summaryrefslogtreecommitdiff
path: root/include/uapi/linux
diff options
context:
space:
mode:
Diffstat (limited to 'include/uapi/linux')
-rw-r--r--include/uapi/linux/audit.h1
-rw-r--r--include/uapi/linux/bpf.h401
-rw-r--r--include/uapi/linux/btrfs_tree.h9
-rw-r--r--include/uapi/linux/capability.h42
-rw-r--r--include/uapi/linux/devlink.h9
-rw-r--r--include/uapi/linux/elf.h11
-rw-r--r--include/uapi/linux/errqueue.h2
-rw-r--r--include/uapi/linux/ethtool.h16
-rw-r--r--include/uapi/linux/ethtool_netlink.h153
-rw-r--r--include/uapi/linux/fcntl.h10
-rw-r--r--include/uapi/linux/fd.h26
-rw-r--r--include/uapi/linux/fdreg.h16
-rw-r--r--include/uapi/linux/fiemap.h6
-rw-r--r--include/uapi/linux/firewire-cdev.h2
-rw-r--r--include/uapi/linux/fscrypt.h3
-rw-r--r--include/uapi/linux/genetlink.h2
-rw-r--r--include/uapi/linux/gfs2_ondisk.h6
-rw-r--r--include/uapi/linux/if.h1
-rw-r--r--include/uapi/linux/if_bridge.h96
-rw-r--r--include/uapi/linux/if_ether.h1
-rw-r--r--include/uapi/linux/if_link.h1
-rw-r--r--include/uapi/linux/if_x25.h2
-rw-r--r--include/uapi/linux/inet_diag.h2
-rw-r--r--include/uapi/linux/io_uring.h12
-rw-r--r--include/uapi/linux/iommu.h5
-rw-r--r--include/uapi/linux/keyctl.h2
-rw-r--r--include/uapi/linux/kfd_ioctl.h21
-rw-r--r--include/uapi/linux/kvm.h18
-rw-r--r--include/uapi/linux/loop.h31
-rw-r--r--include/uapi/linux/magic.h1
-rw-r--r--include/uapi/linux/mii.h2
-rw-r--r--include/uapi/linux/mmc/ioctl.h1
-rw-r--r--include/uapi/linux/mrp_bridge.h122
-rw-r--r--include/uapi/linux/neighbour.h1
-rw-r--r--include/uapi/linux/netfilter/nf_conntrack_common.h8
-rw-r--r--include/uapi/linux/netfilter/nf_nat.h4
-rw-r--r--include/uapi/linux/netfilter/nfnetlink_conntrack.h9
-rw-r--r--include/uapi/linux/netlink.h103
-rw-r--r--include/uapi/linux/nexthop.h3
-rw-r--r--include/uapi/linux/nl80211.h149
-rw-r--r--include/uapi/linux/pkt_cls.h24
-rw-r--r--include/uapi/linux/pkt_sched.h6
-rw-r--r--include/uapi/linux/psample.h22
-rw-r--r--include/uapi/linux/psp-sev.h2
-rw-r--r--include/uapi/linux/ptp_clock.h4
-rw-r--r--include/uapi/linux/rtc.h1
-rw-r--r--include/uapi/linux/rtnetlink.h6
-rw-r--r--include/uapi/linux/stat.h19
-rw-r--r--include/uapi/linux/tc_act/tc_gate.h47
-rw-r--r--include/uapi/linux/tee.h9
-rw-r--r--include/uapi/linux/v4l2-controls.h12
-rw-r--r--include/uapi/linux/v4l2-subdev.h16
-rw-r--r--include/uapi/linux/vfio.h322
-rw-r--r--include/uapi/linux/vfio_ccw.h19
-rw-r--r--include/uapi/linux/vhost.h4
-rw-r--r--include/uapi/linux/videodev2.h5
-rw-r--r--include/uapi/linux/virtio_ids.h1
-rw-r--r--include/uapi/linux/virtio_mem.h211
-rw-r--r--include/uapi/linux/virtio_ring.h48
-rw-r--r--include/uapi/linux/watch_queue.h104
-rw-r--r--include/uapi/linux/wireless.h6
-rw-r--r--include/uapi/linux/xfrm.h2
62 files changed, 2077 insertions, 123 deletions
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index a534d71e689a..9b6a973f4cc3 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -117,6 +117,7 @@
#define AUDIT_TIME_INJOFFSET 1332 /* Timekeeping offset injected */
#define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */
#define AUDIT_BPF 1334 /* BPF subsystem */
+#define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */
#define AUDIT_AVC 1400 /* SE Linux avc denial or grant */
#define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f9b7fdd951e4..19684813faae 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -113,6 +113,10 @@ enum bpf_cmd {
BPF_MAP_DELETE_BATCH,
BPF_LINK_CREATE,
BPF_LINK_UPDATE,
+ BPF_LINK_GET_FD_BY_ID,
+ BPF_LINK_GET_NEXT_ID,
+ BPF_ENABLE_STATS,
+ BPF_ITER_CREATE,
};
enum bpf_map_type {
@@ -143,6 +147,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
+ BPF_MAP_TYPE_RINGBUF,
};
/* Note that tracing related programs such as
@@ -215,11 +220,28 @@ enum bpf_attach_type {
BPF_TRACE_FEXIT,
BPF_MODIFY_RETURN,
BPF_LSM_MAC,
+ BPF_TRACE_ITER,
+ BPF_CGROUP_INET4_GETPEERNAME,
+ BPF_CGROUP_INET6_GETPEERNAME,
+ BPF_CGROUP_INET4_GETSOCKNAME,
+ BPF_CGROUP_INET6_GETSOCKNAME,
+ BPF_XDP_DEVMAP,
__MAX_BPF_ATTACH_TYPE
};
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+enum bpf_link_type {
+ BPF_LINK_TYPE_UNSPEC = 0,
+ BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+ BPF_LINK_TYPE_TRACING = 2,
+ BPF_LINK_TYPE_CGROUP = 3,
+ BPF_LINK_TYPE_ITER = 4,
+ BPF_LINK_TYPE_NETNS = 5,
+
+ MAX_BPF_LINK_TYPE,
+};
+
/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
*
* NONE(default): No further bpf programs allowed in the subtree.
@@ -379,6 +401,12 @@ enum {
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+ /* enabled run_time_ns and run_cnt */
+ BPF_STATS_RUN_TIME = 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,
@@ -523,6 +551,7 @@ union bpf_attr {
__u32 prog_id;
__u32 map_id;
__u32 btf_id;
+ __u32 link_id;
};
__u32 next_id;
__u32 open_flags;
@@ -589,6 +618,15 @@ union bpf_attr {
__u32 old_prog_fd;
} link_update;
+ struct { /* struct used by BPF_ENABLE_STATS command */
+ __u32 type;
+ } enable_stats;
+
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@@ -644,14 +682,16 @@ union bpf_attr {
* For tracing programs, safely attempt to read *size* bytes from
* kernel space address *unsafe_ptr* and store the data in *dst*.
*
- * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
- * instead.
+ * Generally, use **bpf_probe_read_user**\ () or
+ * **bpf_probe_read_kernel**\ () instead.
* Return
* 0 on success, or a negative error in case of failure.
*
* u64 bpf_ktime_get_ns(void)
* Description
* Return the time elapsed since system boot, in nanoseconds.
+ * Does not include time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
* Return
* Current *ktime*.
*
@@ -1510,11 +1550,11 @@ union bpf_attr {
* int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address
- * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
* more details.
*
- * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
- * instead.
+ * Generally, use **bpf_probe_read_user_str**\ () or
+ * **bpf_probe_read_kernel_str**\ () instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -1542,7 +1582,7 @@ union bpf_attr {
*
* u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
* Description
- * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
* *skb*, but gets socket from **struct bpf_sock_ops** context.
* Return
* A 8-byte long non-decreasing number.
@@ -1562,7 +1602,7 @@ union bpf_attr {
* Return
* 0
*
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **setsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1570,6 +1610,12 @@ union bpf_attr {
* must be specified, see **setsockopt(2)** for more information.
* The option value of length *optlen* is pointed by *optval*.
*
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * and **BPF_CGROUP_INET6_CONNECT**.
+ *
* This helper actually implements a subset of **setsockopt()**.
* It supports the following *level*\ s:
*
@@ -1589,6 +1635,13 @@ union bpf_attr {
* Grow or shrink the room for data in the packet associated to
* *skb* by *len_diff*, and according to the selected *mode*.
*
+ * By default, the helper will reset any offloaded checksum
+ * indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * by the following flag:
+ *
+ * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * checksum data of the skb to CHECKSUM_NONE.
+ *
* There are two supported modes at this time:
*
* * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
@@ -1634,12 +1687,12 @@ union bpf_attr {
*
* 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
+ * 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.
*
- * See also bpf_redirect(), which only supports redirecting to an
- * ifindex, but doesn't require a map to do so.
+ * See also **bpf_redirect**\ (), which only supports redirecting
+ * to an ifindex, but doesn't require a map to do so.
* Return
* **XDP_REDIRECT** on success, or the value of the two lower bits
* of the *flags* argument on error.
@@ -1747,7 +1800,7 @@ union bpf_attr {
* the time running for event since last normalization. The
* enabled and running times are accumulated since the perf event
* open. To achieve scaling factor between two invocations of an
- * eBPF program, users can can use CPU id as the key (which is
+ * eBPF program, users can use CPU id as the key (which is
* typical for perf array usage model) to remember the previous
* value and do the calculation inside the eBPF program.
* Return
@@ -1764,7 +1817,7 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
* Description
* Emulate a call to **getsockopt()** on the socket associated to
* *bpf_socket*, which must be a full socket. The *level* at
@@ -1773,6 +1826,12 @@ union bpf_attr {
* The retrieved value is stored in the structure pointed by
* *opval* and of length *optlen*.
*
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * and **BPF_CGROUP_INET6_CONNECT**.
+ *
* This helper actually implements a subset of **getsockopt()**.
* It supports the following *level*\ s:
*
@@ -1790,7 +1849,7 @@ union bpf_attr {
* The first argument is the context *regs* on which the kprobe
* works.
*
- * This helper works by setting setting the PC (program counter)
+ * This helper works by setting the PC (program counter)
* to an override function which is run in place of the original
* probed function. This means the probed function is not run at
* all. The replacement function just returns with the required
@@ -1959,18 +2018,19 @@ union bpf_attr {
*
* This helper works for IPv4 and IPv6, TCP and UDP sockets. The
* domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * **AF_INET6**). Looking for a free port to bind to can be
- * expensive, therefore binding to port is not permitted by the
- * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * must be set to zero.
+ * **AF_INET6**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
* Description
* Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
- * only possible to shrink the packet as of this writing,
- * therefore *delta* must be a negative integer.
+ * possible to both shrink and grow the packet tail.
+ * Shrink done via *delta* being a negative integer.
*
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
@@ -2256,7 +2316,7 @@ union bpf_attr {
* **bpf_rc_keydown**\ () again with the same values, or calling
* **bpf_rc_repeat**\ ().
*
- * Some protocols include a toggle bit, in case the button was
+ * 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
@@ -2602,7 +2662,6 @@ union bpf_attr {
*
* *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.
@@ -2785,7 +2844,6 @@ union bpf_attr {
*
* *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,
@@ -2868,7 +2926,7 @@ union bpf_attr {
* // size, after checking its boundaries.
* }
*
- * In comparison, using **bpf_probe_read_user()** helper here
+ * In comparison, using **bpf_probe_read_user**\ () helper here
* instead to read the string would require to estimate the length
* at compile time, and would often result in copying more memory
* than necessary.
@@ -2886,14 +2944,14 @@ union bpf_attr {
* int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
* Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
- * to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
* Return
- * On success, the strictly positive length of the string, including
+ * On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
*
* int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
* Description
- * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
* *rcv_nxt* is the ack_seq to be sent out.
* Return
* 0 on success, or a negative error in case of failure.
@@ -2921,19 +2979,19 @@ union bpf_attr {
* int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
* Description
* For an eBPF program attached to a perf event, retrieve the
- * branch records (struct perf_branch_entry) associated to *ctx*
- * and store it in the buffer pointed by *buf* up to size
+ * branch records (**struct perf_branch_entry**) associated to *ctx*
+ * and store it in the buffer pointed by *buf* up to size
* *size* bytes.
