_NAME_LEN 16U
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
#define BPF_F_RDONLY (1U << 3)
#define BPF_F_WRONLY (1U << 4)
/* Flag for stack_map, store build_id+offset instead of pointer */
#define BPF_F_STACK_BUILD_ID (1U << 5)
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED (1U << 6)
+
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG (1U << 7)
+#define BPF_F_WRONLY_PROG (1U << 8)
+
+/* Clone map from listener for newly accepted socket */
+#define BPF_F_CLONE (1U << 9)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
enum bpf_stack_build_id_status {
/* user space need an empty entry to identify end of a trace */
BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -320,7 +404,7 @@
__u32 log_level; /* verbosity level of verifier */
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
- __u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 kern_version; /* not used */
__u32 prog_flags;
char prog_name[BPF_OBJ_NAME_LEN];
__u32 prog_ifindex; /* ifindex of netdev to prep for */
@@ -329,6 +413,13 @@
* (context accesses, allowed helpers, etc).
*/
__u32 expected_attach_type;
+ __u32 prog_btf_fd; /* fd pointing to BTF type data */
+ __u32 func_info_rec_size; /* userspace bpf_func_info size */
+ __aligned_u64 func_info; /* func info */
+ __u32 func_info_cnt; /* number of bpf_func_info records */
+ __u32 line_info_rec_size; /* userspace bpf_line_info size */
+ __aligned_u64 line_info; /* line info */
+ __u32 line_info_cnt; /* number of bpf_line_info records */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -347,12 +438,22 @@
struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
__u32 prog_fd;
__u32 retval;
- __u32 data_size_in;
- __u32 data_size_out;
+ __u32 data_size_in; /* input: len of data_in */
+ __u32 data_size_out; /* input/output: len of data_out
+ * returns ENOSPC if data_out
+ * is too small.
+ */
__aligned_u64 data_in;
__aligned_u64 data_out;
__u32 repeat;
__u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
} test;
struct { /* anonymous struct used by BPF_*_GET_*_ID */
@@ -482,6 +583,8 @@
* limited to five).
*
* Each time the helper is called, it appends a line to the trace.
+ * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is
+ * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this.
* The format of the trace is customizable, and the exact output
* one will get depends on the options set in
* *\/sys/kernel/debug/tracing/trace_options* (see also the
@@ -559,7 +662,7 @@
* **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\
* **->swhash** and *skb*\ **->l4hash** to 0).
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -584,7 +687,7 @@
* flexibility and can handle sizes larger than 2 or 4 for the
* checksum to update.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -616,7 +719,7 @@
* flexibility and can handle sizes larger than 2 or 4 for the
* checksum to update.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -671,7 +774,7 @@
* efficient, but it is handled through an action code where the
* redirection happens only after the eBPF program has returned.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -713,7 +816,7 @@
* based on a user-provided identifier for all traffic coming from
* the tasks belonging to the related cgroup. See also the related
* kernel documentation, available from the Linux sources in file
- * *Documentation/cgroup-v1/net_cls.txt*.
+ * *Documentation/admin-guide/cgroup-v1/net_cls.rst*.
*
* The Linux kernel has two versions for cgroups: there are
* cgroups v1 and cgroups v2. Both are available to users, who can
@@ -736,7 +839,7 @@
* **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to
* be **ETH_P_8021Q**.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -748,7 +851,7 @@
* Description
* Pop a VLAN header from the packet associated to *skb*.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -920,7 +1023,7 @@
* The realm of the route for the packet associated to *skb*, or 0
* if none was found.
*
- * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
* Description
* Write raw *data* blob into a special BPF perf event held by
* *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -982,7 +1085,7 @@
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
+ * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags)
* Description
* Walk a user or a kernel stack and return its id. To achieve
* this, the helper needs *ctx*, which is a pointer to the context
@@ -1098,7 +1201,7 @@
* All values for *flags* are reserved for future usage, and must
* be left at zero.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1211,7 +1314,7 @@
* implicitly linearizes, unclones and drops offloads from the
* *skb*.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1247,7 +1350,7 @@
* **bpf_skb_pull_data()** to effectively unclone the *skb* from
* the very beginning in case it is indeed cloned.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1299,7 +1402,7 @@
* All values for *flags* are reserved for future usage, and must
* be left at zero.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1314,7 +1417,7 @@
* can be used to prepare the packet for pushing or popping
* headers.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1373,8 +1476,8 @@
* If no cookie has been set yet, generate a new cookie. Once
* generated, the socket cookie remains stable for the life of the
* socket. This helper can be useful for monitoring per socket
- * networking traffic statistics as it provides a unique socket
- * identifier per namespace.
+ * networking traffic statistics as it provides a global socket
+ * identifier that can be assumed unique.
* Return
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
@@ -1382,14 +1485,14 @@
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * *skb*, but gets socket from **struct bpf_sock_addr** context.
* Return
* A 8-byte long non-decreasing number.
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
- * *skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
*
@@ -1430,20 +1533,38 @@
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
* Description
* Grow or shrink the room for data in the packet associated to
* *skb* by *len_diff*, and according to the selected *mode*.
*
- * There is a single supported mode at this time:
+ * There are two supported modes at this time:
+ *
+ * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
+ * (room space is added or removed below the layer 2 header).
*
* * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
* (room space is added or removed below the layer 3 header).
*
- * All values for *flags* are reserved for future usage, and must
- * be left at zero.
+ * The following flags are supported at this time:
*
- * A call to this helper is susceptible to change the underlaying
+ * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
+ * Adjusting mss in this way is not allowed for datagrams.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**:
+ * Any new space is reserved to hold a tunnel header.
+ * Configure skb offsets and other fields accordingly.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**:
+ * Use with ENCAP_L3 flags to further specify the tunnel type.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*):
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; *len* is the length of the inner MAC header.
+ *
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1460,8 +1581,11 @@
* but this is only implemented for native XDP (with driver
* support) as of this writing).
*
- * All values for *flags* are reserved for future usage, and must
- * be left at zero.
+ * The lower two bits of *flags* are used as the return code if
+ * the map lookup fails. This is so that the return value can be
+ * one of the XDP program return codes up to XDP_TX, as chosen by
+ * the caller. Any higher bits in the *flags* argument must be
+ * unset.
*
* When used to redirect packets to net devices, this helper
* provides a high performance increase over **bpf_redirect**\ ().
@@ -1522,7 +1646,7 @@
* more flexibility as the user is free to store whatever meta
* data they need.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1610,7 +1734,7 @@
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_override_return(struct pt_reg *regs, u64 rc)
+ * int bpf_override_return(struct pt_regs *regs, u64 rc)
* Description
* Used for error injection, this helper uses kprobes to override
* the return value of the probed function, and to set it to *rc*.
@@ -1651,11 +1775,19 @@
* error if an eBPF program tries to set a callback that is not
* supported in the current kernel.
*
- * The supported callback values that *argval* can combine are:
+ * *argval* is a flag array which can combine these flags:
*
* * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
* * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
* * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
+ * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
+ *
+ * Therefore, this function can be used to clear a callback flag by
+ * setting the appropriate bit to zero. e.g. to disable the RTO
+ * callback:
+ *
+ * **bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
*
* Here are some examples of where one could call such eBPF
* program:
@@ -1757,7 +1889,7 @@
* copied if necessary (i.e. if data was not linear and if start
* and end pointers do not point to the same chunk).
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1791,7 +1923,7 @@
* only possible to shrink the packet as of this writing,
* therefore *delta* must be a negative integer.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1882,9 +2014,9 @@
* is set to metric from route (IPv4/IPv6 only), and ifindex
* is set to the device index of the nexthop from the FIB lookup.
*
- * *plen* argument is the size of the passed in struct.
- * *flags* argument can be a combination of one or more of the
- * following values:
+ * *plen* argument is the size of the passed in struct.
+ * *flags* argument can be a combination of one or more of the
+ * following values:
*
* **BPF_FIB_LOOKUP_DIRECT**
* Do a direct table lookup vs full lookup using FIB
@@ -1893,9 +2025,9 @@
* Perform lookup from an egress perspective (default is
* ingress).
*
- * *ctx* is either **struct xdp_md** for XDP programs or
- * **struct sk_buff** tc cls_act programs.
- * Return
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** tc cls_act programs.
+ * Return
* * < 0 if any input argument is invalid
* * 0 on success (packet is forwarded, nexthop neighbor exists)
* * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
@@ -1963,8 +2095,21 @@
* Only works if *skb* contains an IPv6 packet. Insert a
* Segment Routing Header (**struct ipv6_sr_hdr**) inside
* the IPv6 header.
+ * **BPF_LWT_ENCAP_IP**
+ * IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ * must be IPv4 or IPv6, followed by zero or more
+ * additional headers, up to **LWT_BPF_MAX_HEADROOM**
+ * total bytes in all prepended headers. Please note that
+ * if **skb_is_gso**\ (*skb*) is true, no more than two
+ * headers can be prepended, and the inner header, if
+ * present, should be either GRE or UDP/GUE.
*
- * A call to this helper is susceptible to change the underlaying
+ * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs
+ * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can
+ * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and
+ * **BPF_PROG_TYPE_LWT_XMIT**.
+ *
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1979,7 +2124,7 @@
* inside the outermost IPv6 Segment Routing Header can be
* modified through this helper.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -1995,7 +2140,7 @@
* after the segments are accepted. *delta* can be as well
* positive (growing) as negative (shrinking).
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -2018,13 +2163,13 @@
* Type of *param*: **int**.
* **SEG6_LOCAL_ACTION_END_B6**
* End.B6 action: Endpoint bound to an SRv6 policy.
- * Type of param: **struct ipv6_sr_hdr**.
+ * Type of *param*: **struct ipv6_sr_hdr**.
* **SEG6_LOCAL_ACTION_END_B6_ENCAP**
* End.B6.Encap action: Endpoint bound to an SRv6
* encapsulation policy.
- * Type of param: **struct ipv6_sr_hdr**.
+ * Type of *param*: **struct ipv6_sr_hdr**.
*
- * A call to this helper is susceptible to change the underlaying
+ * A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* performed again, if the helper is used in combination with
@@ -2032,32 +2177,6 @@
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
- * Description
- * This helper is used in programs implementing IR decoding, to
- * report a successfully decoded key press with *scancode*,
- * *toggle* value in the given *protocol*. The scancode will be
- * translated to a keycode using the rc keymap, and reported as
- * an input key down event. After a period a key up event is
- * generated. This period can be extended by calling either
- * **bpf_rc_keydown** () again with the same values, or calling
- * **bpf_rc_repeat** ().
- *
- * Some protocols include a toggle bit, in case the button was
- * released and pressed again between consecutive scancodes.
- *
- * The *ctx* should point to the lirc sample as passed into
- * the program.
- *
- * The *protocol* is the decoded protocol number (see
- * **enum rc_proto** for some predefined values).
- *
- * This helper is only available is the kernel was compiled with
- * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
- * "**y**".
- * Return
- * 0
- *
* int bpf_rc_repeat(void *ctx)
* Description
* This helper is used in programs implementing IR decoding, to
@@ -2077,7 +2196,33 @@
* Return
* 0
*
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown**\ () again with the same values, or calling
+ * **bpf_rc_repeat**\ ().
+ *
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
* Description
* Return the cgroup v2 id of the socket associated with the *skb*.
* This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2093,6 +2238,38 @@
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
+ * u64 bpf_get_current_cgroup_id(void)
+ * Return
+ * A 64-bit integer containing the current cgroup id based
+ * on the cgroup within which the current task is running.
+ *
+ * void *bpf_get_local_storage(void *map, u64 flags)
+ * Description
+ * Get the pointer to the local storage area.
+ * The type and the size of the local storage is defined
+ * by the *map* argument.
+ * The *flags* meaning is specific for each map type,
+ * and has to be 0 for cgroup local storage.
+ *
+ * Depending on the BPF program type, a local storage area
+ * can be shared between multiple instances of the BPF program,
+ * running simultaneously.
+ *
+ * A user should care about the synchronization by himself.
+ * For example, by using the **BPF_STX_XADD** instruction to alter
+ * the shared data.
+ * Return
+ * A pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Select a **SO_REUSEPORT** socket from a
+ * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ * It checks the selected socket is matching the incoming
+ * request in the socket buffer.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
* u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
* Description
* Return id of cgroup v2 that is ancestor of cgroup associated
@@ -2111,36 +2288,468 @@
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
- * u64 bpf_get_current_cgroup_id(void)
- * Return
- * A 64-bit integer containing the current cgroup id based
- * on the cgroup within which the current task is running.
- *
- * void* get_local_storage(void *map, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
* Description
- * Get the pointer to the local storage area.
- * The type and the size of the local storage is defined
- * by the *map* argument.
- * The *flags* meaning is specific for each map type,
- * and has to be 0 for cgroup local storage.
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
*
- * Depending on the bpf program type, a local storage area
- * can be shared between multiple instances of the bpf program,
- * running simultaneously.
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
*
- * A user should care about the synchronization by himself.
- * For example, by using the BPF_STX_XADD instruction to alter
- * the shared data.
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx* will
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
* Return
- * Pointer to the local storage area.
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
*
- * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
* Description
- * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map
- * It checks the selected sk is matching the incoming
- * request in the skb.
+ * Look for UDP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
+ *
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx* will
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * All values for *flags* are reserved for future usage, and must
+ * be left at zero.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * int bpf_sk_release(struct bpf_sock *sock)
+ * Description
+ * Release the reference held by *sock*. *sock* must be a
+ * non-**NULL** pointer that was returned from
+ * **bpf_sk_lookup_xxx**\ ().
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * Description
+ * Pop an element from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * Description
+ * Get an element from *map* without removing it.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ * Description
+ * For socket policies, insert *len* bytes into *msg* at offset
+ * *start*.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it may want to insert metadata or options into the *msg*.
+ * This can later be read and used by any of the lower layer BPF
+ * hooks.
+ *
+ * This helper may fail if under memory pressure (a malloc
+ * fails) in these cases BPF programs will get an appropriate
+ * error and BPF programs will need to handle them.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ * Description
+ * Will remove *pop* bytes from a *msg* starting at byte *start*.
+ * This may result in **ENOMEM** errors under certain situations if
+ * an allocation and copy are required due to a full ring buffer.
+ * However, the helper will try to avoid doing the allocation
+ * if possible. Other errors can occur if input parameters are
+ * invalid either due to *start* byte not being valid part of *msg*
+ * payload and/or *pop* value being to large.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded pointer movement.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ * Return
+ * 0
+ *
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_sock** pointer such
+ * that all the fields in this **bpf_sock** can be accessed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_tcp_sock** pointer from a
+ * **struct bpf_sock** pointer.