* Return
* On success, number of bytes written to *buf*. On error, a
* negative value.
*
* The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
- * instead return the number of bytes required to store all the
+ * instead return the number of bytes required to store all the
* branch entries. If this flag is set, *buf* may be NULL.
*
* **-EINVAL** if arguments invalid or **size** not a multiple
- * of sizeof(struct perf_branch_entry).
+ * of **sizeof**\ (**struct perf_branch_entry**\ ).
*
* **-ENOENT** if architecture does not support branch records.
*
@@ -2941,8 +2999,8 @@ union bpf_attr {
* Description
* Returns 0 on success, values for *pid* and *tgid* as seen from the current
* *namespace* will be returned in *nsdata*.
- *
- * On failure, the returned value is one of the following:
+ * Return
+ * 0 on success, or one of the following in case of failure:
*
* **-EINVAL** if dev and inum supplied don't match dev_t and inode number
* with nsfs of current task, or if dev conversion to dev_t lost high bits.
@@ -2981,8 +3039,8 @@ union bpf_attr {
* a global identifier that can be assumed unique. If *ctx* is
* NULL, then the helper returns the cookie for the initial
* network namespace. The cookie itself is very similar to that
- * of bpf_get_socket_cookie() helper, but for network namespaces
- * instead of sockets.
+ * of **bpf_get_socket_cookie**\ () helper, but for network
+ * namespaces instead of sockets.
* Return
* A 8-byte long opaque number.
*
@@ -3017,14 +3075,183 @@ union bpf_attr {
*
* The *flags* argument must be zero.
* Return
- * 0 on success, or a negative errno in case of failure.
- *
- * * **-EINVAL** Unsupported flags specified.
- * * **-ENOENT** Socket is unavailable for assignment.
- * * **-ENETUNREACH** Socket is unreachable (wrong netns).
- * * **-EOPNOTSUPP** Unsupported operation, for example a
- * call from outside of TC ingress.
- * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport).
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EINVAL** if specified *flags* are not supported.
+ *
+ * **-ENOENT** if the socket is unavailable for assignment.
+ *
+ * **-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ * **-EOPNOTSUPP** if the operation is not supported, for example
+ * a call from outside of TC ingress.
+ *
+ * **-ESOCKTNOSUPPORT** if the socket type is not supported
+ * (reuseport).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Does include the time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
+ * Return
+ * Current *ktime*.
+ *
+ * int bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * out the format string.
+ * The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * the format string itself. The *data* and *data_len* are format string
+ * arguments. The *data* are a **u64** array and corresponding format string
+ * values are stored in the array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data* array.
+ * The *data_len* is the size of *data* in bytes.
+ *
+ * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ * Reading kernel memory may fail due to either invalid address or
+ * valid address but requiring a major memory fault. If reading kernel memory
+ * fails, the string for **%s** will be an empty string, and the ip
+ * address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ * bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ * by returning 1 from bpf program.
+ *
+ * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ * **-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * int bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * Description
+ * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * The *m* represents the seq_file. The *data* and *len* represent the
+ * data to write in bytes.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * Description
+ * Return the cgroup v2 id of the socket *sk*.
+ *
+ * *sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ * returned from **bpf_sk_lookup_xxx**\ (),
+ * **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ * same as in **bpf_skb_cgroup_id**\ ().
+ *
+ * This helper is available only if the kernel was compiled with
+ * the **CONFIG_SOCK_CGROUP_DATA** configuration option.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *sk* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *sk*, then return value will be same as that
+ * of **bpf_sk_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *sk*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_sk_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * Description
+ * Copy *size* bytes from *data* into a ring buffer *ringbuf*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * 0, on success;
+ * < 0, on error.
+ *
+ * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * Return
+ * Valid pointer with *size* bytes of memory available; NULL,
+ * otherwise.
+ *
+ * void bpf_ringbuf_submit(void *data, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard(void *data, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample, pointed to by *data*.
+ * If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * new data availability is sent.
+ * IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * new data availability is sent unconditionally.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * u64 bpf_ringbuf_query(void *ringbuf, u64 flags)
+ * Description
+ * Query various characteristics of provided ring buffer. What
+ * exactly is queries is determined by *flags*:
+ * - BPF_RB_AVAIL_DATA - amount of data not yet consumed;
+ * - BPF_RB_RING_SIZE - the size of ring buffer;
+ * - BPF_RB_CONS_POS - consumer position (can wrap around);
+ * - BPF_RB_PROD_POS - producer(s) position (can wrap around);
+ * Data returned is just a momentary snapshots of actual values
+ * and could be inaccurate, so this facility should be used to
+ * power heuristics and for reporting, not to make 100% correct
+ * calculation.
+ * Return
+ * Requested value, or 0, if flags are not recognized.
+ *
+ * int bpf_csum_level(struct sk_buff *skb, u64 level)
+ * Description
+ * Change the skbs checksum level by one layer up or down, or
+ * reset it entirely to none in order to have the stack perform
+ * checksum validation. The level is applicable to the following
+ * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of
+ * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |
+ * through **bpf_skb_adjust_room**\ () helper with passing in
+ * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call
+ * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since
+ * the UDP header is removed. Similarly, an encap of the latter
+ * into the former could be accompanied by a helper call to
+ * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the
+ * skb is still intended to be processed in higher layers of the
+ * stack instead of just egressing at tc.
+ *
+ * There are three supported level settings at this time:
+ *
+ * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and
+ * sets CHECKSUM_NONE to force checksum validation by the stack.
+ * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current
+ * skb->csum_level.
+ * Return
+ * 0 on success, or a negative error in case of failure. In the
+ * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
+ * is returned or the error code -EACCES in case the skb is not
+ * subject to CHECKSUM_UNNECESSARY.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3151,7 +3378,18 @@ union bpf_attr {
FN(xdp_output), \
FN(get_netns_cookie), \
FN(get_current_ancestor_cgroup_id), \
- FN(sk_assign),
+ FN(sk_assign), \
+ FN(ktime_get_boot_ns), \
+ FN(seq_printf), \
+ FN(seq_write), \
+ FN(sk_cgroup_id), \
+ FN(sk_ancestor_cgroup_id), \
+ FN(ringbuf_output), \
+ FN(ringbuf_reserve), \
+ FN(ringbuf_submit), \
+ FN(ringbuf_discard), \
+ FN(ringbuf_query), \
+ FN(csum_level),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3228,6 +3466,14 @@ enum {
BPF_F_CURRENT_NETNS = (-1L),
};
+/* BPF_FUNC_csum_level level values. */
+enum {
+ BPF_CSUM_LEVEL_QUERY,
+ BPF_CSUM_LEVEL_INC,
+ BPF_CSUM_LEVEL_DEC,
+ BPF_CSUM_LEVEL_RESET,
+};
+
/* BPF_FUNC_skb_adjust_room flags. */
enum {
BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
@@ -3235,6 +3481,7 @@ enum {
BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
};
enum {
@@ -3261,6 +3508,29 @@ enum {
BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0),
};
+/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and
+ * BPF_FUNC_bpf_ringbuf_output flags.
+ */
+enum {
+ BPF_RB_NO_WAKEUP = (1ULL << 0),
+ BPF_RB_FORCE_WAKEUP = (1ULL << 1),
+};
+
+/* BPF_FUNC_bpf_ringbuf_query flags */
+enum {
+ BPF_RB_AVAIL_DATA = 0,
+ BPF_RB_RING_SIZE = 1,
+ BPF_RB_CONS_POS = 2,
+ BPF_RB_PROD_POS = 3,
+};
+
+/* BPF ring buffer constants */
+enum {
+ BPF_RINGBUF_BUSY_BIT = (1U << 31),
+ BPF_RINGBUF_DISCARD_BIT = (1U << 30),
+ BPF_RINGBUF_HDR_SZ = 8,
+};
+
/* Mode for BPF_FUNC_skb_adjust_room helper. */
enum bpf_adj_room_mode {
BPF_ADJ_ROOM_NET,
@@ -3393,6 +3663,7 @@ struct bpf_sock {
__u32 dst_ip4;
__u32 dst_ip6[4];
__u32 state;
+ __s32 rx_queue_mapping;
};
struct bpf_tcp_sock {
@@ -3486,6 +3757,21 @@ struct xdp_md {
/* Below access go through struct xdp_rxq_info */
__u32 ingress_ifindex; /* rxq->dev->ifindex */
__u32 rx_queue_index; /* rxq->queue_index */
+
+ __u32 egress_ifindex; /* txq->dev->ifindex */
+};
+
+/* DEVMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_devmap_val {
+ __u32 ifindex; /* device index */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
};
enum sk_action {
@@ -3508,6 +3794,8 @@ struct sk_msg_md {
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
__u32 size; /* Total size of sk_msg */
+
+ __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */
};
struct sk_reuseport_md {
@@ -3598,6 +3886,29 @@ struct bpf_btf_info {
__u32 id;
} __attribute__((aligned(8)));
+struct bpf_link_info {
+ __u32 type;
+ __u32 id;
+ __u32 prog_id;
+ union {
+ struct {
+ __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+ __u32 tp_name_len; /* in/out: tp_name buffer len */
+ } raw_tracepoint;
+ struct {
+ __u32 attach_type;
+ } tracing;
+ struct {
+ __u64 cgroup_id;
+ __u32 attach_type;
+ } cgroup;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
+ };
+} __attribute__((aligned(8)));
+
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
* by user and intended to be used by socket (e.g. to bind to, depends on
* attach attach type).
@@ -3610,7 +3921,7 @@ struct bpf_sock_addr {
__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.
+ __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write.
* Stored in network byte order
*/
__u32 family; /* Allows 4-byte read, but no write */
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 8e322e2c7e78..a3f3975df0de 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -519,15 +519,6 @@ struct btrfs_extent_inline_ref {
__le64 offset;
} __attribute__ ((__packed__));
-/* old style backrefs item */
-struct btrfs_extent_ref_v0 {
- __le64 root;
- __le64 generation;
- __le64 objectid;
- __le32 count;
-} __attribute__ ((__packed__));
-
-
/* dev extents record free space on individual devices. The owner
* field points back to the chunk allocation mapping tree that allocated
* the extent. The chunk tree uuid field is a way to double check the owner
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 272dc69fa080..48ff0757ae5e 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -274,6 +274,7 @@ struct vfs_ns_cap_data {
arbitrary SCSI commands */
/* Allow setting encryption key on loopback filesystem */
/* Allow setting zone reclaim policy */
+/* Allow everything under CAP_BPF and CAP_PERFMON for backward compatibility */
#define CAP_SYS_ADMIN 21
@@ -332,6 +333,8 @@ struct vfs_ns_cap_data {
#define CAP_AUDIT_CONTROL 30
+/* Set or remove capabilities on files */
+
#define CAP_SETFCAP 31
/* Override MAC access.
@@ -367,8 +370,45 @@ struct vfs_ns_cap_data {
#define CAP_AUDIT_READ 37
+/*
+ * Allow system performance and observability privileged operations
+ * using perf_events, i915_perf and other kernel subsystems
+ */
+
+#define CAP_PERFMON 38
+
+/*
+ * CAP_BPF allows the following BPF operations:
+ * - Creating all types of BPF maps
+ * - Advanced verifier features
+ * - Indirect variable access
+ * - Bounded loops
+ * - BPF to BPF function calls
+ * - Scalar precision tracking
+ * - Larger complexity limits
+ * - Dead code elimination
+ * - And potentially other features
+ * - Loading BPF Type Format (BTF) data
+ * - Retrieve xlated and JITed code of BPF programs
+ * - Use bpf_spin_lock() helper
+ *
+ * CAP_PERFMON relaxes the verifier checks further:
+ * - BPF progs can use of pointer-to-integer conversions
+ * - speculation attack hardening measures are bypassed
+ * - bpf_probe_read to read arbitrary kernel memory is allowed
+ * - bpf_trace_printk to print kernel memory is allowed
+ *
+ * CAP_SYS_ADMIN is required to use bpf_probe_write_user.
+ *
+ * CAP_SYS_ADMIN is required to iterate system wide loaded
+ * programs, maps, links, BTFs and convert their IDs to file descriptors.
+ *
+ * CAP_PERFMON and CAP_BPF are required to load tracing programs.
+ * CAP_NET_ADMIN and CAP_BPF are required to load networking programs.
+ */
+#define CAP_BPF 39
-#define CAP_LAST_CAP CAP_AUDIT_READ
+#define CAP_LAST_CAP CAP_BPF
#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 1ae90e06c06d..08563e6a424d 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -233,10 +233,13 @@ enum {
* @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
* sent to the CPU.
* @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU.
+ * @DEVLINK_TRAP_ACTION_MIRROR: Packet is forwarded by the device and a copy is
+ * sent to the CPU.
*/
enum devlink_trap_action {
DEVLINK_TRAP_ACTION_DROP,
DEVLINK_TRAP_ACTION_TRAP,
+ DEVLINK_TRAP_ACTION_MIRROR,
};
/**
@@ -250,10 +253,16 @@ enum devlink_trap_action {
* control plane for resolution. Trapped packets
* are processed by devlink and injected to
* the kernel's Rx path.
+ * @DEVLINK_TRAP_TYPE_CONTROL: Packet was trapped because it is required for
+ * the correct functioning of the control plane.
+ * For example, an ARP request packet. Trapped
+ * packets are injected to the kernel's Rx path,
+ * but not reported to drop monitor.
*/
enum devlink_trap_type {
DEVLINK_TRAP_TYPE_DROP,
DEVLINK_TRAP_TYPE_EXCEPTION,
+ DEVLINK_TRAP_TYPE_CONTROL,
};
enum {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 34c02e4290fe..c6dd0215482e 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -36,6 +36,7 @@ typedef __s64 Elf64_Sxword;
#define PT_LOPROC 0x70000000
#define PT_HIPROC 0x7fffffff
#define PT_GNU_EH_FRAME 0x6474e550
+#define PT_GNU_PROPERTY 0x6474e553
#define PT_GNU_STACK (PT_LOOS + 0x474e551)
@@ -367,6 +368,7 @@ typedef struct elf64_shdr {
* Notes used in ET_CORE. Architectures export some of the arch register sets
* using the corresponding note types via the PTRACE_GETREGSET and
* PTRACE_SETREGSET requests.
+ * The note name for all these is "LINUX".
*/
#define NT_PRSTATUS 1
#define NT_PRFPREG 2
@@ -429,6 +431,9 @@ typedef struct elf64_shdr {
#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */
#define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */
+/* Note types with note name "GNU" */
+#define NT_GNU_PROPERTY_TYPE_0 5
+
/* Note header in a PT_NOTE section */
typedef struct elf32_note {
Elf32_Word n_namesz; /* Name size */
@@ -443,4 +448,10 @@ typedef struct elf64_note {
Elf64_Word n_type; /* Content type */
} Elf64_Nhdr;
+/* .note.gnu.property types for EM_AARCH64: */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000
+
+/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0)
+
#endif /* _UAPI_LINUX_ELF_H */
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index 0cca19670fd2..ca5cb3e3c6df 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -36,7 +36,7 @@ struct sock_extended_err {
*
* The timestamping interfaces SO_TIMESTAMPING, MSG_TSTAMP_*
* communicate network timestamps by passing this struct in a cmsg with
- * recvmsg(). See Documentation/networking/timestamping.txt for details.
+ * recvmsg(). See Documentation/networking/timestamping.rst for details.
* User space sees a timespec definition that matches either
* __kernel_timespec or __kernel_old_timespec, in the kernel we
* require two structure definitions to provide both.
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 92f737f10117..f4662b3a9e1e 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1666,6 +1666,18 @@ static inline int ethtool_validate_duplex(__u8 duplex)
return 0;
}
+#define MASTER_SLAVE_CFG_UNSUPPORTED 0
+#define MASTER_SLAVE_CFG_UNKNOWN 1
+#define MASTER_SLAVE_CFG_MASTER_PREFERRED 2
+#define MASTER_SLAVE_CFG_SLAVE_PREFERRED 3
+#define MASTER_SLAVE_CFG_MASTER_FORCE 4
+#define MASTER_SLAVE_CFG_SLAVE_FORCE 5
+#define MASTER_SLAVE_STATE_UNSUPPORTED 0
+#define MASTER_SLAVE_STATE_UNKNOWN 1
+#define MASTER_SLAVE_STATE_MASTER 2
+#define MASTER_SLAVE_STATE_SLAVE 3
+#define MASTER_SLAVE_STATE_ERR 4
+
/* Which connector port. */
#define PORT_TP 0x00
#define PORT_AUI 0x01
@@ -1904,7 +1916,9 @@ struct ethtool_link_settings {
__u8 eth_tp_mdix_ctrl;
__s8 link_mode_masks_nwords;
__u8 transceiver;
- __u8 reserved1[3];
+ __u8 master_slave_cfg;
+ __u8 master_slave_state;
+ __u8 reserved1[1];
__u32 reserved[7];
__u32 link_mode_masks[0];
/* layout of link_mode_masks fields:
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 7fde76366ba4..4dda5e4244a7 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -2,7 +2,7 @@
/*
* include/uapi/linux/ethtool_netlink.h - netlink interface for ethtool
*
- * See Documentation/networking/ethtool-netlink.txt in kernel source tree for
+ * See Documentation/networking/ethtool-netlink.rst in kernel source tree for
* doucumentation of the interface.
*/
@@ -39,6 +39,8 @@ enum {
ETHTOOL_MSG_EEE_GET,
ETHTOOL_MSG_EEE_SET,
ETHTOOL_MSG_TSINFO_GET,
+ ETHTOOL_MSG_CABLE_TEST_ACT,
+ ETHTOOL_MSG_CABLE_TEST_TDR_ACT,
/* add new constants above here */
__ETHTOOL_MSG_USER_CNT,
@@ -74,6 +76,8 @@ enum {
ETHTOOL_MSG_EEE_GET_REPLY,
ETHTOOL_MSG_EEE_NTF,
ETHTOOL_MSG_TSINFO_GET_REPLY,
+ ETHTOOL_MSG_CABLE_TEST_NTF,
+ ETHTOOL_MSG_CABLE_TEST_TDR_NTF,
/* add new constants above here */
__ETHTOOL_MSG_KERNEL_CNT,
@@ -216,6 +220,8 @@ enum {
ETHTOOL_A_LINKMODES_PEER, /* bitset */
ETHTOOL_A_LINKMODES_SPEED, /* u32 */
ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */
+ ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */
+ ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */
/* add new constants above here */
__ETHTOOL_A_LINKMODES_CNT,
@@ -228,6 +234,8 @@ enum {
ETHTOOL_A_LINKSTATE_UNSPEC,
ETHTOOL_A_LINKSTATE_HEADER, /* nest - _A_HEADER_* */
ETHTOOL_A_LINKSTATE_LINK, /* u8 */
+ ETHTOOL_A_LINKSTATE_SQI, /* u32 */
+ ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */
/* add new constants above here */
__ETHTOOL_A_LINKSTATE_CNT,
@@ -403,6 +411,149 @@ enum {
ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1)
};
+/* CABLE TEST */
+
+enum {
+ ETHTOOL_A_CABLE_TEST_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_HEADER, /* nest - _A_HEADER_* */
+
+ /* add new constants above here */
+ __ETHTOOL_A_CABLE_TEST_CNT,
+ ETHTOOL_A_CABLE_TEST_MAX = __ETHTOOL_A_CABLE_TEST_CNT - 1
+};
+
+/* CABLE TEST NOTIFY */
+enum {
+ ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC,
+ ETHTOOL_A_CABLE_RESULT_CODE_OK,
+ ETHTOOL_A_CABLE_RESULT_CODE_OPEN,
+ ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT,
+ ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT,
+};
+
+enum {
+ ETHTOOL_A_CABLE_PAIR_A,
+ ETHTOOL_A_CABLE_PAIR_B,
+ ETHTOOL_A_CABLE_PAIR_C,
+ ETHTOOL_A_CABLE_PAIR_D,
+};
+
+enum {
+ ETHTOOL_A_CABLE_RESULT_UNSPEC,
+ ETHTOOL_A_CABLE_RESULT_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */
+ ETHTOOL_A_CABLE_RESULT_CODE, /* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */
+
+ __ETHTOOL_A_CABLE_RESULT_CNT,
+ ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC,
+ ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */
+ ETHTOOL_A_CABLE_FAULT_LENGTH_CM, /* u32 */
+
+ __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT,
+ ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_TEST_NTF_STATUS_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_NTF_STATUS_STARTED,
+ ETHTOOL_A_CABLE_TEST_NTF_STATUS_COMPLETED
+};
+
+enum {
+ ETHTOOL_A_CABLE_NEST_UNSPEC,
+ ETHTOOL_A_CABLE_NEST_RESULT, /* nest - ETHTOOL_A_CABLE_RESULT_ */
+ ETHTOOL_A_CABLE_NEST_FAULT_LENGTH, /* nest - ETHTOOL_A_CABLE_FAULT_LENGTH_ */
+ __ETHTOOL_A_CABLE_NEST_CNT,
+ ETHTOOL_A_CABLE_NEST_MAX = (__ETHTOOL_A_CABLE_NEST_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_TEST_NTF_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */
+ ETHTOOL_A_CABLE_TEST_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */
+ ETHTOOL_A_CABLE_TEST_NTF_NEST, /* nest - of results: */
+
+ __ETHTOOL_A_CABLE_TEST_NTF_CNT,
+ ETHTOOL_A_CABLE_TEST_NTF_MAX = (__ETHTOOL_A_CABLE_TEST_NTF_CNT - 1)
+};
+
+/* CABLE TEST TDR */
+
+enum {
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST, /* u32 */
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST, /* u32 */
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP, /* u32 */
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR, /* u8 */
+
+ /* add new constants above here */
+ __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT,
+ ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CFG_CNT - 1
+};
+
+enum {
+ ETHTOOL_A_CABLE_TEST_TDR_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_TDR_HEADER, /* nest - _A_HEADER_* */
+ ETHTOOL_A_CABLE_TEST_TDR_CFG, /* nest - *_TDR_CFG_* */
+
+ /* add new constants above here */
+ __ETHTOOL_A_CABLE_TEST_TDR_CNT,
+ ETHTOOL_A_CABLE_TEST_TDR_MAX = __ETHTOOL_A_CABLE_TEST_TDR_CNT - 1
+};
+
+/* CABLE TEST TDR NOTIFY */
+
+enum {
+ ETHTOOL_A_CABLE_AMPLITUDE_UNSPEC,
+ ETHTOOL_A_CABLE_AMPLITUDE_PAIR, /* u8 */
+ ETHTOOL_A_CABLE_AMPLITUDE_mV, /* s16 */
+
+ __ETHTOOL_A_CABLE_AMPLITUDE_CNT,
+ ETHTOOL_A_CABLE_AMPLITUDE_MAX = (__ETHTOOL_A_CABLE_AMPLITUDE_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_PULSE_UNSPEC,
+ ETHTOOL_A_CABLE_PULSE_mV, /* s16 */
+
+ __ETHTOOL_A_CABLE_PULSE_CNT,
+ ETHTOOL_A_CABLE_PULSE_MAX = (__ETHTOOL_A_CABLE_PULSE_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_STEP_UNSPEC,
+ ETHTOOL_A_CABLE_STEP_FIRST_DISTANCE, /* u32 */
+ ETHTOOL_A_CABLE_STEP_LAST_DISTANCE, /* u32 */
+ ETHTOOL_A_CABLE_STEP_STEP_DISTANCE, /* u32 */
+
+ __ETHTOOL_A_CABLE_STEP_CNT,
+ ETHTOOL_A_CABLE_STEP_MAX = (__ETHTOOL_A_CABLE_STEP_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_TDR_NEST_UNSPEC,
+ ETHTOOL_A_CABLE_TDR_NEST_STEP, /* nest - ETHTTOOL_A_CABLE_STEP */
+ ETHTOOL_A_CABLE_TDR_NEST_AMPLITUDE, /* nest - ETHTOOL_A_CABLE_AMPLITUDE */
+ ETHTOOL_A_CABLE_TDR_NEST_PULSE, /* nest - ETHTOOL_A_CABLE_PULSE */
+
+ __ETHTOOL_A_CABLE_TDR_NEST_CNT,
+ ETHTOOL_A_CABLE_TDR_NEST_MAX = (__ETHTOOL_A_CABLE_TDR_NEST_CNT - 1)
+};
+
+enum {
+ ETHTOOL_A_CABLE_TEST_TDR_NTF_UNSPEC,
+ ETHTOOL_A_CABLE_TEST_TDR_NTF_HEADER, /* nest - ETHTOOL_A_HEADER_* */
+ ETHTOOL_A_CABLE_TEST_TDR_NTF_STATUS, /* u8 - _STARTED/_COMPLETE */
+ ETHTOOL_A_CABLE_TEST_TDR_NTF_NEST, /* nest - of results: */
+
+ /* add new constants above here */
+ __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT,
+ ETHTOOL_A_CABLE_TEST_TDR_NTF_MAX = __ETHTOOL_A_CABLE_TEST_TDR_NTF_CNT - 1
+};
+
/* generic netlink info */
#define ETHTOOL_GENL_NAME "ethtool"
#define ETHTOOL_GENL_VERSION 1
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index ca88b7bce553..2f86b2ad6d7e 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -84,10 +84,20 @@
#define DN_ATTRIB 0x00000020 /* File changed attibutes */
#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat. The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
#define AT_FDCWD -100 /* Special value used to indicate
openat should use the current
working directory. */
#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
+#define AT_EACCESS 0x200 /* Test access permitted for
+ effective IDs, not real IDs. */
#define AT_REMOVEDIR 0x200 /* Remove directory instead of
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
diff --git a/include/uapi/linux/fd.h b/include/uapi/linux/fd.h
index 90fb94712c41..8b80c63b971c 100644
--- a/include/uapi/linux/fd.h
+++ b/include/uapi/linux/fd.h
@@ -172,7 +172,10 @@ struct floppy_drive_params {
* used in succession to try to read the disk. If the FDC cannot lock onto
* the disk, the next format is tried. This uses the variable 'probing'.