+ * Return
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * This function is identical to **bpf_sk_lookup_tcp**\ (), except
+ * that it also returns timewait or request sockets. Use
+ * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the
+ * full structure.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK for
+ * the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ip6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains **sizeof**\ (**struct tcphdr**).
+ *
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
+ * error otherwise.
+ *
+ * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ * Description
+ * Get name of sysctl in /proc/sys/ and copy it into provided by
+ * program buffer *buf* of size *buf_len*.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ * only (e.g. "tcp_mem").
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get current value of sysctl as it is presented in /proc/sys
+ * (incl. newline, etc), and copy it as a string into provided
+ * by program buffer *buf* of size *buf_len*.
+ *
+ * The whole value is copied, no matter what file position user
+ * space issued e.g. sys_read at.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if current value was unavailable, e.g. because
+ * sysctl is uninitialized and read returns -EIO for it.
+ *
+ * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get new value being written by user space to sysctl (before
+ * the actual write happens) and copy it as a string into
+ * provided by program buffer *buf* of size *buf_len*.
+ *
+ * User space may write new value at file position > 0.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ * Description
+ * Override new value being written by user space to sysctl with
+ * value provided by program in buffer *buf* of size *buf_len*.
+ *
+ * *buf* should contain a string in same form as provided by user
+ * space on sysctl write.
+ *
+ * User space may write new value at file position > 0. To override
+ * the whole sysctl value file position should be set to zero.
+ * Return
+ * 0 on success.
+ *
+ * **-E2BIG** if the *buf_len* is too big.
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to a long integer according to the given base
+ * and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)) followed by a single
+ * optional '**-**' sign.
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtol**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to an unsigned long integer according to the
+ * given base and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)).
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtoul**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * Description
+ * Get a bpf-local-storage from a *sk*.
+ *
+ * Logically, it could be thought of getting the value from
+ * a *map* with *sk* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this
+ * helper enforces the key must be a full socket and the map must
+ * be a **BPF_MAP_TYPE_SK_STORAGE** also.
+ *
+ * Underneath, the value is stored locally at *sk* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf-local-storages residing at *sk*.
+ *
+ * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf-local-storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf-local-storage. If *value* is
+ * **NULL**, the new bpf-local-storage will be zero initialized.
+ * Return
+ * A bpf-local-storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf-local-storage.
+ *
+ * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * Description
+ * Delete a bpf-local-storage from a *sk*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf-local-storage cannot be found.
+ *
+ * int bpf_send_signal(u32 sig)
+ * Description
+ * Send signal *sig* to the current task.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ip6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header.
+ *
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** SYN cookie cannot be issued due to error
+ *
+ * **-ENOENT** SYN cookie should not be issued (no SYN flood)
+ *
+ * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies
+ *
+ * **-EPROTONOSUPPORT** IP packet version is not 4 or 6
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2226,7 +2835,34 @@
FN(get_current_cgroup_id), \
FN(get_local_storage), \
FN(sk_select_reuseport), \
- FN(skb_ancestor_cgroup_id),
+ FN(skb_ancestor_cgroup_id), \
+ FN(sk_lookup_tcp), \
+ FN(sk_lookup_udp), \
+ FN(sk_release), \
+ FN(map_push_elem), \
+ FN(map_pop_elem), \
+ FN(map_peek_elem), \
+ FN(msg_push_data), \
+ FN(msg_pop_data), \
+ FN(rc_pointer_rel), \
+ FN(spin_lock), \
+ FN(spin_unlock), \
+ FN(sk_fullsock), \
+ FN(tcp_sock), \
+ FN(skb_ecn_set_ce), \
+ FN(get_listener_sock), \
+ FN(skc_lookup_tcp), \
+ FN(tcp_check_syncookie), \
+ FN(sysctl_get_name), \
+ FN(sysctl_get_current_value), \
+ FN(sysctl_get_new_value), \
+ FN(sysctl_set_new_value), \
+ FN(strtol), \
+ FN(strtoul), \
+ FN(sk_storage_get), \
+ FN(sk_storage_delete), \
+ FN(send_signal), \
+ FN(tcp_gen_syncookie),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -2282,9 +2918,33 @@
/* BPF_FUNC_perf_event_output for sk_buff input context. */
#define BPF_F_CTXLEN_MASK (0xfffffULL << 32)
+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS (-1L)
+
+/* BPF_FUNC_skb_adjust_room flags. */
+#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0)
+
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56
+
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4)
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
+/* BPF_FUNC_sysctl_get_name flags. */
+#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0)
+
+/* BPF_FUNC_sk_storage_get flags */
+#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0)
+
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
BPF_ADJ_ROOM_NET,
+ BPF_ADJ_ROOM_MAC,
};
/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
@@ -2296,9 +2956,16 @@
/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
enum bpf_lwt_encap_mode {
BPF_LWT_ENCAP_SEG6,
- BPF_LWT_ENCAP_SEG6_INLINE
+ BPF_LWT_ENCAP_SEG6_INLINE,
+ BPF_LWT_ENCAP_IP,
};
+#define __bpf_md_ptr(type, name) \
+union { \
+ type name; \
+ __u64 :64; \
+} __attribute__((aligned(8)))
+
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
*/
@@ -2333,6 +3000,11 @@
/* ... here. */
__u32 data_meta;
+ __bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
+ __u64 tstamp;
+ __u32 wire_len;
+ __u32 gso_segs;
+ __bpf_md_ptr(struct bpf_sock *, sk);
};
struct bpf_tunnel_key {
@@ -2374,7 +3046,15 @@
BPF_DROP = 2,
/* 3-6 reserved */
BPF_REDIRECT = 7,
- /* >127 are reserved for prog type specific return codes */
+ /* >127 are reserved for prog type specific return codes.
+ *
+ * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+ * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+ * changed and should be routed based on its new L3 header.
+ * (This is an L3 redirect, as opposed to L2 redirect
+ * represented by BPF_REDIRECT above).
+ */
+ BPF_LWT_REROUTE = 128,
};
struct bpf_sock {
@@ -2384,15 +3064,80 @@
__u32 protocol;
__u32 mark;
__u32 priority;
- __u32 src_ip4; /* Allows 1,2,4-byte read.
- * Stored in network byte order.
+ /* IP address also allows 1 and 2 bytes access */
+ __u32 src_ip4;
+ __u32 src_ip6[4];
+ __u32 src_port; /* host byte order */
+ __u32 dst_port; /* network byte order */
+ __u32 dst_ip4;
+ __u32 dst_ip6[4];
+ __u32 state;
+};
+
+struct bpf_tcp_sock {
+ __u32 snd_cwnd; /* Sending congestion window */
+ __u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ __u32 rtt_min;
+ __u32 snd_ssthresh; /* Slow start size threshold */
+ __u32 rcv_nxt; /* What we want to receive next */
+ __u32 snd_nxt; /* Next sequence we send */
+ __u32 snd_una; /* First byte we want an ack for */
+ __u32 mss_cache; /* Cached effective mss, not including SACKS */
+ __u32 ecn_flags; /* ECN status bits. */
+ __u32 rate_delivered; /* saved rate sample: packets delivered */
+ __u32 rate_interval_us; /* saved rate sample: time elapsed */
+ __u32 packets_out; /* Packets which are "in flight" */
+ __u32 retrans_out; /* Retransmitted packets out */
+ __u32 total_retrans; /* Total retransmits for entire connection */
+ __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
+ * total number of segments in.
*/
- __u32 src_ip6[4]; /* Allows 1,2,4-byte read.
- * Stored in network byte order.
+ __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
+ * total number of data segments in.
*/
- __u32 src_port; /* Allows 4-byte read.
- * Stored in host byte order
+ __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
+ * The total number of segments sent.
*/
+ __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
+ * total number of data segments sent.
+ */
+ __u32 lost_out; /* Lost packets */
+ __u32 sacked_out; /* SACK'd packets */
+ __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+ * sum(delta(rcv_nxt)), or how many bytes
+ * were acked.
+ */
+ __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
+ * sum(delta(snd_una)), or how many bytes
+ * were acked.
+ */
+ __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
+ * total number of DSACK blocks received
+ */
+ __u32 delivered; /* Total data packets delivered incl. rexmits */
+ __u32 delivered_ce; /* Like the above but only ECE marked packets */
+ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */
+};
+
+struct bpf_sock_tuple {
+ union {
+ struct {
+ __be32 saddr;
+ __be32 daddr;
+ __be16 sport;
+ __be16 dport;
+ } ipv4;
+ struct {
+ __be32 saddr[4];
+ __be32 daddr[4];
+ __be16 sport;
+ __be16 dport;
+ } ipv6;
+ };
+};
+
+struct bpf_xdp_sock {
+ __u32 queue_id;
};
#define XDP_PACKET_HEADROOM 256
@@ -2431,8 +3176,8 @@
* be added to the end of this structure
*/
struct sk_msg_md {
- void *data;
- void *data_end;
+ __bpf_md_ptr(void *, data);
+ __bpf_md_ptr(void *, data_end);
__u32 family;
__u32 remote_ip4; /* Stored in network byte order */
@@ -2441,6 +3186,7 @@
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ __u32 size; /* Total size of sk_msg */
};
struct sk_reuseport_md {
@@ -2448,8 +3194,9 @@
* Start of directly accessible data. It begins from
* the tcp/udp header.
*/
- void *data;
- void *data_end; /* End of directly accessible data */
+ __bpf_md_ptr(void *, data);
+ /* End of directly accessible data */
+ __bpf_md_ptr(void *, data_end);
/*
* Total length of packet (starting from the tcp/udp header).
* Note that the directly accessible bytes (data_end - data)
@@ -2484,12 +3231,27 @@
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
__u64 netns_dev;
__u64 netns_ino;
__u32 nr_jited_ksyms;
__u32 nr_jited_func_lens;
__aligned_u64 jited_ksyms;
__aligned_u64 jited_func_lens;
+ __u32 btf_id;
+ __u32 func_info_rec_size;
+ __aligned_u64 func_info;
+ __u32 nr_func_info;
+ __u32 nr_line_info;
+ __aligned_u64 line_info;
+ __aligned_u64 jited_line_info;
+ __u32 nr_jited_line_info;
+ __u32 line_info_rec_size;
+ __u32 jited_line_info_rec_size;
+ __u32 nr_prog_tags;
+ __aligned_u64 prog_tags;
+ __u64 run_time_ns;
+ __u64 run_cnt;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -2524,7 +3286,7 @@
__u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write.
* Stored in network byte order.
*/
- __u32 user_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
* Stored in network byte order.
*/
__u32 user_port; /* Allows 4-byte read and write.
@@ -2533,12 +3295,13 @@
__u32 family; /* Allows 4-byte read, but no write */
__u32 type; /* Allows 4-byte read, but no write */
__u32 protocol; /* Allows 4-byte read, but no write */
- __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write.
+ __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write.
* Stored in network byte order.
*/
- __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write.
+ __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
* Stored in network byte order.
*/
+ __bpf_md_ptr(struct bpf_sock *, sk);
};
/* User bpf_sock_ops struct to access socket values and specify request ops
@@ -2590,13 +3353,15 @@
__u32 sk_txhash;
__u64 bytes_received;
__u64 bytes_acked;
+ __bpf_md_ptr(struct bpf_sock *, sk);
};
/* Definitions for bpf_sock_ops_cb_flags */
#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0)
#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1)
#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently
+#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently
* supported cb flags
*/
@@ -2651,6 +3416,8 @@
BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after
* socket transition to LISTEN state.
*/
+ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -2705,8 +3472,8 @@
/* DIRECT: Skip the FIB rules and go to FIB table associated with device
* OUTPUT: Do lookup from egress perspective; default is ingress
*/
-#define BPF_FIB_LOOKUP_DIRECT BIT(0)
-#define BPF_FIB_LOOKUP_OUTPUT BIT(1)
+#define BPF_FIB_LOOKUP_DIRECT (1U << 0)
+#define BPF_FIB_LOOKUP_OUTPUT (1U << 1)
enum {
BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */
@@ -2778,4 +3545,72 @@
BPF_FD_TYPE_URETPROBE, /* filename + offset */
};
+#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1)
+#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2)
+
+struct bpf_flow_keys {
+ __u16 nhoff;
+ __u16 thoff;
+ __u16 addr_proto; /* ETH_P_* of valid addrs */
+ __u8 is_frag;
+ __u8 is_first_frag;
+ __u8 is_encap;
+ __u8 ip_proto;
+ __be16 n_proto;
+ __be16 sport;
+ __be16 dport;
+ union {
+ struct {
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ };
+ struct {
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+ };
+ __u32 flags;
+ __be32 flow_label;
+};
+
+struct bpf_func_info {
+ __u32 insn_off;
+ __u32 type_id;
+};
+
+#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff)
+
+struct bpf_line_info {
+ __u32 insn_off;
+ __u32 file_name_off;
+ __u32 line_off;
+ __u32 line_col;
+};
+
+struct bpf_spin_lock {
+ __u32 val;
+};
+
+struct bpf_sysctl {
+ __u32 write; /* Sysctl is being read (= 0) or written (= 1).
+ * Allows 1,2,4-byte read, but no write.
+ */
+ __u32 file_pos; /* Sysctl file position to read from, write to.
+ * Allows 1,2,4-byte read an 4-byte write.
+ */
+};
+
+struct bpf_sockopt {
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(void *, optval);
+ __bpf_md_ptr(void *, optval_end);
+
+ __s32 level;
+ __s32 optname;
+ __s32 optlen;
+ __s32 retval;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 972265f..63ae4a3 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -34,13 +34,16 @@
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* bits 24-27: kind (e.g. int, ptr, array...etc)
- * bits 28-31: unused
+ * bits 28-30: unused
+ * bit 31: kind_flag, currently used by
+ * struct, union and fwd
*/
__u32 info;
- /* "size" is used by INT, ENUM, STRUCT and UNION.
+ /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
* "size" tells the size of the type it is describing.
*
- * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+ * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+ * FUNC, FUNC_PROTO and VAR.
* "type" is a type_id referring to another type.