*/
- short autodetect[8]; /* autodetected formats */
+
+#define FD_AUTODETECT_SIZE 8
+
+ short autodetect[FD_AUTODETECT_SIZE]; /* autodetected formats */
int checkfreq; /* how often should the drive be checked for disk
* changes */
@@ -357,10 +360,25 @@ struct floppy_raw_cmd {
int buffer_length; /* length of allocated buffer */
unsigned char rate;
+
+#define FD_RAW_CMD_SIZE 16
+#define FD_RAW_REPLY_SIZE 16
+#define FD_RAW_CMD_FULLSIZE (FD_RAW_CMD_SIZE + 1 + FD_RAW_REPLY_SIZE)
+
+ /* The command may take up the space initially intended for the reply
+ * and the reply count. Needed for long 82078 commands such as RESTORE,
+ * which takes 17 command bytes.
+ */
+
unsigned char cmd_count;
- unsigned char cmd[16];
- unsigned char reply_count;
- unsigned char reply[16];
+ union {
+ struct {
+ unsigned char cmd[FD_RAW_CMD_SIZE];
+ unsigned char reply_count;
+ unsigned char reply[FD_RAW_REPLY_SIZE];
+ };
+ unsigned char fullcmd[FD_RAW_CMD_FULLSIZE];
+ };
int track;
int resultcode;
diff --git a/include/uapi/linux/fdreg.h b/include/uapi/linux/fdreg.h
index 1318881954e1..10d33632939d 100644
--- a/include/uapi/linux/fdreg.h
+++ b/include/uapi/linux/fdreg.h
@@ -7,13 +7,23 @@
* Handbook", Sanches and Canton.
*/
-/* Fd controller regs. S&C, about page 340 */
-#define FD_STATUS 4
-#define FD_DATA 5
+/* 82077's auxiliary status registers A & B (R) */
+#define FD_SRA 0
+#define FD_SRB 1
/* Digital Output Register */
#define FD_DOR 2
+/* 82077's tape drive register (R/W) */
+#define FD_TDR 3
+
+/* 82077's data rate select register (W) */
+#define FD_DSR 4
+
+/* Fd controller regs. S&C, about page 340 */
+#define FD_STATUS 4
+#define FD_DATA 5
+
/* Digital Input Register (read) */
#define FD_DIR 7
diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h
index 8c0bc24d5d95..07c1cdcb715e 100644
--- a/include/uapi/linux/fiemap.h
+++ b/include/uapi/linux/fiemap.h
@@ -9,8 +9,8 @@
* Andreas Dilger <adilger@sun.com>
*/
-#ifndef _LINUX_FIEMAP_H
-#define _LINUX_FIEMAP_H
+#ifndef _UAPI_LINUX_FIEMAP_H
+#define _UAPI_LINUX_FIEMAP_H
#include <linux/types.h>
@@ -67,4 +67,4 @@ struct fiemap {
#define FIEMAP_EXTENT_SHARED 0x00002000 /* Space shared with other
* files. */
-#endif /* _LINUX_FIEMAP_H */
+#endif /* _UAPI_LINUX_FIEMAP_H */
diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h
index 1acd2b179aef..7e5b5c10a49c 100644
--- a/include/uapi/linux/firewire-cdev.h
+++ b/include/uapi/linux/firewire-cdev.h
@@ -308,7 +308,7 @@ struct fw_cdev_event_iso_interrupt_mc {
/**
* struct fw_cdev_event_iso_resource - Iso resources were allocated or freed
* @closure: See &fw_cdev_event_common;
- * set by %FW_CDEV_IOC_(DE)ALLOCATE_ISO_RESOURCE(_ONCE) ioctl
+ * set by``FW_CDEV_IOC_(DE)ALLOCATE_ISO_RESOURCE(_ONCE)`` ioctl
* @type: %FW_CDEV_EVENT_ISO_RESOURCE_ALLOCATED or
* %FW_CDEV_EVENT_ISO_RESOURCE_DEALLOCATED
* @handle: Reference by which an allocated resource can be deallocated
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index a10e3cdc2839..7875709ccfeb 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -19,7 +19,8 @@
#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08
-#define FSCRYPT_POLICY_FLAGS_VALID 0x0F
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10
+#define FSCRYPT_POLICY_FLAGS_VALID 0x1F
/* Encryption algorithms */
#define FSCRYPT_MODE_AES_256_XTS 1
diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index 877f7fa95466..9c0636ec2286 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -48,6 +48,7 @@ enum {
CTRL_CMD_NEWMCAST_GRP,
CTRL_CMD_DELMCAST_GRP,
CTRL_CMD_GETMCAST_GRP, /* unused */
+ CTRL_CMD_GETPOLICY,
__CTRL_CMD_MAX,
};
@@ -62,6 +63,7 @@ enum {
CTRL_ATTR_MAXATTR,
CTRL_ATTR_OPS,
CTRL_ATTR_MCAST_GROUPS,
+ CTRL_ATTR_POLICY,
__CTRL_ATTR_MAX,
};
diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h
index 2dc10a034de1..07e508e6691b 100644
--- a/include/uapi/linux/gfs2_ondisk.h
+++ b/include/uapi/linux/gfs2_ondisk.h
@@ -171,6 +171,12 @@ struct gfs2_rindex {
#define GFS2_RGF_NOALLOC 0x00000008
#define GFS2_RGF_TRIMMED 0x00000010
+struct gfs2_inode_lvb {
+ __be32 ri_magic;
+ __be32 __pad;
+ __be64 ri_generation_deleted;
+};
+
struct gfs2_rgrp_lvb {
__be32 rl_magic;
__be32 rl_flags;
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index be714cd8c826..797ba2c1562a 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -178,6 +178,7 @@ enum {
enum {
IF_LINK_MODE_DEFAULT,
IF_LINK_MODE_DORMANT, /* limit upward transition to dormant */
+ IF_LINK_MODE_TESTING, /* limit upward transition to testing */
};
/*
diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index bfe621ea51b3..caa6914a3e53 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -120,6 +120,7 @@ enum {
IFLA_BRIDGE_MODE,
IFLA_BRIDGE_VLAN_INFO,
IFLA_BRIDGE_VLAN_TUNNEL_INFO,
+ IFLA_BRIDGE_MRP,
__IFLA_BRIDGE_MAX,
};
#define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1)
@@ -157,6 +158,101 @@ struct bridge_vlan_xstats {
__u32 pad2;
};
+enum {
+ IFLA_BRIDGE_MRP_UNSPEC,
+ IFLA_BRIDGE_MRP_INSTANCE,
+ IFLA_BRIDGE_MRP_PORT_STATE,
+ IFLA_BRIDGE_MRP_PORT_ROLE,
+ IFLA_BRIDGE_MRP_RING_STATE,
+ IFLA_BRIDGE_MRP_RING_ROLE,
+ IFLA_BRIDGE_MRP_START_TEST,
+ __IFLA_BRIDGE_MRP_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_MAX (__IFLA_BRIDGE_MRP_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_INSTANCE_UNSPEC,
+ IFLA_BRIDGE_MRP_INSTANCE_RING_ID,
+ IFLA_BRIDGE_MRP_INSTANCE_P_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_S_IFINDEX,
+ IFLA_BRIDGE_MRP_INSTANCE_PRIO,
+ __IFLA_BRIDGE_MRP_INSTANCE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_INSTANCE_MAX (__IFLA_BRIDGE_MRP_INSTANCE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_STATE_STATE,
+ __IFLA_BRIDGE_MRP_PORT_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_STATE_MAX (__IFLA_BRIDGE_MRP_PORT_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_PORT_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_PORT_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_PORT_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_PORT_ROLE_MAX (__IFLA_BRIDGE_MRP_PORT_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_STATE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_STATE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_STATE_STATE,
+ __IFLA_BRIDGE_MRP_RING_STATE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_STATE_MAX (__IFLA_BRIDGE_MRP_RING_STATE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_RING_ROLE_UNSPEC,
+ IFLA_BRIDGE_MRP_RING_ROLE_RING_ID,
+ IFLA_BRIDGE_MRP_RING_ROLE_ROLE,
+ __IFLA_BRIDGE_MRP_RING_ROLE_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_RING_ROLE_MAX (__IFLA_BRIDGE_MRP_RING_ROLE_MAX - 1)
+
+enum {
+ IFLA_BRIDGE_MRP_START_TEST_UNSPEC,
+ IFLA_BRIDGE_MRP_START_TEST_RING_ID,
+ IFLA_BRIDGE_MRP_START_TEST_INTERVAL,
+ IFLA_BRIDGE_MRP_START_TEST_MAX_MISS,
+ IFLA_BRIDGE_MRP_START_TEST_PERIOD,
+ IFLA_BRIDGE_MRP_START_TEST_MONITOR,
+ __IFLA_BRIDGE_MRP_START_TEST_MAX,
+};
+
+#define IFLA_BRIDGE_MRP_START_TEST_MAX (__IFLA_BRIDGE_MRP_START_TEST_MAX - 1)
+
+struct br_mrp_instance {
+ __u32 ring_id;
+ __u32 p_ifindex;
+ __u32 s_ifindex;
+ __u16 prio;
+};
+
+struct br_mrp_ring_state {
+ __u32 ring_id;
+ __u32 ring_state;
+};
+
+struct br_mrp_ring_role {
+ __u32 ring_id;
+ __u32 ring_role;
+};
+
+struct br_mrp_start_test {
+ __u32 ring_id;
+ __u32 interval;
+ __u32 max_miss;
+ __u32 period;
+ __u32 monitor;
+};
+
struct bridge_stp_xstats {
__u64 transition_blk;
__u64 transition_fwd;
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index f6ceb2e63d1e..d6de2b167448 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -92,6 +92,7 @@
#define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */
#define ETH_P_TIPC 0x88CA /* TIPC */
#define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */
+#define ETH_P_MRP 0x88E3 /* Media Redundancy Protocol */
#define ETH_P_MACSEC 0x88E5 /* 802.1ae MACsec */
#define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */
#define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 127c704eeba9..a009365ad67b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -343,6 +343,7 @@ enum {
IFLA_BRPORT_NEIGH_SUPPRESS,
IFLA_BRPORT_ISOLATED,
IFLA_BRPORT_BACKUP_PORT,
+ IFLA_BRPORT_MRP_RING_OPEN,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/include/uapi/linux/if_x25.h b/include/uapi/linux/if_x25.h
index 5d962448345f..3a5938e38370 100644
--- a/include/uapi/linux/if_x25.h
+++ b/include/uapi/linux/if_x25.h
@@ -18,7 +18,7 @@
#include <linux/types.h>
-/* Documentation/networking/x25-iface.txt */
+/* Documentation/networking/x25-iface.rst */
#define X25_IFACE_DATA 0x00
#define X25_IFACE_CONNECT 0x01
#define X25_IFACE_DISCONNECT 0x02
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 57cc429a9177..e6f183ee8417 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -96,6 +96,7 @@ enum {
INET_DIAG_BC_MARK_COND,
INET_DIAG_BC_S_EQ,
INET_DIAG_BC_D_EQ,
+ INET_DIAG_BC_CGROUP_COND, /* u64 cgroup v2 ID */
};
struct inet_diag_hostcond {
@@ -157,6 +158,7 @@ enum {
INET_DIAG_MD5SIG,
INET_DIAG_ULP_INFO,
INET_DIAG_SK_BPF_STORAGES,
+ INET_DIAG_CGROUP_ID,
__INET_DIAG_MAX,
};
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e48d746b8e2a..92c22699a5a7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -129,6 +129,7 @@ enum {
IORING_OP_SPLICE,
IORING_OP_PROVIDE_BUFFERS,
IORING_OP_REMOVE_BUFFERS,
+ IORING_OP_TEE,
/* this goes last, obviously */
IORING_OP_LAST,
@@ -204,10 +205,19 @@ struct io_cqring_offsets {
__u32 ring_entries;
__u32 overflow;
__u32 cqes;
- __u64 resv[2];
+ __u32 flags;
+ __u32 resv1;
+ __u64 resv2;
};
/*
+ * cq_ring->flags
+ */
+
+/* disable eventfd notifications */
+#define IORING_CQ_EVENTFD_DISABLED (1U << 0)
+
+/*
* io_uring_enter(2) flags
*/
#define IORING_ENTER_GETEVENTS (1U << 0)
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index 4ad3496e5c43..e907b7091a46 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -285,6 +285,11 @@ struct iommu_gpasid_bind_data_vtd {
__u32 emt;
};
+#define IOMMU_SVA_VTD_GPASID_MTS_MASK (IOMMU_SVA_VTD_GPASID_CD | \
+ IOMMU_SVA_VTD_GPASID_EMTE | \
+ IOMMU_SVA_VTD_GPASID_PCD | \
+ IOMMU_SVA_VTD_GPASID_PWT)
+
/**
* struct iommu_gpasid_bind_data - Information about device and guest PASID binding
* @version: Version of this data structure
diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h
index ed3d5893830d..4c8884eea808 100644
--- a/include/uapi/linux/keyctl.h
+++ b/include/uapi/linux/keyctl.h
@@ -69,6 +69,7 @@
#define KEYCTL_RESTRICT_KEYRING 29 /* Restrict keys allowed to link to a keyring */
#define KEYCTL_MOVE 30 /* Move keys between keyrings */
#define KEYCTL_CAPABILITIES 31 /* Find capabilities of keyrings subsystem */
+#define KEYCTL_WATCH_KEY 32 /* Watch a key or ring of keys for changes */
/* keyctl structures */
struct keyctl_dh_params {
@@ -130,5 +131,6 @@ struct keyctl_pkey_params {
#define KEYCTL_CAPS0_MOVE 0x80 /* KEYCTL_MOVE supported */
#define KEYCTL_CAPS1_NS_KEYRING_NAME 0x01 /* Keyring names are per-user_namespace */
#define KEYCTL_CAPS1_NS_KEY_TAG 0x02 /* Key indexing can include a namespace tag */
+#define KEYCTL_CAPS1_NOTIFICATIONS 0x04 /* Keys generate watchable notifications */
#endif /* _LINUX_KEYCTL_H */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 20917c59f39c..b6be62356d34 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -251,7 +251,7 @@ struct kfd_memory_exception_failure {
__u32 imprecise; /* Can't determine the exact fault address */
};
-/* memory exception data*/
+/* memory exception data */
struct kfd_hsa_memory_exception_data {
struct kfd_memory_exception_failure failure;
__u64 va;
@@ -410,6 +410,20 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
__u32 n_success; /* to/from KFD */
};
+/* Allocate GWS for specific queue
+ *
+ * @queue_id: queue's id that GWS is allocated for
+ * @num_gws: how many GWS to allocate
+ * @first_gws: index of the first GWS allocated.
+ * only support contiguous GWS allocation
+ */
+struct kfd_ioctl_alloc_queue_gws_args {
+ __u32 queue_id; /* to KFD */
+ __u32 num_gws; /* to KFD */
+ __u32 first_gws; /* from KFD */
+ __u32 pad;
+};
+
struct kfd_ioctl_get_dmabuf_info_args {
__u64 size; /* from KFD */
__u64 metadata_ptr; /* to KFD */
@@ -529,7 +543,10 @@ enum kfd_mmio_remap {
#define AMDKFD_IOC_IMPORT_DMABUF \
AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)
+#define AMDKFD_IOC_ALLOC_QUEUE_GWS \
+ AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
+
#define AMDKFD_COMMAND_START 0x01
-#define AMDKFD_COMMAND_END 0x1E
+#define AMDKFD_COMMAND_END 0x1F
#endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 428c7dde6b4b..4fdf30316582 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -116,7 +116,7 @@ struct kvm_irq_level {
* 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/virt/kvm/api.txt
+ * For ARM: See Documentation/virt/kvm/api.rst
*/
union {
__u32 irq;
@@ -188,10 +188,13 @@ struct kvm_s390_cmma_log {
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
+#define KVM_EXIT_HYPERV_SYNDBG 3
__u32 type;
+ __u32 pad1;
union {
struct {
__u32 msr;
+ __u32 pad2;
__u64 control;
__u64 evt_page;
__u64 msg_page;
@@ -201,6 +204,15 @@ struct kvm_hyperv_exit {
__u64 result;
__u64 params[2];
} hcall;
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 status;
+ __u64 send_page;
+ __u64 recv_page;
+ __u64 pending_page;
+ } syndbg;
} u;
};
@@ -1017,6 +1029,8 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_VCPU_RESETS 179
#define KVM_CAP_S390_PROTECTED 180
#define KVM_CAP_PPC_SECURE_GUEST 181
+#define KVM_CAP_HALT_POLL 182
+#define KVM_CAP_ASYNC_PF_INT 183
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1107,7 +1121,7 @@ struct kvm_xen_hvm_config {
*
* KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
* the irqfd to operate in resampling mode for level triggered interrupt
- * emulation. See Documentation/virt/kvm/api.txt.
+ * emulation. See Documentation/virt/kvm/api.rst.
*/
#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h
index 080a8df134ef..24a1c45bd1ae 100644
--- a/include/uapi/linux/loop.h
+++ b/include/uapi/linux/loop.h
@@ -25,6 +25,16 @@ enum {
LO_FLAGS_DIRECT_IO = 16,
};
+/* LO_FLAGS that can be set using LOOP_SET_STATUS(64) */
+#define LOOP_SET_STATUS_SETTABLE_FLAGS (LO_FLAGS_AUTOCLEAR | LO_FLAGS_PARTSCAN)
+
+/* LO_FLAGS that can be cleared using LOOP_SET_STATUS(64) */
+#define LOOP_SET_STATUS_CLEARABLE_FLAGS (LO_FLAGS_AUTOCLEAR)
+
+/* LO_FLAGS that can be set using LOOP_CONFIGURE */
+#define LOOP_CONFIGURE_SETTABLE_FLAGS (LO_FLAGS_READ_ONLY | LO_FLAGS_AUTOCLEAR \
+ | LO_FLAGS_PARTSCAN | LO_FLAGS_DIRECT_IO)
+
#include <asm/posix_types.h> /* for __kernel_old_dev_t */
#include <linux/types.h> /* for __u64 */
@@ -37,7 +47,7 @@ struct loop_info {
int lo_offset;
int lo_encrypt_type;
int lo_encrypt_key_size; /* ioctl w/o */
- int lo_flags; /* ioctl r/o */
+ int lo_flags;
char lo_name[LO_NAME_SIZE];
unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
unsigned long lo_init[2];
@@ -53,13 +63,29 @@ struct loop_info64 {
__u32 lo_number; /* ioctl r/o */
__u32 lo_encrypt_type;
__u32 lo_encrypt_key_size; /* ioctl w/o */
- __u32 lo_flags; /* ioctl r/o */
+ __u32 lo_flags;
__u8 lo_file_name[LO_NAME_SIZE];
__u8 lo_crypt_name[LO_NAME_SIZE];
__u8 lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
__u64 lo_init[2];
};
+/**
+ * struct loop_config - Complete configuration for a loop device.
+ * @fd: fd of the file to be used as a backing file for the loop device.
+ * @block_size: block size to use; ignored if 0.
+ * @info: struct loop_info64 to configure the loop device with.
+ *
+ * This structure is used with the LOOP_CONFIGURE ioctl, and can be used to
+ * atomically setup and configure all loop device parameters at once.