*/
union {
@@ -51,6 +54,7 @@
#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f)
#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+#define BTF_INFO_KFLAG(info) ((info) >> 31)
#define BTF_KIND_UNKN 0 /* Unknown */
#define BTF_KIND_INT 1 /* Integer */
@@ -64,8 +68,12 @@
#define BTF_KIND_VOLATILE 9 /* Volatile */
#define BTF_KIND_CONST 10 /* Const */
#define BTF_KIND_RESTRICT 11 /* Restrict */
-#define BTF_KIND_MAX 11
-#define NR_BTF_KINDS 12
+#define BTF_KIND_FUNC 12 /* Function */
+#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
+#define BTF_KIND_VAR 14 /* Variable */
+#define BTF_KIND_DATASEC 15 /* Section */
+#define BTF_KIND_MAX BTF_KIND_DATASEC
+#define NR_BTF_KINDS (BTF_KIND_MAX + 1)
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
@@ -75,7 +83,7 @@
* is the 32 bits arrangement:
*/
#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24)
-#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
+#define BTF_INT_OFFSET(VAL) (((VAL) & 0x00ff0000) >> 16)
#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff)
/* Attributes stored in the BTF_INT_ENCODING */
@@ -107,7 +115,51 @@
struct btf_member {
__u32 name_off;
__u32 type;
- __u32 offset; /* offset in bits */
+ /* If the type info kind_flag is set, the btf_member offset
+ * contains both member bitfield size and bit offset. The
+ * bitfield size is set for bitfield members. If the type
+ * info kind_flag is not set, the offset contains only bit
+ * offset.
+ */
+ __u32 offset;
+};
+
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val) ((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val) ((val) & 0xffffff)
+
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+ __u32 name_off;
+ __u32 type;
+};
+
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
};
#endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
new file mode 100644
index 0000000..5ed721a
--- /dev/null
+++ b/tools/include/uapi/linux/const.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* const.h: Macros for dealing with constants. */
+
+#ifndef _UAPI_LINUX_CONST_H
+#define _UAPI_LINUX_CONST_H
+
+/* Some constant macros are used in both assembler and
+ * C code. Therefore we cannot annotate them always with
+ * 'UL' and other type specifiers unilaterally. We
+ * use the following macros to deal with this.
+ *
+ * Similarly, _AT() will cast an expression with a type in C, but
+ * leave it unchanged in asm.
+ */
+
+#ifdef __ASSEMBLY__
+#define _AC(X,Y) X
+#define _AT(T,X) X
+#else
+#define __AC(X,Y) (X##Y)
+#define _AC(X,Y) __AC(X,Y)
+#define _AT(T,X) ((T)(X))
+#endif
+
+#define _UL(x) (_AC(x, UL))
+#define _ULL(x) (_AC(x, ULL))
+
+#define _BITUL(x) (_UL(1) << (x))
+#define _BITULL(x) (_ULL(1) << (x))
+
+#endif /* _UAPI_LINUX_CONST_H */
diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h
new file mode 100644
index 0000000..c86c3e9
--- /dev/null
+++ b/tools/include/uapi/linux/ethtool.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ethtool.h: Defines for Linux ethtool.
+ *
+ * Copyright (C) 1998 David S. Miller (davem@redhat.com)
+ * Copyright 2001 Jeff Garzik <jgarzik@pobox.com>
+ * Portions Copyright 2001 Sun Microsystems (thockin@sun.com)
+ * Portions Copyright 2002 Intel (eli.kupermann@intel.com,
+ * christopher.leech@intel.com,
+ * scott.feldman@intel.com)
+ * Portions Copyright (C) Sun Microsystems 2008
+ */
+
+#ifndef _UAPI_LINUX_ETHTOOL_H
+#define _UAPI_LINUX_ETHTOOL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */
+
+/**
+ * struct ethtool_channels - configuring number of network channel
+ * @cmd: ETHTOOL_{G,S}CHANNELS
+ * @max_rx: Read only. Maximum number of receive channel the driver support.
+ * @max_tx: Read only. Maximum number of transmit channel the driver support.
+ * @max_other: Read only. Maximum number of other channel the driver support.
+ * @max_combined: Read only. Maximum number of combined channel the driver
+ * support. Set of queues RX, TX or other.
+ * @rx_count: Valid values are in the range 1 to the max_rx.
+ * @tx_count: Valid values are in the range 1 to the max_tx.
+ * @other_count: Valid values are in the range 1 to the max_other.
+ * @combined_count: Valid values are in the range 1 to the max_combined.
+ *
+ * This can be used to configure RX, TX and other channels.
+ */
+
+struct ethtool_channels {
+ __u32 cmd;
+ __u32 max_rx;
+ __u32 max_tx;
+ __u32 max_other;
+ __u32 max_combined;
+ __u32 rx_count;
+ __u32 tx_count;
+ __u32 other_count;
+ __u32 combined_count;
+};
+
+#endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/tools/include/uapi/linux/fadvise.h b/tools/include/uapi/linux/fadvise.h
new file mode 100644
index 0000000..0862b87
--- /dev/null
+++ b/tools/include/uapi/linux/fadvise.h
@@ -0,0 +1,22 @@
+/* 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/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6448cdd..1d33835 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
#define F_SEAL_GROW 0x0004 /* prevent file from growing */
#define F_SEAL_WRITE 0x0008 /* prevent writes */
+#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
/* (1U << 31) is reserved for signed error codes */
/*
@@ -90,5 +91,7 @@
#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+
#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 0000000..379a612
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's. Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
+
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be
+ * recompiled to take full advantage of the new limits..
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET 0 /* seek relative to beginning of file */
+#define SEEK_CUR 1 /* seek relative to current file position */
+#define SEEK_END 2 /* seek relative to end of file */
+#define SEEK_DATA 3 /* seek to the next data */
+#define SEEK_HOLE 4 /* seek to the next hole */
+#define SEEK_MAX SEEK_HOLE
+
+#define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */
+#define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */
+#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */
+
+struct file_clone_range {
+ __s64 src_fd;
+ __u64 src_offset;
+ __u64 src_length;
+ __u64 dest_offset;
+};
+
+struct fstrim_range {
+ __u64 start;
+ __u64 len;
+ __u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME 0
+#define FILE_DEDUPE_RANGE_DIFFERS 1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+ __s64 dest_fd; /* in - destination file */
+ __u64 dest_offset; /* in - start of extent in destination */
+ __u64 bytes_deduped; /* out - total # of bytes we were able
+ * to dedupe from this file. */
+ /* status of this dedupe operation:
+ * < 0 for error
+ * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+ * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+ */
+ __s32 status; /* out - see above description */
+ __u32 reserved; /* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+ __u64 src_offset; /* in - start of extent in source */
+ __u64 src_length; /* in - length of extent */
+ __u16 dest_count; /* in - total elements in info array */
+ __u16 reserved1; /* must be zero */
+ __u32 reserved2; /* must be zero */
+ struct file_dedupe_range_info info[0];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+ unsigned long nr_files; /* read only */
+ unsigned long nr_free_files; /* read only */
+ unsigned long max_files; /* tunable */
+};
+
+struct inodes_stat_t {
+ long nr_inodes;
+ long nr_unused;
+ long dummy[5]; /* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE 8192 /* this can well be larger on a larger system */
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+ __u32 fsx_xflags; /* xflags field value (get/set) */
+ __u32 fsx_extsize; /* extsize field value (get/set)*/
+ __u32 fsx_nextents; /* nextents field value (get) */
+ __u32 fsx_projid; /* project identifier (get/set) */
+ __u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/
+ unsigned char fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */
+#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */
+#define FS_XFLAG_APPEND 0x00000010 /* all writes append */
+#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */
+#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */
+#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */
+#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */
+#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */
+#define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */
+
+/* the read-only stuff doesn't really belong here, but any other place is
+ probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */
+#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */
+#define BLKRRPART _IO(0x12,95) /* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */
+#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */
+#define BLKRASET _IO(0x12,98) /* set read ahead for block device */
+#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */
+#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons. Do not use sizeof! */
+
+#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+ probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET _IOR(0x12,112,size_t)
+#define BLKBSZSET _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
+#define FIBMAP _IO(0x00,1) /* bmap access */
+#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */
+#define FIFREEZE _IOWR('X', 119, int) /* Freeze */
+#define FITHAW _IOWR('X', 120, int) /* Thaw */
+#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
+#define FICLONE _IOW(0x94, 9, int)
+#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256 /* Max chars for the interface; each fs may differ */
+
+#define FS_IOC_GETFLAGS _IOR('f', 1, long)
+#define FS_IOC_SETFLAGS _IOW('f', 2, long)
+#define FS_IOC_GETVERSION _IOR('v', 1, long)
+#define FS_IOC_SETVERSION _IOW('v', 2, long)
+#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
+#define FS_IOC32_GETVERSION _IOR('v', 1, int)
+#define FS_IOC32_SETVERSION _IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs). You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4. Also, we are
+ * almost out of 32-bit flags. :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface. This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define FS_SECRM_FL 0x00000001 /* Secure deletion */
+#define FS_UNRM_FL 0x00000002 /* Undelete */
+#define FS_COMPR_FL 0x00000004 /* Compress file */
+#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
+#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL 0x00000040 /* do not dump file */
+#define FS_NOATIME_FL 0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL 0x00000100
+#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */
+#define FS_BTREE_FL 0x00001000 /* btree format dir */
+#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL 0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL 0x00080000 /* Extents */
+#define FS_VERITY_FL 0x00100000 /* Verity protected inode */
+#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
+#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */
+#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE 1
+#define SYNC_FILE_RANGE_WRITE 2
+#define SYNC_FILE_RANGE_WAIT_AFTER 4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \
+ SYNC_FILE_RANGE_WAIT_BEFORE | \
+ SYNC_FILE_RANGE_WAIT_AFTER)
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+ RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
new file mode 100644
index 0000000..39ccfe9
--- /dev/null
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * fscrypt user API
+ *
+ * These ioctls can be used on filesystems that support fscrypt. See the
+ * "User API" section of Documentation/filesystems/fscrypt.rst.
+ */
+#ifndef _UAPI_LINUX_FSCRYPT_H
+#define _UAPI_LINUX_FSCRYPT_H
+
+#include <linux/types.h>
+
+/* Encryption policy flags */
+#define FSCRYPT_POLICY_FLAGS_PAD_4 0x00
+#define FSCRYPT_POLICY_FLAGS_PAD_8 0x01
+#define FSCRYPT_POLICY_FLAGS_PAD_16 0x02
+#define FSCRYPT_POLICY_FLAGS_PAD_32 0x03
+#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
+#define FSCRYPT_POLICY_FLAGS_VALID 0x07
+
+/* Encryption algorithms */
+#define FSCRYPT_MODE_AES_256_XTS 1
+#define FSCRYPT_MODE_AES_256_CTS 4
+#define FSCRYPT_MODE_AES_128_CBC 5
+#define FSCRYPT_MODE_AES_128_CTS 6
+#define FSCRYPT_MODE_ADIANTUM 9
+#define __FSCRYPT_MODE_MAX 9
+
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1 0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
+struct fscrypt_policy_v1 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+};
+#define fscrypt_policy fscrypt_policy_v1
+
+/*
+ * Process-subscribed "logon" key description prefix and payload format.
+ * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead.
+ */
+#define FSCRYPT_KEY_DESC_PREFIX "fscrypt:"
+#define FSCRYPT_KEY_DESC_PREFIX_SIZE 8
+#define FSCRYPT_MAX_KEY_SIZE 64
+struct fscrypt_key {
+ __u32 mode;
+ __u8 raw[FSCRYPT_MAX_KEY_SIZE];
+ __u32 size;
+};
+
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2 2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE 16
+struct fscrypt_policy_v2 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 __reserved[4];
+ __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+ __u64 policy_size; /* input/output */
+ union {
+ __u8 version;
+ struct fscrypt_policy_v1 v1;
+ struct fscrypt_policy_v2 v2;
+ } policy; /* output */
+};
+
+/*
+ * v1 policy keys are specified by an arbitrary 8-byte key "descriptor",
+ * matching fscrypt_policy_v1::master_key_descriptor.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1
+
+/*
+ * v2 policy keys are specified by a 16-byte key "identifier" which the kernel
+ * calculates as a cryptographic hash of the key itself,
+ * matching fscrypt_policy_v2::master_key_identifier.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2
+
+/*
+ * Specifies a key, either for v1 or v2 policies. This doesn't contain the
+ * actual key itself; this is just the "name" of the key.
+ */
+struct fscrypt_key_specifier {
+ __u32 type; /* one of FSCRYPT_KEY_SPEC_TYPE_* */
+ __u32 __reserved;
+ union {
+ __u8 __reserved[32]; /* reserve some extra space */
+ __u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+ __u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ } u;
+};
+
+/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
+struct fscrypt_add_key_arg {
+ struct fscrypt_key_specifier key_spec;
+ __u32 raw_size;
+ __u32 __reserved[9];
+ __u8 raw[];
+};
+
+/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
+struct fscrypt_remove_key_arg {
+ struct fscrypt_key_specifier key_spec;
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY 0x00000001
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS 0x00000002
+ __u32 removal_status_flags; /* output */
+ __u32 __reserved[5];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+ /* input */
+ struct fscrypt_key_specifier key_spec;
+ __u32 __reserved[6];
+
+ /* output */
+#define FSCRYPT_KEY_STATUS_ABSENT 1
+#define FSCRYPT_KEY_STATUS_PRESENT 2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
+ __u32 status;
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001
+ __u32 status_flags;
+ __u32 user_count;
+ __u32 __out_reserved[13];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
+#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS _IOWR('f', 25, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 26, struct fscrypt_get_key_status_arg)
+
+/**********************************************************************/
+
+/* old names; don't add anything new here! */
+#ifndef __KERNEL__
+#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
+#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
+#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
+#define FS_POLICY_FLAGS_PAD_16 FSCRYPT_POLICY_FLAGS_PAD_16
+#define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32
+#define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK
+#define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY
+#define FS_POLICY_FLAGS_VALID FSCRYPT_POLICY_FLAGS_VALID
+#define FS_ENCRYPTION_MODE_INVALID 0 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS
+#define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CBC 3 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CTS FSCRYPT_MODE_AES_256_CTS
+#define FS_ENCRYPTION_MODE_AES_128_CBC FSCRYPT_MODE_AES_128_CBC
+#define FS_ENCRYPTION_MODE_AES_128_CTS FSCRYPT_MODE_AES_128_CTS
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* removed */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* removed */
+#define FS_ENCRYPTION_MODE_ADIANTUM FSCRYPT_MODE_ADIANTUM
+#define FS_KEY_DESC_PREFIX FSCRYPT_KEY_DESC_PREFIX
+#define FS_KEY_DESC_PREFIX_SIZE FSCRYPT_KEY_DESC_PREFIX_SIZE
+#define FS_MAX_KEY_SIZE FSCRYPT_MAX_KEY_SIZE
+#endif /* !__KERNEL__ */
+
+#endif /* _UAPI_LINUX_FSCRYPT_H */
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 43391e2..4a8c02c 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -161,6 +161,7 @@
IFLA_EVENT,
IFLA_NEW_NETNSID,
IFLA_IF_NETNSID,
+ IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
IFLA_CARRIER_UP_COUNT,
IFLA_CARRIER_DOWN_COUNT,
IFLA_NEW_IFINDEX,
@@ -286,6 +287,8 @@
IFLA_BR_MCAST_STATS_ENABLED,
IFLA_BR_MCAST_IGMP_VERSION,
IFLA_BR_MCAST_MLD_VERSION,
+ IFLA_BR_VLAN_STATS_PER_PORT,
+ IFLA_BR_MULTI_BOOLOPT,
__IFLA_BR_MAX,
};
@@ -531,6 +534,7 @@
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
IFLA_VXLAN_TTL_INHERIT,
+ IFLA_VXLAN_DF,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
@@ -540,6 +544,14 @@
__be16 high;
};
+enum ifla_vxlan_df {
+ VXLAN_DF_UNSET = 0,
+ VXLAN_DF_SET,
+ VXLAN_DF_INHERIT,
+ __VXLAN_DF_END,
+ VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
/* GENEVE section */
enum {
IFLA_GENEVE_UNSPEC,
@@ -554,10 +566,20 @@
IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
IFLA_GENEVE_LABEL,
+ IFLA_GENEVE_TTL_INHERIT,
+ IFLA_GENEVE_DF,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+enum ifla_geneve_df {
+ GENEVE_DF_UNSET = 0,
+ GENEVE_DF_SET,
+ GENEVE_DF_INHERIT,
+ __GENEVE_DF_END,
+ GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
/* PPP section */
enum {
IFLA_PPP_UNSPEC,
@@ -614,6 +636,7 @@
IFLA_BOND_AD_USER_PORT_KEY,
IFLA_BOND_AD_ACTOR_SYSTEM,
IFLA_BOND_TLB_DYNAMIC_LB,
+ IFLA_BOND_PEER_NOTIF_DELAY,
__IFLA_BOND_MAX,
};
@@ -672,6 +695,7 @@
IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */
IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */
IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */
+ IFLA_VF_BROADCAST, /* VF broadcast */
__IFLA_VF_MAX,
};
@@ -682,6 +706,10 @@
__u8 mac[32]; /* MAX_ADDR_LEN */
};
+struct ifla_vf_broadcast {
+ __u8 broadcast[32];
+};
+
struct ifla_vf_vlan {
__u32 vf;
__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
@@ -903,6 +931,7 @@
enum {
LINK_XSTATS_TYPE_UNSPEC,
LINK_XSTATS_TYPE_BRIDGE,
+ LINK_XSTATS_TYPE_BOND,
__LINK_XSTATS_TYPE_MAX
};
#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
new file mode 100644
index 0000000..454ae31
--- /dev/null
+++ b/tools/include/uapi/linux/if_tun.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Universal TUN/TAP device driver.
+ * Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI__IF_TUN_H
+#define _UAPI__IF_TUN_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/filter.h>
+
+/* Read queue size */
+#define TUN_READQ_SIZE 500
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV IFF_TUN
+#define TUN_TAP_DEV IFF_TAP
+#define TUN_TYPE_MASK 0x000f
+
+/* Ioctl defines */
+#define TUNSETNOCSUM _IOW('T', 200, int)
+#define TUNSETDEBUG _IOW('T', 201, int)
+#define TUNSETIFF _IOW('T', 202, int)
+#define TUNSETPERSIST _IOW('T', 203, int)
+#define TUNSETOWNER _IOW('T', 204, int)
+#define TUNSETLINK _IOW('T', 205, int)
+#define TUNSETGROUP _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
+#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
+#define TUNGETIFF _IOR('T', 210, unsigned int)
+#define TUNGETSNDBUF _IOR('T', 211, int)
+#define TUNSETSNDBUF _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
+#define TUNSETIFINDEX _IOW('T', 218, unsigned int)
+#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
+#define TUNSETSTEERINGEBPF _IOR('T', 224, int)
+#define TUNSETFILTEREBPF _IOR('T', 225, int)
+#define TUNSETCARRIER _IOW('T', 226, int)
+#define TUNGETDEVNETNS _IO('T', 227)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TUN 0x0001
+#define IFF_TAP 0x0002
+#define IFF_NAPI 0x0010
+#define IFF_NAPI_FRAGS 0x0020
+#define IFF_NO_PI 0x1000
+/* This flag has no real effect */
+#define IFF_ONE_QUEUE 0x2000
+#define IFF_VNET_HDR 0x4000
+#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+/* read-only flag */
+#define IFF_PERSIST 0x0800
+#define IFF_NOFILTER 0x1000
+
+/* Socket options */
+#define TUN_TX_TIMESTAMP 1
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */
+#define TUN_F_UFO 0x10 /* I can handle UFO packets */
+
+/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
+#define TUN_PKT_STRIP 0x0001
+struct tun_pi {
+ __u16 flags;
+ __be16 proto;
+};
+
+/*
+ * Filter spec (used for SETXXFILTER ioctls)
+ * This stuff is applicable only to the TAP (Ethernet) devices.
+ * If the count is zero the filter is disabled and the driver accepts
+ * all packets (promisc mode).
+ * If the filter is enabled in order to accept broadcast packets
+ * broadcast addr must be explicitly included in the addr list.
+ */
+#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
+struct tun_filter {
+ __u16 flags; /* TUN_FLT_ flags see above */
+ __u16 count; /* Number of addresses */
+ __u8 addr[0][ETH_ALEN];
+};
+
+#endif /* _UAPI__IF_TUN_H */
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
new file mode 100644
index 0000000..be328c5
--- /dev/null
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ * Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* Options for the sxdp_flags field */
+#define XDP_SHARED_UMEM (1 << 0)
+#define XDP_COPY (1 << 1) /* Force copy-mode */
+#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */
+/* If this option is set, the driver might go sleep and in that case
+ * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be
+ * set. If it is set, the application need to explicitly wake up the
+ * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are
+ * running the driver and the application on the same core, you should
+ * use this option so that the kernel will yield to the user space
+ * application.
+ */
+#define XDP_USE_NEED_WAKEUP (1 << 3)
+
+/* Flags for xsk_umem_config flags */
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+
+struct sockaddr_xdp {
+ __u16 sxdp_family;
+ __u16 sxdp_flags;
+ __u32 sxdp_ifindex;
+ __u32 sxdp_queue_id;
+ __u32 sxdp_shared_umem_fd;
+};
+
+/* XDP_RING flags */
+#define XDP_RING_NEED_WAKEUP (1 << 0)
+
+struct xdp_ring_offset {
+ __u64 producer;
+ __u64 consumer;
+ __u64 desc;
+ __u64 flags;
+};
+
+struct xdp_mmap_offsets {
+ struct xdp_ring_offset rx;
+ struct xdp_ring_offset tx;
+ struct xdp_ring_offset fr; /* Fill */
+ struct xdp_ring_offset cr; /* Completion */
+};
+
+/* XDP socket options */
+#define XDP_MMAP_OFFSETS 1
+#define XDP_RX_RING 2
+#define XDP_TX_RING 3
+#define XDP_UMEM_REG 4
+#define XDP_UMEM_FILL_RING 5
+#define XDP_UMEM_COMPLETION_RING 6
+#define XDP_STATISTICS 7
+#define XDP_OPTIONS 8
+
+struct xdp_umem_reg {
+ __u64 addr; /* Start of packet data area */
+ __u64 len; /* Length of packet data area */
+ __u32 chunk_size;
+ __u32 headroom;
+ __u32 flags;
+};
+
+struct xdp_statistics {
+ __u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+ __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
+ __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+};
+
+struct xdp_options {
+ __u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
+/* Pgoff for mmaping the rings */
+#define XDP_PGOFF_RX_RING 0
+#define XDP_PGOFF_TX_RING 0x80000000
+#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL
+#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL
+
+/* Masks for unaligned chunks mode */
+#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48
+#define XSK_UNALIGNED_BUF_ADDR_MASK \
+ ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+
+/* Rx/Tx descriptor */
+struct xdp_desc {
+ __u64 addr;
+ __u32 len;
+ __u32 options;
+};
+
+/* UMEM descriptor is __u64 */
+
+#endif /* _LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 48e8a22..e7ad9d3 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -266,10 +266,14 @@
#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000)
#define IN_MULTICAST(a) IN_CLASSD(a)
-#define IN_MULTICAST_NET 0xF0000000
+#define IN_MULTICAST_NET 0xe0000000
-#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
-#define IN_BADCLASS(a) IN_EXPERIMENTAL((a))
+#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff)
+#define IN_EXPERIMENTAL(a) IN_BADCLASS((a))
+
+#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_CLASSE_NET 0xffffffff
+#define IN_CLASSE_NSHIFT 0
/* Address to accept any incoming messages. */
#define INADDR_ANY ((unsigned long int) 0x00000000)
@@ -288,10 +292,11 @@
#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000)
/* Defines for Multicast INADDR */
-#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
-#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
-#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
-#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
+#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */
+#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */
+#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */
+#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */
#endif
/* <asm/byteorder.h> contains the htonl type stuff.. */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 251be35..52641d8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -116,7 +116,7 @@
* ACPI gsi notion of irq.
* For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
* For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
- * For ARM: See Documentation/virtual/kvm/api.txt
+ * For ARM: See Documentation/virt/kvm/api.txt
*/
union {
__u32 irq;
@@ -243,6 +243,8 @@
#define KVM_INTERNAL_ERROR_SIMUL_EX 2
/* Encounter unexpected vm-exit due to delivery event. */
#define KVM_INTERNAL_ERROR_DELIVERY_EV 3
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4
/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
struct kvm_run {
@@ -420,13 +422,19 @@
struct kvm_coalesced_mmio_zone {
__u64 addr;
__u32 size;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
};
struct kvm_coalesced_mmio {
__u64 phys_addr;
__u32 len;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
__u8 data[8];
};
@@ -486,6 +494,17 @@
};
};
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
/* for KVM_SET_SIGNAL_MASK */
struct kvm_signal_mask {
__u32 len;
@@ -679,9 +698,11 @@
#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
KVM_X86_DISABLE_EXITS_HLT | \
- KVM_X86_DISABLE_EXITS_PAUSE)
+ KVM_X86_DISABLE_EXITS_PAUSE | \
+ KVM_X86_DISABLE_EXITS_CSTATE)
/* for KVM_ENABLE_CAP */
struct kvm_enable_cap {
@@ -719,6 +740,7 @@
#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
struct kvm_ppc_smmu_info {
__u64 flags;
@@ -751,6 +773,15 @@
#define KVM_S390_SIE_PAGE_OFFSET 1
/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#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)
+/*
* ioctls for /dev/kvm fds:
*/
#define KVM_GET_API_VERSION _IO(KVMIO, 0x00)
@@ -953,6 +984,22 @@
#define KVM_CAP_NESTED_STATE 157
#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
#define KVM_CAP_MSR_PLATFORM_INFO 159
+#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */
+#define KVM_CAP_HYPERV_CPUID 167
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168
+#define KVM_CAP_PPC_IRQ_XIVE 169
+#define KVM_CAP_ARM_SVE 170
+#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
+#define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1043,7 +1090,7 @@
*
* KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
* the irqfd to operate in resampling mode for level triggered interrupt
- * emulation. See Documentation/virtual/kvm/api.txt.
+ * emulation. See Documentation/virt/kvm/api.txt.
*/
#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
@@ -1099,6 +1146,7 @@
#define KVM_REG_S390 0x5000000000000000ULL
#define KVM_REG_ARM64 0x6000000000000000ULL
#define KVM_REG_MIPS 0x7000000000000000ULL
+#define KVM_REG_RISCV 0x8000000000000000ULL
#define KVM_REG_SIZE_SHIFT 52
#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL
@@ -1110,6 +1158,7 @@
#define KVM_REG_SIZE_U256 0x0050000000000000ULL
#define KVM_REG_SIZE_U512 0x0060000000000000ULL
#define KVM_REG_SIZE_U1024 0x0070000000000000ULL
+#define KVM_REG_SIZE_U2048 0x0080000000000000ULL
struct kvm_reg_list {
__u64 n; /* number of regs */
@@ -1176,6 +1225,8 @@
#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3
KVM_DEV_TYPE_ARM_VGIC_ITS,
#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
+ KVM_DEV_TYPE_XIVE,
+#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
KVM_DEV_TYPE_MAX,
};
@@ -1284,6 +1335,8 @@
#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info)
/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
/* ioctl for vm fd */
#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)
@@ -1399,6 +1452,15 @@
#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state)
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
+#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
+/* Available with KVM_CAP_ARM_SVE */
+#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h
index f189931..45fcbf9 100644
--- a/tools/include/uapi/linux/lirc.h
+++ b/tools/include/uapi/linux/lirc.h
@@ -134,6 +134,12 @@
#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
/*
+ * Return the recording timeout, which is either set by
+ * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols.
+ */
+#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32)
+
+/*
* struct lirc_scancode - decoded scancode with protocol for use with
* LIRC_MODE_SCANCODE
*
@@ -186,6 +192,9 @@
* @RC_PROTO_XMP: XMP protocol
* @RC_PROTO_CEC: CEC protocol
* @RC_PROTO_IMON: iMon Pad protocol
+ * @RC_PROTO_RCMM12: RC-MM protocol 12 bits
+ * @RC_PROTO_RCMM24: RC-MM protocol 24 bits
+ * @RC_PROTO_RCMM32: RC-MM protocol 32 bits
*/
enum rc_proto {
RC_PROTO_UNKNOWN = 0,
@@ -212,6 +221,9 @@
RC_PROTO_XMP = 21,
RC_PROTO_CEC = 22,
RC_PROTO_IMON = 23,
+ RC_PROTO_RCMM12 = 24,
+ RC_PROTO_RCMM24 = 25,
+ RC_PROTO_RCMM32 = 26,
};
#endif
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index bfd5938..fc1a64c 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -12,6 +12,10 @@
#define OVERCOMMIT_ALWAYS 1
#define OVERCOMMIT_NEVER 2
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+
/*
* Huge page size encoding when MAP_HUGETLB is specified, and a huge page
* size other than the default is desired. See hugetlb_encode.h.
@@ -28,7 +32,9 @@
#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB
#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB
#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB
#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB
#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB
#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
new file mode 100644
index 0000000..96a0240
--- /dev/null
+++ b/tools/include/uapi/linux/mount.h
@@ -0,0 +1,120 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only. Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY 1 /* Mount read-only */
+#define MS_NOSUID 2 /* Ignore suid and sgid bits */
+#define MS_NODEV 4 /* Disallow access to device special files */
+#define MS_NOEXEC 8 /* Disallow program execution */
+#define MS_SYNCHRONOUS 16 /* Writes are synced at once */
+#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
+#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
+#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
+#define MS_NOATIME 1024 /* Do not update access times. */
+#define MS_NODIRATIME 2048 /* Do not update directory access times */
+#define MS_BIND 4096
+#define MS_MOVE 8192
+#define MS_REC 16384
+#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence.