+ */
+struct loop_config {
+ __u32 fd;
+ __u32 block_size;
+ struct loop_info64 info;
+ __u64 __reserved[8];
+};
+
/*
* Loop filter types
*/
@@ -90,6 +116,7 @@ struct loop_info64 {
#define LOOP_SET_CAPACITY 0x4C07
#define LOOP_SET_DIRECT_IO 0x4C08
#define LOOP_SET_BLOCK_SIZE 0x4C09
+#define LOOP_CONFIGURE 0x4C0A
/* /dev/loop-control interface */
#define LOOP_CTL_ADD 0x4C80
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index d78064007b17..f3956fc11de6 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -94,6 +94,7 @@
#define BALLOON_KVM_MAGIC 0x13661366
#define ZSMALLOC_MAGIC 0x58295829
#define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */
+#define DEVMEM_MAGIC 0x454d444d /* "DMEM" */
#define Z3FOLD_MAGIC 0x33
#define PPC_CMM_MAGIC 0xc7571590
diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h
index 90f9b4e1ba27..39f7c44baf53 100644
--- a/include/uapi/linux/mii.h
+++ b/include/uapi/linux/mii.h
@@ -151,11 +151,13 @@
/* 1000BASE-T Control register */
#define ADVERTISE_1000FULL 0x0200 /* Advertise 1000BASE-T full duplex */
#define ADVERTISE_1000HALF 0x0100 /* Advertise 1000BASE-T half duplex */
+#define CTL1000_PREFER_MASTER 0x0400 /* prefer to operate as master */
#define CTL1000_AS_MASTER 0x0800
#define CTL1000_ENABLE_MASTER 0x1000
/* 1000BASE-T Status register */
#define LPA_1000MSFAIL 0x8000 /* Master/Slave resolution failure */
+#define LPA_1000MSRES 0x4000 /* Master/Slave resolution status */
#define LPA_1000LOCALRXOK 0x2000 /* Link partner local receiver status */
#define LPA_1000REMRXOK 0x1000 /* Link partner remote receiver status */
#define LPA_1000FULL 0x0800 /* Link partner 1000BASE-T full duplex */
diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h
index 00c08120f3ba..27a39847d55c 100644
--- a/include/uapi/linux/mmc/ioctl.h
+++ b/include/uapi/linux/mmc/ioctl.h
@@ -3,6 +3,7 @@
#define LINUX_MMC_IOCTL_H
#include <linux/types.h>
+#include <linux/major.h>
struct mmc_ioc_cmd {
/*
diff --git a/include/uapi/linux/mrp_bridge.h b/include/uapi/linux/mrp_bridge.h
new file mode 100644
index 000000000000..84f15f48a7cb
--- /dev/null
+++ b/include/uapi/linux/mrp_bridge.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_MRP_BRIDGE_H_
+#define _UAPI_LINUX_MRP_BRIDGE_H_
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define MRP_MAX_FRAME_LENGTH 200
+#define MRP_DEFAULT_PRIO 0x8000
+#define MRP_DOMAIN_UUID_LENGTH 16
+#define MRP_VERSION 1
+#define MRP_FRAME_PRIO 7
+#define MRP_OUI_LENGTH 3
+#define MRP_MANUFACTURE_DATA_LENGTH 2
+
+enum br_mrp_ring_role_type {
+ BR_MRP_RING_ROLE_DISABLED,
+ BR_MRP_RING_ROLE_MRC,
+ BR_MRP_RING_ROLE_MRM,
+ BR_MRP_RING_ROLE_MRA,
+};
+
+enum br_mrp_ring_state_type {
+ BR_MRP_RING_STATE_OPEN,
+ BR_MRP_RING_STATE_CLOSED,
+};
+
+enum br_mrp_port_state_type {
+ BR_MRP_PORT_STATE_DISABLED,
+ BR_MRP_PORT_STATE_BLOCKED,
+ BR_MRP_PORT_STATE_FORWARDING,
+ BR_MRP_PORT_STATE_NOT_CONNECTED,
+};
+
+enum br_mrp_port_role_type {
+ BR_MRP_PORT_ROLE_PRIMARY,
+ BR_MRP_PORT_ROLE_SECONDARY,
+ BR_MRP_PORT_ROLE_NONE,
+};
+
+enum br_mrp_tlv_header_type {
+ BR_MRP_TLV_HEADER_END = 0x0,
+ BR_MRP_TLV_HEADER_COMMON = 0x1,
+ BR_MRP_TLV_HEADER_RING_TEST = 0x2,
+ BR_MRP_TLV_HEADER_RING_TOPO = 0x3,
+ BR_MRP_TLV_HEADER_RING_LINK_DOWN = 0x4,
+ BR_MRP_TLV_HEADER_RING_LINK_UP = 0x5,
+ BR_MRP_TLV_HEADER_OPTION = 0x7f,
+};
+
+enum br_mrp_sub_tlv_header_type {
+ BR_MRP_SUB_TLV_HEADER_TEST_MGR_NACK = 0x1,
+ BR_MRP_SUB_TLV_HEADER_TEST_PROPAGATE = 0x2,
+ BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR = 0x3,
+};
+
+struct br_mrp_tlv_hdr {
+ __u8 type;
+ __u8 length;
+};
+
+struct br_mrp_sub_tlv_hdr {
+ __u8 type;
+ __u8 length;
+};
+
+struct br_mrp_end_hdr {
+ struct br_mrp_tlv_hdr hdr;
+};
+
+struct br_mrp_common_hdr {
+ __be16 seq_id;
+ __u8 domain[MRP_DOMAIN_UUID_LENGTH];
+};
+
+struct br_mrp_ring_test_hdr {
+ __be16 prio;
+ __u8 sa[ETH_ALEN];
+ __be16 port_role;
+ __be16 state;
+ __be16 transitions;
+ __be32 timestamp;
+};
+
+struct br_mrp_ring_topo_hdr {
+ __be16 prio;
+ __u8 sa[ETH_ALEN];
+ __be16 interval;
+};
+
+struct br_mrp_ring_link_hdr {
+ __u8 sa[ETH_ALEN];
+ __be16 port_role;
+ __be16 interval;
+ __be16 blocked;
+};
+
+struct br_mrp_sub_opt_hdr {
+ __u8 type;
+ __u8 manufacture_data[MRP_MANUFACTURE_DATA_LENGTH];
+};
+
+struct br_mrp_test_mgr_nack_hdr {
+ __be16 prio;
+ __u8 sa[ETH_ALEN];
+ __be16 other_prio;
+ __u8 other_sa[ETH_ALEN];
+};
+
+struct br_mrp_test_prop_hdr {
+ __be16 prio;
+ __u8 sa[ETH_ALEN];
+ __be16 other_prio;
+ __u8 other_sa[ETH_ALEN];
+};
+
+struct br_mrp_oui_hdr {
+ __u8 oui[MRP_OUI_LENGTH];
+};
+
+#endif
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index cd144e3099a3..eefcda8ca44e 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -29,6 +29,7 @@ enum {
NDA_LINK_NETNSID,
NDA_SRC_VNI,
NDA_PROTOCOL, /* Originator of entry */
+ NDA_NH_ID,
__NDA_MAX
};
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index b6f0bb1dc799..4b3395082d15 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -114,15 +114,19 @@ enum ip_conntrack_status {
IPS_OFFLOAD_BIT = 14,
IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT),
+ /* Conntrack has been offloaded to hardware. */
+ IPS_HW_OFFLOAD_BIT = 15,
+ IPS_HW_OFFLOAD = (1 << IPS_HW_OFFLOAD_BIT),
+
/* Be careful here, modifying these bits can make things messy,
* so don't let users modify them directly.
*/
IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED |
- IPS_OFFLOAD),
+ IPS_OFFLOAD | IPS_HW_OFFLOAD),
- __IPS_MAX_BIT = 15,
+ __IPS_MAX_BIT = 16,
};
/* Connection tracking event types */
diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h
index 4a95c0db14d4..a64586e77b24 100644
--- a/include/uapi/linux/netfilter/nf_nat.h
+++ b/include/uapi/linux/netfilter/nf_nat.h
@@ -11,6 +11,7 @@
#define NF_NAT_RANGE_PERSISTENT (1 << 3)
#define NF_NAT_RANGE_PROTO_RANDOM_FULLY (1 << 4)
#define NF_NAT_RANGE_PROTO_OFFSET (1 << 5)
+#define NF_NAT_RANGE_NETMAP (1 << 6)
#define NF_NAT_RANGE_PROTO_RANDOM_ALL \
(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
@@ -18,7 +19,8 @@
#define NF_NAT_RANGE_MASK \
(NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED | \
NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT | \
- NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET)
+ NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET | \
+ NF_NAT_RANGE_NETMAP)
struct nf_nat_ipv4_range {
unsigned int flags;
diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
index 1d41810d17e2..262881792671 100644
--- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h
@@ -55,6 +55,7 @@ enum ctattr_type {
CTA_LABELS,
CTA_LABELS_MASK,
CTA_SYNPROXY,
+ CTA_FILTER,
__CTA_MAX
};
#define CTA_MAX (__CTA_MAX - 1)
@@ -276,4 +277,12 @@ enum ctattr_expect_stats {
};
#define CTA_STATS_EXP_MAX (__CTA_STATS_EXP_MAX - 1)
+enum ctattr_filter {
+ CTA_FILTER_UNSPEC,
+ CTA_FILTER_ORIG_FLAGS,
+ CTA_FILTER_REPLY_FLAGS,
+ __CTA_FILTER_MAX
+};
+#define CTA_FILTER_MAX (__CTA_FILTER_MAX - 1)
+
#endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 0a4d73317759..eac8a6a648ea 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -249,4 +249,107 @@ struct nla_bitfield32 {
__u32 selector;
};
+/*
+ * policy descriptions - it's specific to each family how this is used
+ * Normally, it should be retrieved via a dump inside another attribute
+ * specifying where it applies.
+ */
+
+/**
+ * enum netlink_attribute_type - type of an attribute
+ * @NL_ATTR_TYPE_INVALID: unused
+ * @NL_ATTR_TYPE_FLAG: flag attribute (present/not present)
+ * @NL_ATTR_TYPE_U8: 8-bit unsigned attribute
+ * @NL_ATTR_TYPE_U16: 16-bit unsigned attribute
+ * @NL_ATTR_TYPE_U32: 32-bit unsigned attribute
+ * @NL_ATTR_TYPE_U64: 64-bit unsigned attribute
+ * @NL_ATTR_TYPE_S8: 8-bit signed attribute
+ * @NL_ATTR_TYPE_S16: 16-bit signed attribute
+ * @NL_ATTR_TYPE_S32: 32-bit signed attribute
+ * @NL_ATTR_TYPE_S64: 64-bit signed attribute
+ * @NL_ATTR_TYPE_BINARY: binary data, min/max length may be specified
+ * @NL_ATTR_TYPE_STRING: string, min/max length may be specified
+ * @NL_ATTR_TYPE_NUL_STRING: NUL-terminated string,
+ * min/max length may be specified
+ * @NL_ATTR_TYPE_NESTED: nested, i.e. the content of this attribute
+ * consists of sub-attributes. The nested policy and maxtype
+ * inside may be specified.
+ * @NL_ATTR_TYPE_NESTED_ARRAY: nested array, i.e. the content of this
+ * attribute contains sub-attributes whose type is irrelevant
+ * (just used to separate the array entries) and each such array
+ * entry has attributes again, the policy for those inner ones
+ * and the corresponding maxtype may be specified.
+ * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute
+ */
+enum netlink_attribute_type {
+ NL_ATTR_TYPE_INVALID,
+
+ NL_ATTR_TYPE_FLAG,
+
+ NL_ATTR_TYPE_U8,
+ NL_ATTR_TYPE_U16,
+ NL_ATTR_TYPE_U32,
+ NL_ATTR_TYPE_U64,
+
+ NL_ATTR_TYPE_S8,
+ NL_ATTR_TYPE_S16,
+ NL_ATTR_TYPE_S32,
+ NL_ATTR_TYPE_S64,
+
+ NL_ATTR_TYPE_BINARY,
+ NL_ATTR_TYPE_STRING,
+ NL_ATTR_TYPE_NUL_STRING,
+
+ NL_ATTR_TYPE_NESTED,
+ NL_ATTR_TYPE_NESTED_ARRAY,
+
+ NL_ATTR_TYPE_BITFIELD32,
+};
+
+/**
+ * enum netlink_policy_type_attr - policy type attributes
+ * @NL_POLICY_TYPE_ATTR_UNSPEC: unused
+ * @NL_POLICY_TYPE_ATTR_TYPE: type of the attribute,
+ * &enum netlink_attribute_type (U32)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_S: minimum value for signed
+ * integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_S: maximum value for signed
+ * integers (S64)
+ * @NL_POLICY_TYPE_ATTR_MIN_VALUE_U: minimum value for unsigned
+ * integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MAX_VALUE_U: maximum value for unsigned
+ * integers (U64)
+ * @NL_POLICY_TYPE_ATTR_MIN_LENGTH: minimum length for binary
+ * attributes, no minimum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_MAX_LENGTH: maximum length for binary
+ * attributes, no maximum if not given (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_IDX: sub policy for nested and
+ * nested array types (U32)
+ * @NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE: maximum sub policy
+ * attribute for nested and nested array types, this can
+ * in theory be < the size of the policy pointed to by
+ * the index, if limited inside the nesting (U32)
+ * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the
+ * bitfield32 type (U32)
+ * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment
+ */
+enum netlink_policy_type_attr {
+ NL_POLICY_TYPE_ATTR_UNSPEC,
+ NL_POLICY_TYPE_ATTR_TYPE,
+ NL_POLICY_TYPE_ATTR_MIN_VALUE_S,
+ NL_POLICY_TYPE_ATTR_MAX_VALUE_S,
+ NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
+ NL_POLICY_TYPE_ATTR_MAX_VALUE_U,
+ NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+ NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+ NL_POLICY_TYPE_ATTR_POLICY_IDX,
+ NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
+ NL_POLICY_TYPE_ATTR_BITFIELD32_MASK,
+ NL_POLICY_TYPE_ATTR_PAD,
+
+ /* keep last */
+ __NL_POLICY_TYPE_ATTR_MAX,
+ NL_POLICY_TYPE_ATTR_MAX = __NL_POLICY_TYPE_ATTR_MAX - 1
+};
+
#endif /* _UAPI__LINUX_NETLINK_H */
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index 7b61867e9848..2d4a1e784cf0 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -49,6 +49,9 @@ enum {
NHA_GROUPS, /* flag; only return nexthop groups in dump */
NHA_MASTER, /* u32; only return nexthops with given master dev */
+ NHA_FDB, /* flag; nexthop belongs to a bridge fdb */
+ /* if NHA_FDB is added, OIF, BLACKHOLE, ENCAP cannot be set */
+
__NHA_MAX,
};
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 2b691161830f..4e6339ab1fce 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -296,13 +296,14 @@
* to get a list of all present wiphys.