+ MS_VERBOSE is deprecated. */
+#define MS_SILENT 32768
+#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
+#define MS_UNBINDABLE (1<<17) /* change to unbindable */
+#define MS_PRIVATE (1<<18) /* change to private */
+#define MS_SLAVE (1<<19) /* change to slave */
+#define MS_SHARED (1<<20) /* change to shared */
+#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION (1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT (1<<26)
+#define MS_NOREMOTELOCK (1<<27)
+#define MS_NOSEC (1<<28)
+#define MS_BORN (1<<29)
+#define MS_ACTIVE (1<<30)
+#define MS_NOUSER (1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+ MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */
+
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT__MASK 0x00000077
+
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC 0x00000001
+
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC 0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW 0x00000002
+#define FSPICK_NO_AUTOMOUNT 0x00000004
+#define FSPICK_EMPTY_PATH 0x00000008
+
+/*
+ * The type of fsconfig() call made.
+ */
+enum fsconfig_command {
+ FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */
+ FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */
+ FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */
+ 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_RECONFIGURE = 7, /* Invoke superblock reconfiguration */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC 0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
index 776bc92..0a4d733 100644
--- a/tools/include/uapi/linux/netlink.h
+++ b/tools/include/uapi/linux/netlink.h
@@ -155,6 +155,7 @@
#define NETLINK_LIST_MEMBERSHIPS 9
#define NETLINK_CAP_ACK 10
#define NETLINK_EXT_ACK 11
+#define NETLINK_GET_STRICT_CHK 12
struct nl_pktinfo {
__u32 group;
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72..bb7b271 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -372,7 +372,10 @@
context_switch : 1, /* context switch data */
write_backward : 1, /* Write ring buffer from end to beginning */
namespaces : 1, /* include namespaces data */
- __reserved_1 : 35;
+ ksymbol : 1, /* include ksymbol events */
+ bpf_event : 1, /* include bpf events */
+ aux_output : 1, /* generate AUX records instead of events */
+ __reserved_1 : 32;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -445,8 +448,6 @@
__u32 ids[0];
};
-#define perf_flags(attr) (*(&(attr)->read_format + 1))
-
/*
* Ioctls that can be done on a perf event fd:
*/
@@ -646,10 +647,12 @@
*
* PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events
* PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event
+ * PERF_RECORD_MISC_FORK_EXEC - PERF_RECORD_FORK event (perf internal)
* PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
*/
#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
#define PERF_RECORD_MISC_COMM_EXEC (1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC (1 << 13)
#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13)
/*
* These PERF_RECORD_MISC_* flags below are safely reused
@@ -963,9 +966,58 @@
*/
PERF_RECORD_NAMESPACES = 16,
+ /*
+ * Record ksymbol register/unregister events:
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 addr;
+ * u32 len;
+ * u16 ksym_type;
+ * u16 flags;
+ * char name[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_KSYMBOL = 17,
+
+ /*
+ * Record bpf events:
+ * enum perf_bpf_event_type {
+ * PERF_BPF_EVENT_UNKNOWN = 0,
+ * PERF_BPF_EVENT_PROG_LOAD = 1,
+ * PERF_BPF_EVENT_PROG_UNLOAD = 2,
+ * };
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u16 type;
+ * u16 flags;
+ * u32 id;
+ * u8 tag[BPF_TAG_SIZE];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_BPF_EVENT = 18,
+
PERF_RECORD_MAX, /* non-ABI */
};
+enum perf_record_ksymbol_type {
+ PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0,
+ PERF_RECORD_KSYMBOL_TYPE_BPF = 1,
+ PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */
+};
+
+#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0)
+
+enum perf_bpf_event_type {
+ PERF_BPF_EVENT_UNKNOWN = 0,
+ PERF_BPF_EVENT_PROG_LOAD = 1,
+ PERF_BPF_EVENT_PROG_UNLOAD = 2,
+ PERF_BPF_EVENT_MAX, /* non-ABI */
+};
+
#define PERF_MAX_STACK_DEPTH 127
#define PERF_MAX_CONTEXTS_PER_STACK 8
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 0000000..1215377
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+ TCA_ACT_UNSPEC,
+ TCA_ACT_KIND,
+ TCA_ACT_OPTIONS,
+ TCA_ACT_INDEX,
+ TCA_ACT_STATS,
+ TCA_ACT_PAD,
+ TCA_ACT_COOKIE,
+ __TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND 1
+#define TCA_ACT_NOBIND 0
+#define TCA_ACT_UNBIND 1
+#define TCA_ACT_NOUNBIND 0
+#define TCA_ACT_REPLACE 1
+#define TCA_ACT_NOREPLACE 0
+
+#define TC_ACT_UNSPEC (-1)
+#define TC_ACT_OK 0
+#define TC_ACT_RECLASSIFY 1
+#define TC_ACT_SHOT 2
+#define TC_ACT_PIPE 3
+#define TC_ACT_STOLEN 4
+#define TC_ACT_QUEUED 5
+#define TC_ACT_REPEAT 6
+#define TC_ACT_REDIRECT 7
+#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu"
+ * and don't further process the frame
+ * in hardware. For sw path, this is
+ * equivalent of TC_ACT_STOLEN - drop
+ * the skb and act like everything
+ * is alright.
+ */
+#define TC_ACT_VALUE_MAX TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+ TCA_ID_UNSPEC=0,
+ TCA_ID_POLICE=1,
+ /* other actions go here */
+ __TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+ __u32 index;
+ int action;
+#define TC_POLICE_UNSPEC TC_ACT_UNSPEC
+#define TC_POLICE_OK TC_ACT_OK
+#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT TC_ACT_SHOT
+#define TC_POLICE_PIPE TC_ACT_PIPE
+
+ __u32 limit;
+ __u32 burst;
+ __u32 mtu;
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ int refcnt;
+ int bindcnt;
+ __u32 capab;
+};
+
+struct tcf_t {
+ __u64 install;
+ __u64 lastuse;
+ __u64 expires;
+ __u64 firstuse;
+};
+
+struct tc_cnt {
+ int refcnt;
+ int bindcnt;
+};
+
+#define tc_gen \
+ __u32 index; \
+ __u32 capab; \
+ int action; \
+ int refcnt; \
+ int bindcnt
+
+enum {
+ TCA_POLICE_UNSPEC,
+ TCA_POLICE_TBF,
+ TCA_POLICE_RATE,
+ TCA_POLICE_PEAKRATE,
+ TCA_POLICE_AVRATE,
+ TCA_POLICE_RESULT,
+ TCA_POLICE_TM,
+ TCA_POLICE_PAD,
+ __TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC 0
+#define TC_U32_ROOT (0xFFF00000)
+
+enum {
+ TCA_U32_UNSPEC,
+ TCA_U32_CLASSID,
+ TCA_U32_HASH,
+ TCA_U32_LINK,
+ TCA_U32_DIVISOR,
+ TCA_U32_SEL,
+ TCA_U32_POLICE,
+ TCA_U32_ACT,
+ TCA_U32_INDEV,
+ TCA_U32_PCNT,
+ TCA_U32_MARK,
+ TCA_U32_FLAGS,
+ TCA_U32_PAD,
+ __TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+ __be32 mask;
+ __be32 val;
+ int off;
+ int offmask;
+};
+
+struct tc_u32_sel {
+ unsigned char flags;
+ unsigned char offshift;
+ unsigned char nkeys;
+
+ __be16 offmask;
+ __u16 off;
+ short offoff;
+
+ short hoff;
+ __be32 hmask;
+ struct tc_u32_key keys[0];
+};
+
+struct tc_u32_mark {
+ __u32 val;
+ __u32 mask;
+ __u32 success;
+};
+
+struct tc_u32_pcnt {
+ __u64 rcnt;
+ __u64 rhit;
+ __u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL 1
+#define TC_U32_OFFSET 2
+#define TC_U32_VAROFFSET 4
+#define TC_U32_EAT 8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+ TCA_RSVP_UNSPEC,
+ TCA_RSVP_CLASSID,
+ TCA_RSVP_DST,
+ TCA_RSVP_SRC,
+ TCA_RSVP_PINFO,
+ TCA_RSVP_POLICE,
+ TCA_RSVP_ACT,
+ __TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+ __u32 key;
+ __u32 mask;
+ int offset;
+};
+
+struct tc_rsvp_pinfo {
+ struct tc_rsvp_gpi dpi;
+ struct tc_rsvp_gpi spi;
+ __u8 protocol;
+ __u8 tunnelid;
+ __u8 tunnelhdr;
+ __u8 pad;
+};
+
+/* ROUTE filter */
+
+enum {
+ TCA_ROUTE4_UNSPEC,
+ TCA_ROUTE4_CLASSID,
+ TCA_ROUTE4_TO,
+ TCA_ROUTE4_FROM,
+ TCA_ROUTE4_IIF,
+ TCA_ROUTE4_POLICE,
+ TCA_ROUTE4_ACT,
+ __TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+ TCA_FW_UNSPEC,
+ TCA_FW_CLASSID,
+ TCA_FW_POLICE,
+ TCA_FW_INDEV,
+ TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+ TCA_FW_MASK,
+ __TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+ TCA_TCINDEX_UNSPEC,
+ TCA_TCINDEX_HASH,
+ TCA_TCINDEX_MASK,
+ TCA_TCINDEX_SHIFT,
+ TCA_TCINDEX_FALL_THROUGH,
+ TCA_TCINDEX_CLASSID,
+ TCA_TCINDEX_POLICE,
+ TCA_TCINDEX_ACT,
+ __TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+ FLOW_KEY_SRC,
+ FLOW_KEY_DST,
+ FLOW_KEY_PROTO,
+ FLOW_KEY_PROTO_SRC,
+ FLOW_KEY_PROTO_DST,
+ FLOW_KEY_IIF,
+ FLOW_KEY_PRIORITY,
+ FLOW_KEY_MARK,
+ FLOW_KEY_NFCT,
+ FLOW_KEY_NFCT_SRC,
+ FLOW_KEY_NFCT_DST,
+ FLOW_KEY_NFCT_PROTO_SRC,
+ FLOW_KEY_NFCT_PROTO_DST,
+ FLOW_KEY_RTCLASSID,
+ FLOW_KEY_SKUID,
+ FLOW_KEY_SKGID,
+ FLOW_KEY_VLAN_TAG,
+ FLOW_KEY_RXHASH,
+ __FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1)
+
+enum {
+ FLOW_MODE_MAP,
+ FLOW_MODE_HASH,
+};
+
+enum {
+ TCA_FLOW_UNSPEC,
+ TCA_FLOW_KEYS,
+ TCA_FLOW_MODE,
+ TCA_FLOW_BASECLASS,
+ TCA_FLOW_RSHIFT,
+ TCA_FLOW_ADDEND,
+ TCA_FLOW_MASK,
+ TCA_FLOW_XOR,
+ TCA_FLOW_DIVISOR,
+ TCA_FLOW_ACT,
+ TCA_FLOW_POLICE,
+ TCA_FLOW_EMATCHES,
+ TCA_FLOW_PERTURB,
+ __TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+ TCA_BASIC_UNSPEC,
+ TCA_BASIC_CLASSID,
+ TCA_BASIC_EMATCHES,
+ TCA_BASIC_ACT,
+ TCA_BASIC_POLICE,
+ __TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+ TCA_CGROUP_UNSPEC,
+ TCA_CGROUP_ACT,
+ TCA_CGROUP_POLICE,
+ TCA_CGROUP_EMATCHES,
+ __TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0)
+
+enum {
+ TCA_BPF_UNSPEC,
+ TCA_BPF_ACT,
+ TCA_BPF_POLICE,
+ TCA_BPF_CLASSID,
+ TCA_BPF_OPS_LEN,
+ TCA_BPF_OPS,
+ TCA_BPF_FD,
+ TCA_BPF_NAME,
+ TCA_BPF_FLAGS,
+ TCA_BPF_FLAGS_GEN,
+ TCA_BPF_TAG,
+ TCA_BPF_ID,
+ __TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+ TCA_FLOWER_UNSPEC,
+ TCA_FLOWER_CLASSID,
+ TCA_FLOWER_INDEV,
+ TCA_FLOWER_ACT,
+ TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_TYPE, /* be16 */
+ TCA_FLOWER_KEY_IP_PROTO, /* u8 */
+ TCA_FLOWER_KEY_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_TCP_SRC, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST, /* be16 */
+
+ TCA_FLOWER_FLAGS,
+ TCA_FLOWER_KEY_VLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+ TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_SCTP_SRC, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_FLAGS, /* be32 */
+ TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */
+
+ TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+ TCA_FLOWER_KEY_ARP_SIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_OP, /* u8 */
+ TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */
+ TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */
+
+ TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */
+ TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */
+ TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */
+ TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */
+
+ TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */
+ TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_CVLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_ENC_OPTS,
+ TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+ TCA_FLOWER_IN_HW_COUNT,
+
+ __TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+ * attributes
+ */
+ __TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */
+
+ __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+ TCA_MATCHALL_UNSPEC,
+ TCA_MATCHALL_CLASSID,
+ TCA_MATCHALL_ACT,
+ TCA_MATCHALL_FLAGS,
+ __TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+ __u16 nmatches;
+ __u16 progid;
+};
+
+enum {
+ TCA_EMATCH_TREE_UNSPEC,
+ TCA_EMATCH_TREE_HDR,
+ TCA_EMATCH_TREE_LIST,
+ __TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+ __u16 matchid;
+ __u16 kind;
+ __u16 flags;
+ __u16 pad; /* currently unused */
+};
+
+/* 0 1
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
+ * +-----------------------+-+-+---+
+ * | Unused |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ * where: 0 0 END (last ematch)
+ * 0 1 AND
+ * 1 0 OR
+ * 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END 0
+#define TCF_EM_REL_AND (1<<0)
+#define TCF_EM_REL_OR (1<<1)
+#define TCF_EM_INVERT (1<<2)
+#define TCF_EM_SIMPLE (1<<3)
+
+#define TCF_EM_REL_MASK 3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+ TCF_LAYER_LINK,
+ TCF_LAYER_NETWORK,
+ TCF_LAYER_TRANSPORT,
+ __TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ * 1..32767 Reserved for ematches inside kernel tree
+ * 32768..65535 Free to use, not reliable
+ */
+#define TCF_EM_CONTAINER 0
+#define TCF_EM_CMP 1
+#define TCF_EM_NBYTE 2
+#define TCF_EM_U32 3
+#define TCF_EM_META 4
+#define TCF_EM_TEXT 5
+#define TCF_EM_VLAN 6
+#define TCF_EM_CANID 7
+#define TCF_EM_IPSET 8
+#define TCF_EM_IPT 9
+#define TCF_EM_MAX 9
+
+enum {
+ TCF_EM_PROG_TC
+};
+
+enum {
+ TCF_EM_OPND_EQ,
+ TCF_EM_OPND_GT,
+ TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
new file mode 100644
index 0000000..0d18b1d
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -0,0 +1,1163 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+ Every scheduler will map them to real traffic classes, if it has
+ no more precise mechanism to classify packets.
+
+ These numbers have no special meaning, though their coincidence
+ with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+ preferred full anarchy inspired by diffserv group.
+
+ Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+ class, actually, as rule it will be handled with more care than
+ filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT 0
+#define TC_PRIO_FILLER 1
+#define TC_PRIO_BULK 2
+#define TC_PRIO_INTERACTIVE_BULK 4
+#define TC_PRIO_INTERACTIVE 6
+#define TC_PRIO_CONTROL 7
+
+#define TC_PRIO_MAX 15
+
+/* Generic queue statistics, available for all the elements.
+ Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+ __u64 bytes; /* Number of enqueued bytes */
+ __u32 packets; /* Number of enqueued packets */
+ __u32 drops; /* Packets dropped because of lack of resources */
+ __u32 overlimits; /* Number of throttle events when this
+ * flow goes out of allocated bandwidth */
+ __u32 bps; /* Current flow byte rate */
+ __u32 pps; /* Current flow packet rate */
+ __u32 qlen;
+ __u32 backlog;
+};
+
+struct tc_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+/* "Handles"
+ ---------
+
+ All the traffic control objects have 32bit identifiers, or "handles".
+
+ They can be considered as opaque numbers from user API viewpoint,
+ but actually they always consist of two fields: major and
+ minor numbers, which are interpreted by kernel specially,
+ that may be used by applications, though not recommended.
+
+ F.e. qdisc handles always have minor number equal to zero,
+ classes (or flows) have major equal to parent qdisc major, and
+ minor uniquely identifying class inside qdisc.
+
+ Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC (0U)
+#define TC_H_ROOT (0xFFFFFFFFU)
+#define TC_H_INGRESS (0xFFFFFFF1U)
+#define TC_H_CLSACT TC_H_INGRESS
+
+#define TC_H_MIN_PRIORITY 0xFFE0U
+#define TC_H_MIN_INGRESS 0xFFF2U
+#define TC_H_MIN_EGRESS 0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+ unsigned char cell_log;
+ __u8 linklayer; /* lower 4 bits */
+ unsigned short overhead;
+ short cell_align;
+ unsigned short mpu;
+ __u32 rate;
+};
+
+#define TC_RTAB_SIZE 1024
+
+struct tc_sizespec {
+ unsigned char cell_log;
+ unsigned char size_log;
+ short cell_align;
+ int overhead;
+ unsigned int linklayer;
+ unsigned int mpu;
+ unsigned int mtu;
+ unsigned int tsize;
+};
+
+enum {
+ TCA_STAB_UNSPEC,
+ TCA_STAB_BASE,
+ TCA_STAB_DATA,
+ __TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+ __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+ __u32 limit; /* Queue length in packets. */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS 16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+ int bands; /* Number of bands */
+ __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+ __u16 bands; /* Number of bands */
+ __u16 max_bands; /* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER 0
+#define TCQ_PLUG_RELEASE_ONE 1
+#define TCQ_PLUG_RELEASE_INDEFINITE 2
+#define TCQ_PLUG_LIMIT 3
+
+struct tc_plug_qopt {
+ /* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+ * buffer any incoming packets
+ * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+ * to beginning of the next plug.
+ * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+ * Stop buffering packets until the next TCQ_PLUG_BUFFER
+ * command is received (just act as a pass-thru queue).
+ * TCQ_PLUG_LIMIT: Increase/decrease queue size
+ */
+ int action;
+ __u32 limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ __u32 limit;
+ __u32 buffer;
+ __u32 mtu;
+};
+
+enum {
+ TCA_TBF_UNSPEC,
+ TCA_TBF_PARMS,
+ TCA_TBF_RTAB,
+ TCA_TBF_PTAB,
+ TCA_TBF_RATE64,
+ TCA_TBF_PRATE64,
+ TCA_TBF_BURST,
+ TCA_TBF_PBURST,
+ TCA_TBF_PAD,
+ __TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+ unsigned quantum; /* Bytes per round allocated to flow */
+ int perturb_period; /* Period of hash perturbation */
+ __u32 limit; /* Maximal packets in queue */
+ unsigned divisor; /* Hash divisor */
+ unsigned flows; /* Maximal number of flows */
+};
+
+struct tc_sfqred_stats {
+ __u32 prob_drop; /* Early drops, below max threshold */
+ __u32 forced_drop; /* Early drops, after max threshold */
+ __u32 prob_mark; /* Marked packets, below max threshold */
+ __u32 forced_mark; /* Marked packets, after max threshold */
+ __u32 prob_mark_head; /* Marked packets, below max threshold */
+ __u32 forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+ struct tc_sfq_qopt v0;
+ unsigned int depth; /* max number of packets per flow */
+ unsigned int headdrop;
+/* SFQRED parameters */
+ __u32 limit; /* HARD maximal flow queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+ __u32 max_P; /* probability, high resolution */
+/* SFQRED stats */
+ struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+ __s32 allot;
+};
+
+/* RED section */
+
+enum {
+ TCA_RED_UNSPEC,
+ TCA_RED_PARMS,
+ TCA_RED_STAB,
+ TCA_RED_MAX_P,
+ __TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+#define TC_RED_ECN 1
+#define TC_RED_HARDDROP 2
+#define TC_RED_ADAPTATIVE 4
+};
+
+struct tc_red_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+ TCA_GRED_UNSPEC,
+ TCA_GRED_PARMS,
+ TCA_GRED_STAB,
+ TCA_GRED_DPS,
+ TCA_GRED_MAX_P,
+ TCA_GRED_LIMIT,
+ TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */
+ __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_ENTRY_UNSPEC,
+ TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */
+ __TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_UNSPEC,
+ TCA_GRED_VQ_PAD,
+ TCA_GRED_VQ_DP, /* u32 */
+ TCA_GRED_VQ_STAT_BYTES, /* u64 */
+ TCA_GRED_VQ_STAT_PACKETS, /* u32 */
+ TCA_GRED_VQ_STAT_BACKLOG, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_PDROP, /* u32 */
+ TCA_GRED_VQ_STAT_OTHER, /* u32 */
+ TCA_GRED_VQ_FLAGS, /* u32 */
+ __TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
+struct tc_gred_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ __u32 DP; /* up to 2^32 DPs */
+ __u32 backlog;
+ __u32 qave;
+ __u32 forced;
+ __u32 early;
+ __u32 other;
+ __u32 pdrop;
+ __u8 Wlog; /* log(W) */
+ __u8 Plog; /* log(P_max/(qth_max-qth_min)) */
+ __u8 Scell_log; /* cell size for idle damping */
+ __u8 prio; /* prio of this VQ */
+ __u32 packets;
+ __u32 bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+ __u32 DPs;
+ __u32 def_DP;
+ __u8 grio;
+ __u8 flags;
+ __u16 pad1;
+};
+
+/* CHOKe section */
+
+enum {
+ TCA_CHOKE_UNSPEC,
+ TCA_CHOKE_PARMS,
+ TCA_CHOKE_STAB,
+ TCA_CHOKE_MAX_P,
+ __TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+ __u32 limit; /* Hard queue length (packets) */
+ __u32 qth_min; /* Min average threshold (packets) */
+ __u32 qth_max; /* Max average threshold (packets) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags; /* see RED flags */
+};
+
+struct tc_choke_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+ __u32 matched; /* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO 8
+#define TC_HTB_MAXDEPTH 8
+#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+ struct tc_ratespec rate;
+ struct tc_ratespec ceil;
+ __u32 buffer;
+ __u32 cbuffer;
+ __u32 quantum;
+ __u32 level; /* out only */
+ __u32 prio;
+};
+struct tc_htb_glob {
+ __u32 version; /* to match HTB/TC */
+ __u32 rate2quantum; /* bps->quantum divisor */
+ __u32 defcls; /* default class number */
+ __u32 debug; /* debug flags */
+
+ /* stats */
+ __u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+ TCA_HTB_UNSPEC,
+ TCA_HTB_PARMS,
+ TCA_HTB_INIT,
+ TCA_HTB_CTAB,
+ TCA_HTB_RTAB,
+ TCA_HTB_DIRECT_QLEN,
+ TCA_HTB_RATE64,
+ TCA_HTB_CEIL64,
+ TCA_HTB_PAD,
+ __TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+ __u32 lends;
+ __u32 borrows;
+ __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */
+ __s32 tokens;
+ __s32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+ __u16 defcls; /* default class */
+};
+
+struct tc_service_curve {
+ __u32 m1; /* slope of the first segment in bps */
+ __u32 d; /* x-projection of the first segment in us */
+ __u32 m2; /* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+ __u64 work; /* total work done */
+ __u64 rtwork; /* work done by real-time criteria */
+ __u32 period; /* current period */
+ __u32 level; /* class level in hierarchy */
+};
+
+enum {
+ TCA_HFSC_UNSPEC,
+ TCA_HFSC_RSC,
+ TCA_HFSC_FSC,
+ TCA_HFSC_USC,
+ __TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO 8
+#define TC_CBQ_MAXLEVEL 8
+#define TC_CBQ_DEF_EWMA 5
+
+struct tc_cbq_lssopt {
+ unsigned char change;
+ unsigned char flags;
+#define TCF_CBQ_LSS_BOUNDED 1
+#define TCF_CBQ_LSS_ISOLATED 2
+ unsigned char ewma_log;
+ unsigned char level;
+#define TCF_CBQ_LSS_FLAGS 1
+#define TCF_CBQ_LSS_EWMA 2
+#define TCF_CBQ_LSS_MAXIDLE 4
+#define TCF_CBQ_LSS_MINIDLE 8
+#define TCF_CBQ_LSS_OFFTIME 0x10
+#define TCF_CBQ_LSS_AVPKT 0x20
+ __u32 maxidle;
+ __u32 minidle;
+ __u32 offtime;
+ __u32 avpkt;
+};
+
+struct tc_cbq_wrropt {
+ unsigned char flags;
+ unsigned char priority;
+ unsigned char cpriority;
+ unsigned char __reserved;
+ __u32 allot;
+ __u32 weight;
+};
+
+struct tc_cbq_ovl {
+ unsigned char strategy;
+#define TC_CBQ_OVL_CLASSIC 0
+#define TC_CBQ_OVL_DELAY 1
+#define TC_CBQ_OVL_LOWPRIO 2
+#define TC_CBQ_OVL_DROP 3
+#define TC_CBQ_OVL_RCLASSIC 4
+ unsigned char priority2;
+ __u16 pad;
+ __u32 penalty;
+};
+
+struct tc_cbq_police {
+ unsigned char police;
+ unsigned char __res1;
+ unsigned short __res2;
+};
+
+struct tc_cbq_fopt {
+ __u32 split;
+ __u32 defmap;
+ __u32 defchange;
+};
+
+struct tc_cbq_xstats {
+ __u32 borrows;
+ __u32 overactions;
+ __s32 avgidle;
+ __s32 undertime;
+};
+
+enum {
+ TCA_CBQ_UNSPEC,
+ TCA_CBQ_LSSOPT,
+ TCA_CBQ_WRROPT,
+ TCA_CBQ_FOPT,
+ TCA_CBQ_OVL_STRATEGY,
+ TCA_CBQ_RATE,
+ TCA_CBQ_RTAB,
+ TCA_CBQ_POLICE,
+ __TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+ TCA_DSMARK_UNSPEC,
+ TCA_DSMARK_INDICES,
+ TCA_DSMARK_DEFAULT_INDEX,
+ TCA_DSMARK_SET_TC_INDEX,
+ TCA_DSMARK_MASK,
+ TCA_DSMARK_VALUE,
+ __TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM section */
+
+enum {
+ TCA_ATM_UNSPEC,
+ TCA_ATM_FD, /* file/socket descriptor */
+ TCA_ATM_PTR, /* pointer to descriptor - later */
+ TCA_ATM_HDR, /* LL header */
+ TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */
+ TCA_ATM_ADDR, /* PVC address (for output only) */
+ TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */
+ __TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX (__TCA_ATM_MAX - 1)
+
+/* Network emulator */
+
+enum {
+ TCA_NETEM_UNSPEC,
+ TCA_NETEM_CORR,
+ TCA_NETEM_DELAY_DIST,
+ TCA_NETEM_REORDER,
+ TCA_NETEM_CORRUPT,
+ TCA_NETEM_LOSS,
+ TCA_NETEM_RATE,
+ TCA_NETEM_ECN,
+ TCA_NETEM_RATE64,
+ TCA_NETEM_PAD,
+ TCA_NETEM_LATENCY64,
+ TCA_NETEM_JITTER64,
+ TCA_NETEM_SLOT,
+ TCA_NETEM_SLOT_DIST,
+ __TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+ __u32 latency; /* added delay (us) */
+ __u32 limit; /* fifo limit (packets) */
+ __u32 loss; /* random packet loss (0=none ~0=100%) */
+ __u32 gap; /* re-ordering gap (0 for none) */
+ __u32 duplicate; /* random packet dup (0=none ~0=100%) */
+ __u32 jitter; /* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+ __u32 delay_corr; /* delay correlation */
+ __u32 loss_corr; /* packet loss correlation */
+ __u32 dup_corr; /* duplicate correlation */
+};
+
+struct tc_netem_reorder {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_corrupt {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_rate {
+ __u32 rate; /* byte/s */
+ __s32 packet_overhead;
+ __u32 cell_size;
+ __s32 cell_overhead;
+};
+
+struct tc_netem_slot {
+ __s64 min_delay; /* nsec */
+ __s64 max_delay;
+ __s32 max_packets;
+ __s32 max_bytes;
+ __s64 dist_delay; /* nsec */
+ __s64 dist_jitter; /* nsec */
+};
+
+enum {
+ NETEM_LOSS_UNSPEC,
+ NETEM_LOSS_GI, /* General Intuitive - 4 state model */
+ NETEM_LOSS_GE, /* Gilbert Elliot models */
+ __NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+ __u32 p13;
+ __u32 p31;
+ __u32 p32;
+ __u32 p14;
+ __u32 p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+ __u32 p;
+ __u32 r;
+ __u32 h;
+ __u32 k1;
+};
+
+#define NETEM_DIST_SCALE 8192
+#define NETEM_DIST_MAX 16384
+
+/* DRR */
+
+enum {
+ TCA_DRR_UNSPEC,
+ TCA_DRR_QUANTUM,
+ __TCA_DRR_MAX
+};
+
+#define TCA_DRR_MAX (__TCA_DRR_MAX - 1)
+
+struct tc_drr_stats {
+ __u32 deficit;
+};
+
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+enum {
+ TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */
+ TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */
+ __TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
+enum {
+ TC_MQPRIO_MODE_DCB,
+ TC_MQPRIO_MODE_CHANNEL,
+ __TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+ TC_MQPRIO_SHAPER_DCB,
+ TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */
+ __TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
+struct tc_mqprio_qopt {
+ __u8 num_tc;
+ __u8 prio_tc_map[TC_QOPT_BITMASK + 1];
+ __u8 hw;
+ __u16 count[TC_QOPT_MAX_QUEUE];
+ __u16 offset[TC_QOPT_MAX_QUEUE];
+};
+
+#define TC_MQPRIO_F_MODE 0x1
+#define TC_MQPRIO_F_SHAPER 0x2
+#define TC_MQPRIO_F_MIN_RATE 0x4
+#define TC_MQPRIO_F_MAX_RATE 0x8
+
+enum {
+ TCA_MQPRIO_UNSPEC,
+ TCA_MQPRIO_MODE,
+ TCA_MQPRIO_SHAPER,
+ TCA_MQPRIO_MIN_RATE64,
+ TCA_MQPRIO_MAX_RATE64,
+ __TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
+/* SFB */
+
+enum {
+ TCA_SFB_UNSPEC,
+ TCA_SFB_PARMS,
+ __TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+ __u32 rehash_interval; /* delay between hash move, in ms */
+ __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */
+ __u32 max; /* max len of qlen_min */
+ __u32 bin_size; /* maximum queue length per bin */
+ __u32 increment; /* probability increment, (d1 in Blue) */
+ __u32 decrement; /* probability decrement, (d2 in Blue) */
+ __u32 limit; /* max SFB queue length */
+ __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */
+ __u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+ __u32 earlydrop;
+ __u32 penaltydrop;
+ __u32 bucketdrop;
+ __u32 queuedrop;
+ __u32 childdrop; /* drops in child qdisc */
+ __u32 marked;
+ __u32 maxqlen;
+ __u32 maxprob;
+ __u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
+/* QFQ */
+enum {
+ TCA_QFQ_UNSPEC,
+ TCA_QFQ_WEIGHT,
+ TCA_QFQ_LMAX,
+ __TCA_QFQ_MAX
+};
+
+#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1)
+
+struct tc_qfq_stats {
+ __u32 weight;
+ __u32 lmax;
+};
+
+/* CODEL */
+
+enum {
+ TCA_CODEL_UNSPEC,
+ TCA_CODEL_TARGET,
+ TCA_CODEL_LIMIT,
+ TCA_CODEL_INTERVAL,
+ TCA_CODEL_ECN,
+ TCA_CODEL_CE_THRESHOLD,
+ __TCA_CODEL_MAX
+};
+
+#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1)
+
+struct tc_codel_xstats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 count; /* how many drops we've done since the last time we
+ * entered dropping state
+ */
+ __u32 lastcount; /* count at entry to dropping state */
+ __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */
+ __s32 drop_next; /* time to drop next packet */
+ __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */
+ __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */
+ __u32 dropping; /* are we in dropping state ? */
+ __u32 ce_mark; /* number of CE marked packets because of ce_threshold */
+};
+
+/* FQ_CODEL */
+
+enum {
+ TCA_FQ_CODEL_UNSPEC,
+ TCA_FQ_CODEL_TARGET,
+ TCA_FQ_CODEL_LIMIT,
+ TCA_FQ_CODEL_INTERVAL,
+ TCA_FQ_CODEL_ECN,
+ TCA_FQ_CODEL_FLOWS,
+ TCA_FQ_CODEL_QUANTUM,
+ TCA_FQ_CODEL_CE_THRESHOLD,
+ TCA_FQ_CODEL_DROP_BATCH_SIZE,
+ TCA_FQ_CODEL_MEMORY_LIMIT,
+ __TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+ TCA_FQ_CODEL_XSTATS_QDISC,
+ TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 drop_overlimit; /* number of time max qdisc
+ * packet limit was hit
+ */
+ __u32 ecn_mark; /* number of packets we ECN marked
+ * instead of being dropped
+ */
+ __u32 new_flow_count; /* number of time packets
+ * created a 'new flow'
+ */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 ce_mark; /* packets above ce_threshold */
+ __u32 memory_usage; /* in bytes */
+ __u32 drop_overmemory;
+};
+
+struct tc_fq_codel_cl_stats {
+ __s32 deficit;
+ __u32 ldelay; /* in-queue delay seen by most recently
+ * dequeued packet
+ */
+ __u32 count;
+ __u32 lastcount;
+ __u32 dropping;
+ __s32 drop_next;
+};
+
+struct tc_fq_codel_xstats {
+ __u32 type;
+ union {
+ struct tc_fq_codel_qd_stats qdisc_stats;
+ struct tc_fq_codel_cl_stats class_stats;
+ };
+};
+
+/* FQ */
+
+enum {
+ TCA_FQ_UNSPEC,
+
+ TCA_FQ_PLIMIT, /* limit of total number of packets in queue */
+
+ TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */
+
+ TCA_FQ_QUANTUM, /* RR quantum */
+
+ TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */
+
+ TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */
+
+ TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
+
+ TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */
+
+ TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */
+
+ TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */
+
+ TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */
+
+ TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */
+
+ TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */
+
+ __TCA_FQ_MAX
+};
+
+#define TCA_FQ_MAX (__TCA_FQ_MAX - 1)
+
+struct tc_fq_qd_stats {
+ __u64 gc_flows;
+ __u64 highprio_packets;
+ __u64 tcp_retrans;
+ __u64 throttled;
+ __u64 flows_plimit;
+ __u64 pkts_too_long;
+ __u64 allocation_errors;
+ __s64 time_next_delayed_flow;
+ __u32 flows;
+ __u32 inactive_flows;
+ __u32 throttled_flows;
+ __u32 unthrottle_latency_ns;
+ __u64 ce_mark; /* packets above ce_threshold */
+};
+
+/* Heavy-Hitter Filter */
+
+enum {
+ TCA_HHF_UNSPEC,
+ TCA_HHF_BACKLOG_LIMIT,
+ TCA_HHF_QUANTUM,
+ TCA_HHF_HH_FLOWS_LIMIT,
+ TCA_HHF_RESET_TIMEOUT,
+ TCA_HHF_ADMIT_BYTES,
+ TCA_HHF_EVICT_TIMEOUT,
+ TCA_HHF_NON_HH_WEIGHT,
+ __TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX (__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+ __u32 drop_overlimit; /* number of times max qdisc packet limit
+ * was hit
+ */
+ __u32 hh_overlimit; /* number of times max heavy-hitters was hit */
+ __u32 hh_tot_count; /* number of captured heavy-hitters so far */
+ __u32 hh_cur_count; /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+ TCA_PIE_UNSPEC,
+ TCA_PIE_TARGET,
+ TCA_PIE_LIMIT,
+ TCA_PIE_TUPDATE,
+ TCA_PIE_ALPHA,
+ TCA_PIE_BETA,
+ TCA_PIE_ECN,
+ TCA_PIE_BYTEMODE,
+ __TCA_PIE_MAX
+};
+#define TCA_PIE_MAX (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+ __u32 prob; /* current probability */
+ __u32 delay; /* current delay in ms */
+ __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to pie_action */
+ __u32 overlimit; /* dropped due to lack of space in queue */
+ __u32 maxq; /* maximum queue size */
+ __u32 ecn_mark; /* packets marked with ecn*/
+};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+#define TC_ETF_OFFLOAD_ON BIT(1)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
+
+/* CAKE */
+enum {
+ TCA_CAKE_UNSPEC,
+ TCA_CAKE_PAD,
+ TCA_CAKE_BASE_RATE64,
+ TCA_CAKE_DIFFSERV_MODE,
+ TCA_CAKE_ATM,
+ TCA_CAKE_FLOW_MODE,
+ TCA_CAKE_OVERHEAD,
+ TCA_CAKE_RTT,
+ TCA_CAKE_TARGET,
+ TCA_CAKE_AUTORATE,
+ TCA_CAKE_MEMORY,
+ TCA_CAKE_NAT,
+ TCA_CAKE_RAW,
+ TCA_CAKE_WASH,
+ TCA_CAKE_MPU,
+ TCA_CAKE_INGRESS,
+ TCA_CAKE_ACK_FILTER,
+ TCA_CAKE_SPLIT_GSO,
+ __TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1)
+
+enum {
+ __TCA_CAKE_STATS_INVALID,
+ TCA_CAKE_STATS_PAD,
+ TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+ TCA_CAKE_STATS_MEMORY_LIMIT,
+ TCA_CAKE_STATS_MEMORY_USED,
+ TCA_CAKE_STATS_AVG_NETOFF,
+ TCA_CAKE_STATS_MIN_NETLEN,
+ TCA_CAKE_STATS_MAX_NETLEN,
+ TCA_CAKE_STATS_MIN_ADJLEN,
+ TCA_CAKE_STATS_MAX_ADJLEN,
+ TCA_CAKE_STATS_TIN_STATS,
+ TCA_CAKE_STATS_DEFICIT,
+ TCA_CAKE_STATS_COBALT_COUNT,
+ TCA_CAKE_STATS_DROPPING,
+ TCA_CAKE_STATS_DROP_NEXT_US,
+ TCA_CAKE_STATS_P_DROP,
+ TCA_CAKE_STATS_BLUE_TIMER_US,
+ __TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+ __TCA_CAKE_TIN_STATS_INVALID,
+ TCA_CAKE_TIN_STATS_PAD,
+ TCA_CAKE_TIN_STATS_SENT_PACKETS,
+ TCA_CAKE_TIN_STATS_SENT_BYTES64,
+ TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+ TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+ TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+ TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+ TCA_CAKE_TIN_STATS_TARGET_US,
+ TCA_CAKE_TIN_STATS_INTERVAL_US,
+ TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+ TCA_CAKE_TIN_STATS_WAY_MISSES,
+ TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+ TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+ TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+ TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+ TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+ TCA_CAKE_TIN_STATS_BULK_FLOWS,
+ TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+ TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+ TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+ __TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+ CAKE_FLOW_NONE = 0,
+ CAKE_FLOW_SRC_IP,
+ CAKE_FLOW_DST_IP,
+ CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+ CAKE_FLOW_FLOWS,
+ CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_MAX,
+};
+
+enum {
+ CAKE_DIFFSERV_DIFFSERV3 = 0,
+ CAKE_DIFFSERV_DIFFSERV4,
+ CAKE_DIFFSERV_DIFFSERV8,
+ CAKE_DIFFSERV_BESTEFFORT,
+ CAKE_DIFFSERV_PRECEDENCE,
+ CAKE_DIFFSERV_MAX
+};
+
+enum {
+ CAKE_ACK_NONE = 0,
+ CAKE_ACK_FILTER,
+ CAKE_ACK_AGGRESSIVE,
+ CAKE_ACK_MAX
+};
+
+enum {
+ CAKE_ATM_NONE = 0,
+ CAKE_ATM_ATM,
+ CAKE_ATM_PTM,
+ CAKE_ATM_MAX
+};
+
+
+/* TAPRIO */
+enum {
+ TC_TAPRIO_CMD_SET_GATES = 0x00,
+ TC_TAPRIO_CMD_SET_AND_HOLD = 0x01,
+ TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02,
+};
+
+enum {
+ TCA_TAPRIO_SCHED_ENTRY_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */
+ TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */
+ __TCA_TAPRIO_SCHED_ENTRY_MAX,
+};
+#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1)
+
+/* The format for schedule entry list is:
+ * [TCA_TAPRIO_SCHED_ENTRY_LIST]
+ * [TCA_TAPRIO_SCHED_ENTRY]
+ * [TCA_TAPRIO_SCHED_ENTRY_CMD]
+ * [TCA_TAPRIO_SCHED_ENTRY_GATES]
+ * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL]
+ */
+enum {
+ TCA_TAPRIO_SCHED_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY,
+ __TCA_TAPRIO_SCHED_MAX,
+};
+
+#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
+
+enum {
+ TCA_TAPRIO_ATTR_UNSPEC,
+ TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
+ TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */
+ TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */
+ TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
+ TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
+ TCA_TAPRIO_PAD,
+ __TCA_TAPRIO_ATTR_MAX,
+};
+
+#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1)
+
+#endif
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index b17201e..7da1b37 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -181,7 +181,7 @@
#define PR_GET_THP_DISABLE 42
/*
- * Tell the kernel to start/stop helping userspace manage bounds tables.
+ * No longer implemented, but left here to ensure the numbers stay reserved:
*/
#define PR_MPX_ENABLE_MANAGEMENT 43
#define PR_MPX_DISABLE_MANAGEMENT 44
@@ -219,5 +219,19 @@
# define PR_SPEC_ENABLE (1UL << 1)
# define PR_SPEC_DISABLE (1UL << 2)
# define PR_SPEC_FORCE_DISABLE (1UL << 3)
+# define PR_SPEC_DISABLE_NOEXEC (1UL << 4)
+
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS 54
+# define PR_PAC_APIAKEY (1UL << 0)
+# define PR_PAC_APIBKEY (1UL << 1)
+# define PR_PAC_APDAKEY (1UL << 2)
+# define PR_PAC_APDBKEY (1UL << 3)
+# define PR_PAC_APGAKEY (1UL << 4)
+
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL 55
+#define PR_GET_TAGGED_ADDR_CTRL 56
+# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 22627f8..99335e1 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -2,6 +2,8 @@
#ifndef _UAPI_LINUX_SCHED_H
#define _UAPI_LINUX_SCHED_H
+#include <linux/types.h>
+
/*
* cloning flags:
*/
@@ -10,6 +12,7 @@
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
+#define CLONE_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
@@ -30,6 +33,46 @@
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags: Flags for the new process as listed above.
+ * All flags are valid except for CSIGNAL and
+ * CLONE_DETACHED.
+ * @pidfd: If CLONE_PIDFD is set, a pidfd will be
+ * returned in this argument.
+ * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
+ * child process will be returned in the child's
+ * memory.
+ * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
+ * the child process will be returned in the
+ * parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ * sent when the child exits.
+ * @stack: Specify the location of the stack for the
+ * child process.
+ * @stack_size: The size of the stack for the child process.
+ * @tls: If CLONE_SETTLS is set, the tls descriptor
+ * is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
+ */
+struct clone_args {
+ __aligned_u64 flags;
+ __aligned_u64 pidfd;
+ __aligned_u64 child_tid;
+ __aligned_u64 parent_tid;
+ __aligned_u64 exit_signal;
+ __aligned_u64 stack;
+ __aligned_u64 stack_size;
+ __aligned_u64 tls;
+};
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+
/*
* Scheduling policies
*/
@@ -50,9 +93,21 @@
#define SCHED_FLAG_RESET_ON_FORK 0x01
#define SCHED_FLAG_RECLAIM 0x02
#define SCHED_FLAG_DL_OVERRUN 0x04
+#define SCHED_FLAG_KEEP_POLICY 0x08
+#define SCHED_FLAG_KEEP_PARAMS 0x10
+#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
+#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+
+#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
+ SCHED_FLAG_KEEP_PARAMS)
+
+#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \
+ SCHED_FLAG_UTIL_CLAMP_MAX)
#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
SCHED_FLAG_RECLAIM | \
- SCHED_FLAG_DL_OVERRUN)
+ SCHED_FLAG_DL_OVERRUN | \
+ SCHED_FLAG_KEEP_ALL | \
+ SCHED_FLAG_UTIL_CLAMP)
#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 0000000..653c4f9
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_act_bpf {
+ tc_gen;
+};
+
+enum {
+ TCA_ACT_BPF_UNSPEC,
+ TCA_ACT_BPF_TM,
+ TCA_ACT_BPF_PARMS,
+ TCA_ACT_BPF_OPS_LEN,
+ TCA_ACT_BPF_OPS,
+ TCA_ACT_BPF_FD,
+ TCA_ACT_BPF_NAME,
+ TCA_ACT_BPF_PAD,
+ TCA_ACT_BPF_TAG,
+ TCA_ACT_BPF_ID,
+ __TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/tools/include/uapi/linux/tls.h b/tools/include/uapi/linux/tls.h
new file mode 100644
index 0000000..ff02287
--- /dev/null
+++ b/tools/include/uapi/linux/tls.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_TLS_H
+#define _UAPI_LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX 1 /* Set transmit parameters */
+#define TLS_RX 2 /* Set receive parameters */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver) (((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id) ((((id##_VERSION_MAJOR) & 0xFF) << 8) | \
+ ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR 0x3
+#define TLS_1_2_VERSION_MINOR 0x3
+#define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128 51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE 8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE 4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8
+
+#define TLS_SET_RECORD_TYPE 1
+#define TLS_GET_RECORD_TYPE 2
+
+struct tls_crypto_info {
+ __u16 version;
+ __u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+ unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+#endif /* _UAPI_LINUX_TLS_H */
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
new file mode 100644
index 0000000..cf525cd
--- /dev/null
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*****************************************************************************/
+
+/*
+ * usbdevice_fs.h -- USB device file system.
+ *
+ * Copyright (C) 2000
+ * Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * History:
+ * 0.1 04.01.2000 Created
+ */
+
+/*****************************************************************************/
+
+#ifndef _UAPI_LINUX_USBDEVICE_FS_H
+#define _UAPI_LINUX_USBDEVICE_FS_H
+
+#include <linux/types.h>
+#include <linux/magic.h>
+
+/* --------------------------------------------------------------------- */
+
+/* usbdevfs ioctl codes */
+
+struct usbdevfs_ctrltransfer {
+ __u8 bRequestType;
+ __u8 bRequest;
+ __u16 wValue;
+ __u16 wIndex;
+ __u16 wLength;
+ __u32 timeout; /* in milliseconds */
+ void __user *data;
+};
+
+struct usbdevfs_bulktransfer {
+ unsigned int ep;
+ unsigned int len;
+ unsigned int timeout; /* in milliseconds */
+ void __user *data;
+};
+
+struct usbdevfs_setinterface {
+ unsigned int interface;
+ unsigned int altsetting;
+};
+
+struct usbdevfs_disconnectsignal {
+ unsigned int signr;
+ void __user *context;
+};
+
+#define USBDEVFS_MAXDRIVERNAME 255
+
+struct usbdevfs_getdriver {
+ unsigned int interface;
+ char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_connectinfo {
+ unsigned int devnum;
+ unsigned char slow;
+};
+
+struct usbdevfs_conninfo_ex {
+ __u32 size; /* Size of the structure from the kernel's */
+ /* point of view. Can be used by userspace */
+ /* to determine how much data can be */
+ /* used/trusted. */
+ __u32 busnum; /* USB bus number, as enumerated by the */
+ /* kernel, the device is connected to. */
+ __u32 devnum; /* Device address on the bus. */
+ __u32 speed; /* USB_SPEED_* constants from ch9.h */
+ __u8 num_ports; /* Number of ports the device is connected */
+ /* to on the way to the root hub. It may */
+ /* be bigger than size of 'ports' array so */
+ /* userspace can detect overflows. */
+ __u8 ports[7]; /* List of ports on the way from the root */
+ /* hub to the device. Current limit in */
+ /* USB specification is 7 tiers (root hub, */
+ /* 5 intermediate hubs, device), which */
+ /* gives at most 6 port entries. */
+};
+
+#define USBDEVFS_URB_SHORT_NOT_OK 0x01
+#define USBDEVFS_URB_ISO_ASAP 0x02
+#define USBDEVFS_URB_BULK_CONTINUATION 0x04
+#define USBDEVFS_URB_NO_FSBR 0x20 /* Not used */
+#define USBDEVFS_URB_ZERO_PACKET 0x40
+#define USBDEVFS_URB_NO_INTERRUPT 0x80
+
+#define USBDEVFS_URB_TYPE_ISO 0
+#define USBDEVFS_URB_TYPE_INTERRUPT 1
+#define USBDEVFS_URB_TYPE_CONTROL 2
+#define USBDEVFS_URB_TYPE_BULK 3
+
+struct usbdevfs_iso_packet_desc {
+ unsigned int length;
+ unsigned int actual_length;
+ unsigned int status;
+};
+
+struct usbdevfs_urb {
+ unsigned char type;
+ unsigned char endpoint;
+ int status;
+ unsigned int flags;
+ void __user *buffer;
+ int buffer_length;
+ int actual_length;
+ int start_frame;
+ union {
+ int number_of_packets; /* Only used for isoc urbs */
+ unsigned int stream_id; /* Only used with bulk streams */
+ };
+ int error_count;
+ unsigned int signr; /* signal to be sent on completion,
+ or 0 if none should be sent. */
+ void __user *usercontext;
+ struct usbdevfs_iso_packet_desc iso_frame_desc[0];
+};
+
+/* ioctls for talking directly to drivers */
+struct usbdevfs_ioctl {
+ int ifno; /* interface 0..N ; negative numbers reserved */
+ int ioctl_code; /* MUST encode size + direction of data so the
+ * macros in <asm/ioctl.h> give correct values */
+ void __user *data; /* param buffer (in, or out) */
+};
+
+/* You can do most things with hubs just through control messages,
+ * except find out what device connects to what port. */
+struct usbdevfs_hub_portinfo {
+ char nports; /* number of downstream ports in this hub */
+ char port [127]; /* e.g. port 3 connects to device 27 */
+};
+
+/* System and bus capability flags */
+#define USBDEVFS_CAP_ZERO_PACKET 0x01
+#define USBDEVFS_CAP_BULK_CONTINUATION 0x02
+#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04
+#define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08
+#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10
+#define USBDEVFS_CAP_MMAP 0x20
+#define USBDEVFS_CAP_DROP_PRIVILEGES 0x40
+#define USBDEVFS_CAP_CONNINFO_EX 0x80
+#define USBDEVFS_CAP_SUSPEND 0x100
+
+/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
+
+/* disconnect-and-claim if the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER 0x01
+/* disconnect-and-claim except when the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER 0x02
+
+struct usbdevfs_disconnect_claim {
+ unsigned int interface;
+ unsigned int flags;
+ char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_streams {
+ unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
+ unsigned int num_eps;
+ unsigned char eps[0];
+};
+
+/*
+ * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
+ * linux/usb/ch9.h
+ */
+
+#define USBDEVFS_CONTROL _IOWR('U', 0, struct usbdevfs_ctrltransfer)
+#define USBDEVFS_CONTROL32 _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
+#define USBDEVFS_BULK _IOWR('U', 2, struct usbdevfs_bulktransfer)
+#define USBDEVFS_BULK32 _IOWR('U', 2, struct usbdevfs_bulktransfer32)
+#define USBDEVFS_RESETEP _IOR('U', 3, unsigned int)
+#define USBDEVFS_SETINTERFACE _IOR('U', 4, struct usbdevfs_setinterface)
+#define USBDEVFS_SETCONFIGURATION _IOR('U', 5, unsigned int)
+#define USBDEVFS_GETDRIVER _IOW('U', 8, struct usbdevfs_getdriver)
+#define USBDEVFS_SUBMITURB _IOR('U', 10, struct usbdevfs_urb)
+#define USBDEVFS_SUBMITURB32 _IOR('U', 10, struct usbdevfs_urb32)
+#define USBDEVFS_DISCARDURB _IO('U', 11)
+#define USBDEVFS_REAPURB _IOW('U', 12, void *)
+#define USBDEVFS_REAPURB32 _IOW('U', 12, __u32)
+#define USBDEVFS_REAPURBNDELAY _IOW('U', 13, void *)
+#define USBDEVFS_REAPURBNDELAY32 _IOW('U', 13, __u32)
+#define USBDEVFS_DISCSIGNAL _IOR('U', 14, struct usbdevfs_disconnectsignal)
+#define USBDEVFS_DISCSIGNAL32 _IOR('U', 14, struct usbdevfs_disconnectsignal32)
+#define USBDEVFS_CLAIMINTERFACE _IOR('U', 15, unsigned int)
+#define USBDEVFS_RELEASEINTERFACE _IOR('U', 16, unsigned int)
+#define USBDEVFS_CONNECTINFO _IOW('U', 17, struct usbdevfs_connectinfo)
+#define USBDEVFS_IOCTL _IOWR('U', 18, struct usbdevfs_ioctl)
+#define USBDEVFS_IOCTL32 _IOWR('U', 18, struct usbdevfs_ioctl32)
+#define USBDEVFS_HUB_PORTINFO _IOR('U', 19, struct usbdevfs_hub_portinfo)
+#define USBDEVFS_RESET _IO('U', 20)
+#define USBDEVFS_CLEAR_HALT _IOR('U', 21, unsigned int)
+#define USBDEVFS_DISCONNECT _IO('U', 22)
+#define USBDEVFS_CONNECT _IO('U', 23)
+#define USBDEVFS_CLAIM_PORT _IOR('U', 24, unsigned int)
+#define USBDEVFS_RELEASE_PORT _IOR('U', 25, unsigned int)
+#define USBDEVFS_GET_CAPABILITIES _IOR('U', 26, __u32)
+#define USBDEVFS_DISCONNECT_CLAIM _IOR('U', 27, struct usbdevfs_disconnect_claim)
+#define USBDEVFS_ALLOC_STREAMS _IOR('U', 28, struct usbdevfs_streams)
+#define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams)
+#define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32)
+#define USBDEVFS_GET_SPEED _IO('U', 31)
+/*
+ * Returns struct usbdevfs_conninfo_ex; length is variable to allow
+ * extending size of the data returned.
+ */
+#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME _IO('U', 35)
+
+#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 84c3de8..40d028e 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -11,94 +11,9 @@
* device configuration.
*/
+#include <linux/vhost_types.h>
#include <linux/types.h>
-#include <linux/compiler.h>
#include <linux/ioctl.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-
-struct vhost_vring_state {
- unsigned int index;
- unsigned int num;
-};
-
-struct vhost_vring_file {
- unsigned int index;
- int fd; /* Pass -1 to unbind from file. */
-
-};
-
-struct vhost_vring_addr {
- unsigned int index;
- /* Option flags. */
- unsigned int flags;
- /* Flag values: */
- /* Whether log address is valid. If set enables logging. */
-#define VHOST_VRING_F_LOG 0
-
- /* Start of array of descriptors (virtually contiguous) */
- __u64 desc_user_addr;
- /* Used structure address. Must be 32 bit aligned */
- __u64 used_user_addr;
- /* Available structure address. Must be 16 bit aligned */
- __u64 avail_user_addr;
- /* Logging support. */
- /* Log writes to used structure, at offset calculated from specified
- * address. Address must be 32 bit aligned. */
- __u64 log_guest_addr;
-};
-
-/* no alignment requirement */
-struct vhost_iotlb_msg {
- __u64 iova;
- __u64 size;
- __u64 uaddr;
-#define VHOST_ACCESS_RO 0x1
-#define VHOST_ACCESS_WO 0x2
-#define VHOST_ACCESS_RW 0x3
- __u8 perm;
-#define VHOST_IOTLB_MISS 1
-#define VHOST_IOTLB_UPDATE 2
-#define VHOST_IOTLB_INVALIDATE 3
-#define VHOST_IOTLB_ACCESS_FAIL 4
- __u8 type;
-};
-
-#define VHOST_IOTLB_MSG 0x1
-#define VHOST_IOTLB_MSG_V2 0x2
-
-struct vhost_msg {
- int type;
- union {
- struct vhost_iotlb_msg iotlb;
- __u8 padding[64];
- };
-};
-
-struct vhost_msg_v2 {
- __u32 type;
- __u32 reserved;
- union {
- struct vhost_iotlb_msg iotlb;
- __u8 padding[64];
- };
-};
-
-struct vhost_memory_region {
- __u64 guest_phys_addr;
- __u64 memory_size; /* bytes */
- __u64 userspace_addr;
- __u64 flags_padding; /* No flags are currently specified. */
-};
-
-/* All region addresses and sizes must be 4K aligned. */
-#define VHOST_PAGE_SIZE 0x1000
-
-struct vhost_memory {
- __u32 nregions;
- __u32 padding;
- struct vhost_memory_region regions[0];
-};
/* ioctls */
@@ -186,31 +101,7 @@
* device. This can be used to stop the ring (e.g. for migration). */
#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
-/* Feature bits */
-/* Log all write descriptors. Can be changed while device is active. */
-#define VHOST_F_LOG_ALL 26
-/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
-#define VHOST_NET_F_VIRTIO_NET_HDR 27
-
-/* VHOST_SCSI specific definitions */
-
-/*
- * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
- *
- * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
- * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage
- * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
- * All the targets under vhost_wwpn can be seen and used by guset.
- */
-
-#define VHOST_SCSI_ABI_VERSION 1
-
-struct vhost_scsi_target {
- int abi_version;
- char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
- unsigned short vhost_tpgt;
- unsigned short reserved;
-};
+/* VHOST_SCSI specific defines */
#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)