* @NL80211_CMD_SET_WIPHY: set wiphy parameters, needs %NL80211_ATTR_WIPHY or
* %NL80211_ATTR_IFINDEX; can be used to set %NL80211_ATTR_WIPHY_NAME,
- * %NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ (and the
- * attributes determining the channel width; this is used for setting
- * monitor mode channel), %NL80211_ATTR_WIPHY_RETRY_SHORT,
- * %NL80211_ATTR_WIPHY_RETRY_LONG, %NL80211_ATTR_WIPHY_FRAG_THRESHOLD,
- * and/or %NL80211_ATTR_WIPHY_RTS_THRESHOLD.
- * However, for setting the channel, see %NL80211_CMD_SET_CHANNEL
- * instead, the support here is for backward compatibility only.
+ * %NL80211_ATTR_WIPHY_TXQ_PARAMS, %NL80211_ATTR_WIPHY_FREQ,
+ * %NL80211_ATTR_WIPHY_FREQ_OFFSET (and the attributes determining the
+ * channel width; this is used for setting monitor mode channel),
+ * %NL80211_ATTR_WIPHY_RETRY_SHORT, %NL80211_ATTR_WIPHY_RETRY_LONG,
+ * %NL80211_ATTR_WIPHY_FRAG_THRESHOLD, and/or
+ * %NL80211_ATTR_WIPHY_RTS_THRESHOLD. However, for setting the channel,
+ * see %NL80211_CMD_SET_CHANNEL instead, the support here is for backward
+ * compatibility only.
* @NL80211_CMD_NEW_WIPHY: Newly created wiphy, response to get request
* or rename notification. Has attributes %NL80211_ATTR_WIPHY and
* %NL80211_ATTR_WIPHY_NAME.
@@ -351,7 +352,8 @@
* %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_INACTIVITY_TIMEOUT,
* %NL80211_ATTR_ACL_POLICY and %NL80211_ATTR_MAC_ADDRS.
* The channel to use can be set on the interface or be given using the
- * %NL80211_ATTR_WIPHY_FREQ and the attributes determining channel width.
+ * %NL80211_ATTR_WIPHY_FREQ and %NL80211_ATTR_WIPHY_FREQ_OFFSET, and the
+ * attributes determining channel width.
* @NL80211_CMD_NEW_BEACON: old alias for %NL80211_CMD_START_AP
* @NL80211_CMD_STOP_AP: Stop AP operation on the given interface
* @NL80211_CMD_DEL_BEACON: old alias for %NL80211_CMD_STOP_AP
@@ -536,11 +538,12 @@
* interface. %NL80211_ATTR_MAC is used to specify PeerSTAAddress (and
* BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify
* the SSID (mainly for association, but is included in authentication
- * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ is used
- * to specify the frequence of the channel in MHz. %NL80211_ATTR_AUTH_TYPE
- * is used to specify the authentication type. %NL80211_ATTR_IE is used to
- * define IEs (VendorSpecificInfo, but also including RSN IE and FT IEs)
- * to be added to the frame.
+ * request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ +
+ * %NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequence of the
+ * channel in MHz. %NL80211_ATTR_AUTH_TYPE is used to specify the
+ * authentication type. %NL80211_ATTR_IE is used to define IEs
+ * (VendorSpecificInfo, but also including RSN IE and FT IEs) to be added
+ * to the frame.
* When used as an event, this reports reception of an Authentication
* frame in station and IBSS modes when the local MLME processed the
* frame, i.e., it was for the local STA and was received in correct
@@ -595,8 +598,9 @@
* requests to connect to a specified network but without separating
* auth and assoc steps. For this, you need to specify the SSID in a
* %NL80211_ATTR_SSID attribute, and can optionally specify the association
- * IEs in %NL80211_ATTR_IE, %NL80211_ATTR_AUTH_TYPE, %NL80211_ATTR_USE_MFP,
- * %NL80211_ATTR_MAC, %NL80211_ATTR_WIPHY_FREQ, %NL80211_ATTR_CONTROL_PORT,
+ * IEs in %NL80211_ATTR_IE, %NL80211_ATTR_AUTH_TYPE,
+ * %NL80211_ATTR_USE_MFP, %NL80211_ATTR_MAC, %NL80211_ATTR_WIPHY_FREQ,
+ * %NL80211_ATTR_WIPHY_FREQ_OFFSET, %NL80211_ATTR_CONTROL_PORT,
* %NL80211_ATTR_CONTROL_PORT_ETHERTYPE,
* %NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT,
* %NL80211_ATTR_CONTROL_PORT_OVER_NL80211, %NL80211_ATTR_MAC_HINT, and
@@ -687,6 +691,10 @@
* four bytes for vendor frames including the OUI. The registration
* cannot be dropped, but is removed automatically when the netlink
* socket is closed. Multiple registrations can be made.
+ * The %NL80211_ATTR_RECEIVE_MULTICAST flag attribute can be given if
+ * %NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS is available, in which
+ * case the registration can also be modified to include/exclude the
+ * flag, rather than requiring unregistration to change it.
* @NL80211_CMD_REGISTER_ACTION: Alias for @NL80211_CMD_REGISTER_FRAME for
* backward compatibility
* @NL80211_CMD_FRAME: Management frame TX request and RX notification. This
@@ -786,7 +794,7 @@
* various triggers. These triggers can be configured through this
* command with the %NL80211_ATTR_WOWLAN_TRIGGERS attribute. For
* more background information, see
- * http://wireless.kernel.org/en/users/Documentation/WoWLAN.
+ * https://wireless.wiki.kernel.org/en/users/Documentation/WoWLAN.
* The @NL80211_CMD_SET_WOWLAN command can also be used as a notification
* from the driver reporting the wakeup reason. In this case, the
* @NL80211_ATTR_WOWLAN_TRIGGERS attribute will contain the reason
@@ -1151,6 +1159,17 @@
* @NL80211_CMD_SET_TID_CONFIG: Data frame TID specific configuration
* is passed using %NL80211_ATTR_TID_CONFIG attribute.
*
+ * @NL80211_CMD_UNPROT_BEACON: Unprotected or incorrectly protected Beacon
+ * frame. This event is used to indicate that a received Beacon frame was
+ * dropped because it did not include a valid MME MIC while beacon
+ * protection was enabled (BIGTK configured in station mode).
+ *
+ * @NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS: Report TX status of a control
+ * port frame transmitted with %NL80211_CMD_CONTROL_PORT_FRAME.
+ * %NL80211_ATTR_COOKIE identifies the TX command and %NL80211_ATTR_FRAME
+ * includes the contents of the frame. %NL80211_ATTR_ACK flag is included
+ * if the recipient acknowledged the frame.
+ *
* @NL80211_CMD_MAX: highest used command number
* @__NL80211_CMD_AFTER_LAST: internal use
*/
@@ -1377,6 +1396,10 @@ enum nl80211_commands {
NL80211_CMD_SET_TID_CONFIG,
+ NL80211_CMD_UNPROT_BEACON,
+
+ NL80211_CMD_CONTROL_PORT_FRAME_TX_STATUS,
+
/* add new commands above here */
/* used to define NL80211_CMD_MAX below */
@@ -1422,7 +1445,8 @@ enum nl80211_commands {
* of &enum nl80211_chan_width, describing the channel width. See the
* documentation of the enum for more information.
* @NL80211_ATTR_CENTER_FREQ1: Center frequency of the first part of the
- * channel, used for anything but 20 MHz bandwidth
+ * channel, used for anything but 20 MHz bandwidth. In S1G this is the
+ * operating channel center frequency.
* @NL80211_ATTR_CENTER_FREQ2: Center frequency of the second part of the
* channel, used only for 80+80 MHz bandwidth
* @NL80211_ATTR_WIPHY_CHANNEL_TYPE: included with NL80211_ATTR_WIPHY_FREQ
@@ -2469,6 +2493,17 @@ enum nl80211_commands {
* entry without having to force a disconnection after the PMK timeout. If
* no roaming occurs between the reauth threshold and PMK expiration,
* disassociation is still forced.
+ * @NL80211_ATTR_RECEIVE_MULTICAST: multicast flag for the
+ * %NL80211_CMD_REGISTER_FRAME command, see the description there.
+ * @NL80211_ATTR_WIPHY_FREQ_OFFSET: offset of the associated
+ * %NL80211_ATTR_WIPHY_FREQ in positive KHz. Only valid when supplied with
+ * an %NL80211_ATTR_WIPHY_FREQ_OFFSET.
+ * @NL80211_ATTR_CENTER_FREQ1_OFFSET: Center frequency offset in KHz for the
+ * first channel segment specified in %NL80211_ATTR_CENTER_FREQ1.
+ * @NL80211_ATTR_SCAN_FREQ_KHZ: nested attribute with KHz frequencies
+ *
+ * @NL80211_ATTR_HE_6GHZ_CAPABILITY: HE 6 GHz Band Capability element (from
+ * association request when used with NL80211_CMD_NEW_STATION).
*
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -2945,6 +2980,13 @@ enum nl80211_attrs {
NL80211_ATTR_PMK_LIFETIME,
NL80211_ATTR_PMK_REAUTH_THRESHOLD,
+ NL80211_ATTR_RECEIVE_MULTICAST,
+ NL80211_ATTR_WIPHY_FREQ_OFFSET,
+ NL80211_ATTR_CENTER_FREQ1_OFFSET,
+ NL80211_ATTR_SCAN_FREQ_KHZ,
+
+ NL80211_ATTR_HE_6GHZ_CAPABILITY,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
@@ -3523,6 +3565,8 @@ enum nl80211_mpath_info {
* defined in HE capabilities IE
* @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently
* defined
+ * @NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA: HE 6GHz band capabilities (__le16),
+ * given for all 6 GHz band channels
* @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use
*/
enum nl80211_band_iftype_attr {
@@ -3533,6 +3577,7 @@ enum nl80211_band_iftype_attr {
NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY,
NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET,
NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE,
+ NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA,
/* keep last */
__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST,
@@ -3666,6 +3711,7 @@ enum nl80211_wmm_rule {
* (see &enum nl80211_wmm_rule)
* @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel
* in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_OFFSET: frequency offset in KHz
* @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
* currently defined
* @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -3696,6 +3742,7 @@ enum nl80211_frequency_attr {
NL80211_FREQUENCY_ATTR_NO_10MHZ,
NL80211_FREQUENCY_ATTR_WMM,
NL80211_FREQUENCY_ATTR_NO_HE,
+ NL80211_FREQUENCY_ATTR_OFFSET,
/* keep last */
__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -4466,6 +4513,7 @@ enum nl80211_bss_scan_width {
* @NL80211_BSS_CHAIN_SIGNAL: per-chain signal strength of last BSS update.
* Contains a nested array of signal strength attributes (u8, dBm),
* using the nesting index as the antenna number.
+ * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz
* @__NL80211_BSS_AFTER_LAST: internal
* @NL80211_BSS_MAX: highest BSS attribute
*/
@@ -4490,6 +4538,7 @@ enum nl80211_bss {
NL80211_BSS_PARENT_TSF,
NL80211_BSS_PARENT_BSSID,
NL80211_BSS_CHAIN_SIGNAL,
+ NL80211_BSS_FREQUENCY_OFFSET,
/* keep last */
__NL80211_BSS_AFTER_LAST,
@@ -4800,6 +4849,17 @@ enum nl80211_tid_config {
NL80211_TID_CONFIG_DISABLE,
};
+/* enum nl80211_tx_rate_setting - TX rate configuration type
+ * @NL80211_TX_RATE_AUTOMATIC: automatically determine TX rate
+ * @NL80211_TX_RATE_LIMITED: limit the TX rate by the TX rate parameter
+ * @NL80211_TX_RATE_FIXED: fix TX rate to the TX rate parameter
+ */
+enum nl80211_tx_rate_setting {
+ NL80211_TX_RATE_AUTOMATIC,
+ NL80211_TX_RATE_LIMITED,
+ NL80211_TX_RATE_FIXED,
+};
+
/* enum nl80211_tid_config_attr - TID specific configuration.
* @NL80211_TID_CONFIG_ATTR_PAD: pad attribute for 64-bit values
* @NL80211_TID_CONFIG_ATTR_VIF_SUPP: a bitmap (u64) of attributes supported
@@ -4807,12 +4867,10 @@ enum nl80211_tid_config {
* (%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE).
* @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but
* per peer instead.
- * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if no peer
- * is selected, if set indicates that the new configuration overrides
- * all previous peer configurations, otherwise previous peer specific
- * configurations should be left untouched. If peer is selected then
- * it will reset particular TID configuration of that peer and it will
- * not accept other TID config attributes along with peer.
+ * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if set indicates
+ * that the new configuration overrides all previous peer
+ * configurations, otherwise previous peer specific configurations
+ * should be left untouched.
* @NL80211_TID_CONFIG_ATTR_TIDS: a bitmask value of TIDs (bit 0 to 7)
* Its type is u16.
* @NL80211_TID_CONFIG_ATTR_NOACK: Configure ack policy for the TID.
@@ -4828,12 +4886,23 @@ enum nl80211_tid_config {
* &NL80211_CMD_SET_TID_CONFIG. Its type is u8, min value is 1 and
* the max value is advertised by the driver in this attribute on
* output in wiphy capabilities.
- * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable aggregation for the TIDs
- * specified in %NL80211_TID_CONFIG_ATTR_TIDS. Its type is u8, using
- * the values from &nl80211_tid_config.
+ * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable MPDU aggregation
+ * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS.
+ * Its type is u8, using the values from &nl80211_tid_config.
* @NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL: Enable/Disable RTS_CTS for the TIDs
* specified in %NL80211_TID_CONFIG_ATTR_TIDS. It is u8 type, using
* the values from &nl80211_tid_config.
+ * @NL80211_TID_CONFIG_ATTR_AMSDU_CTRL: Enable/Disable MSDU aggregation
+ * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS.
+ * Its type is u8, using the values from &nl80211_tid_config.
+ * @NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE: This attribute will be useful
+ * to notfiy the driver that what type of txrate should be used
+ * for the TIDs specified in %NL80211_TID_CONFIG_ATTR_TIDS. using
+ * the values form &nl80211_tx_rate_setting.
+ * @NL80211_TID_CONFIG_ATTR_TX_RATE: Data frame TX rate mask should be applied
+ * with the parameters passed through %NL80211_ATTR_TX_RATES.
+ * configuration is applied to the data frame for the tid to that connected
+ * station.
*/
enum nl80211_tid_config_attr {
__NL80211_TID_CONFIG_ATTR_INVALID,
@@ -4847,6 +4916,9 @@ enum nl80211_tid_config_attr {
NL80211_TID_CONFIG_ATTR_RETRY_LONG,
NL80211_TID_CONFIG_ATTR_AMPDU_CTRL,
NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL,
+ NL80211_TID_CONFIG_ATTR_AMSDU_CTRL,
+ NL80211_TID_CONFIG_ATTR_TX_RATE_TYPE,
+ NL80211_TID_CONFIG_ATTR_TX_RATE,
/* keep last */
__NL80211_TID_CONFIG_ATTR_AFTER_LAST,
@@ -5324,6 +5396,8 @@ enum plink_actions {
#define NL80211_KCK_LEN 16
#define NL80211_KEK_LEN 16
+#define NL80211_KCK_EXT_LEN 24
+#define NL80211_KEK_EXT_LEN 32
#define NL80211_REPLAY_CTR_LEN 8
/**
@@ -5332,6 +5406,7 @@ enum plink_actions {
* @NL80211_REKEY_DATA_KEK: key encryption key (binary)
* @NL80211_REKEY_DATA_KCK: key confirmation key (binary)
* @NL80211_REKEY_DATA_REPLAY_CTR: replay counter (binary)
+ * @NL80211_REKEY_DATA_AKM: AKM data (OUI, suite type)
* @NUM_NL80211_REKEY_DATA: number of rekey attributes (internal)
* @MAX_NL80211_REKEY_DATA: highest rekey attribute (internal)
*/
@@ -5340,6 +5415,7 @@ enum nl80211_rekey_data {
NL80211_REKEY_DATA_KEK,
NL80211_REKEY_DATA_KCK,
NL80211_REKEY_DATA_REPLAY_CTR,
+ NL80211_REKEY_DATA_AKM,
/* keep last */
NUM_NL80211_REKEY_DATA,
@@ -5674,6 +5750,8 @@ enum nl80211_feature_flags {
*
* @NL80211_EXT_FEATURE_BEACON_PROTECTION: The driver supports Beacon protection
* and can receive key configuration for BIGTK using key indexes 6 and 7.
+ * @NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT: The driver supports Beacon
+ * protection as a client only and cannot transmit protected beacons.
*
* @NL80211_EXT_FEATURE_CONTROL_PORT_NO_PREAUTH: The driver can disable the
* forwarding of preauth frames over the control port. They are then
@@ -5684,6 +5762,17 @@ enum nl80211_feature_flags {
* @NL80211_EXT_FEATURE_DEL_IBSS_STA: The driver supports removing stations
* in IBSS mode, essentially by dropping their state.
*
+ * @NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS: management frame registrations
+ * are possible for multicast frames and those will be reported properly.
+ *
+ * @NL80211_EXT_FEATURE_SCAN_FREQ_KHZ: This driver supports receiving and
+ * reporting scan request with %NL80211_ATTR_SCAN_FREQ_KHZ. In order to
+ * report %NL80211_ATTR_SCAN_FREQ_KHZ, %NL80211_SCAN_FLAG_FREQ_KHZ must be
+ * included in the scan request.
+ *
+ * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS: The driver
+ * can report tx status for control port over nl80211 tx operations.
+ *
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
*/
@@ -5735,6 +5824,10 @@ enum nl80211_ext_feature_index {
NL80211_EXT_FEATURE_CONTROL_PORT_NO_PREAUTH,
NL80211_EXT_FEATURE_PROTECTED_TWT,
NL80211_EXT_FEATURE_DEL_IBSS_STA,
+ NL80211_EXT_FEATURE_MULTICAST_REGISTRATIONS,
+ NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT,
+ NL80211_EXT_FEATURE_SCAN_FREQ_KHZ,
+ NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
@@ -5846,6 +5939,9 @@ enum nl80211_timeout_reason {
* @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to
* only have supported rates and no additional capabilities (unless
* added by userspace explicitly.)
+ * @NL80211_SCAN_FLAG_FREQ_KHZ: report scan results with
+ * %NL80211_ATTR_SCAN_FREQ_KHZ. This also means
+ * %NL80211_ATTR_SCAN_FREQUENCIES will not be included.
*/
enum nl80211_scan_flags {
NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0,
@@ -5861,6 +5957,7 @@ enum nl80211_scan_flags {
NL80211_SCAN_FLAG_HIGH_ACCURACY = 1<<10,
NL80211_SCAN_FLAG_RANDOM_SN = 1<<11,
NL80211_SCAN_FLAG_MIN_PREQ_CONTENT = 1<<12,
+ NL80211_SCAN_FLAG_FREQ_KHZ = 1<<13,
};
/**
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 9f06d29cab70..7576209d96f9 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -134,6 +134,7 @@ enum tca_id {
TCA_ID_CTINFO,
TCA_ID_MPLS,
TCA_ID_CT,
+ TCA_ID_GATE,
/* other actions go here */
__TCA_ID_MAX = 255
};
@@ -575,6 +576,8 @@ enum {
TCA_FLOWER_KEY_CT_LABELS, /* u128 */
TCA_FLOWER_KEY_CT_LABELS_MASK, /* u128 */
+ TCA_FLOWER_KEY_MPLS_OPTS,
+
__TCA_FLOWER_MAX,
};
@@ -640,6 +643,27 @@ enum {
(__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1)
enum {
+ TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPTS_LSE,
+ __TCA_FLOWER_KEY_MPLS_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPTS_MAX (__TCA_FLOWER_KEY_MPLS_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_UNSPEC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_BOS,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_TC,
+ TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+ __TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX,
+};
+
+#define TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX \
+ (__TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX - 1)
+
+enum {
TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
};
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 0c02737c8f47..a95f3ae7ab37 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -913,6 +913,10 @@ enum {
TCA_FQ_TIMER_SLACK, /* timer slack */
+ TCA_FQ_HORIZON, /* time horizon in us */
+
+ TCA_FQ_HORIZON_DROP, /* drop packets beyond horizon, or cap their EDT */
+
__TCA_FQ_MAX
};
@@ -932,6 +936,8 @@ struct tc_fq_qd_stats {
__u32 throttled_flows;
__u32 unthrottle_latency_ns;
__u64 ce_mark; /* packets above ce_threshold */
+ __u64 horizon_drops;
+ __u64 horizon_caps;
};
/* Heavy-Hitter Filter */
diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
index ce1116cff53d..aea26ab1431c 100644
--- a/include/uapi/linux/psample.h
+++ b/include/uapi/linux/psample.h
@@ -11,6 +11,7 @@ enum {
PSAMPLE_ATTR_GROUP_SEQ,
PSAMPLE_ATTR_SAMPLE_RATE,
PSAMPLE_ATTR_DATA,
+ PSAMPLE_ATTR_TUNNEL,
/* commands attributes */
PSAMPLE_ATTR_GROUP_REFCOUNT,
@@ -25,6 +26,27 @@ enum psample_command {
PSAMPLE_CMD_DEL_GROUP,
};
+enum psample_tunnel_key_attr {
+ PSAMPLE_TUNNEL_KEY_ATTR_ID, /* be64 Tunnel ID */
+ PSAMPLE_TUNNEL_KEY_ATTR_IPV4_SRC, /* be32 src IP address. */
+ PSAMPLE_TUNNEL_KEY_ATTR_IPV4_DST, /* be32 dst IP address. */
+ PSAMPLE_TUNNEL_KEY_ATTR_TOS, /* u8 Tunnel IP ToS. */
+ PSAMPLE_TUNNEL_KEY_ATTR_TTL, /* u8 Tunnel IP TTL. */
+ PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */
+ PSAMPLE_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */
+ PSAMPLE_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */
+ PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, /* Array of Geneve options. */
+ PSAMPLE_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */
+ PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */
+ PSAMPLE_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested VXLAN opts* */
+ PSAMPLE_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */
+ PSAMPLE_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */
+ PSAMPLE_TUNNEL_KEY_ATTR_PAD,
+ PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* struct erspan_metadata */
+ PSAMPLE_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE, /* No argument. IPV4_INFO_BRIDGE mode.*/
+ __PSAMPLE_TUNNEL_KEY_ATTR_MAX
+};
+
/* Can be overridden at runtime by module option */
#define PSAMPLE_ATTR_MAX (__PSAMPLE_ATTR_MAX - 1)
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index 0549a5c622bf..91b4c63d5cbf 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -83,6 +83,8 @@ struct sev_user_data_status {
__u32 guest_count; /* Out */
} __packed;
+#define SEV_STATUS_FLAGS_CONFIG_ES 0x0100
+
/**
* struct sev_user_data_pek_csr - PEK_CSR command parameters
*
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index 9dc9d0079e98..ff070aa64278 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -89,7 +89,9 @@ struct ptp_clock_caps {
int n_pins; /* Number of input/output pins. */
/* Whether the clock supports precise system-device cross timestamps */
int cross_timestamping;
- int rsv[13]; /* Reserved for future use. */
+ /* Whether the clock supports adjust phase */
+ int adjust_phase;
+ int rsv[12]; /* Reserved for future use. */
};
struct ptp_extts_request {
diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h
index 83bba58d47f4..fa9aff91cbf2 100644
--- a/include/uapi/linux/rtc.h
+++ b/include/uapi/linux/rtc.h
@@ -99,6 +99,7 @@ struct rtc_pll_info {
#define RTC_VL_BACKUP_LOW _BITUL(1) /* Backup voltage is low */
#define RTC_VL_BACKUP_EMPTY _BITUL(2) /* Backup empty or not present */
#define RTC_VL_ACCURACY_LOW _BITUL(3) /* Voltage is low, RTC accuracy is reduced */
+#define RTC_VL_BACKUP_SWITCH _BITUL(4) /* Backup switchover happened */
#define RTC_VL_READ _IOR('p', 0x13, unsigned int) /* Voltage low detection */
#define RTC_VL_CLR _IO('p', 0x14) /* Clear voltage low information */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 4a8c5b745157..073e71ef6bdd 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -609,11 +609,17 @@ enum {
TCA_HW_OFFLOAD,
TCA_INGRESS_BLOCK,
TCA_EGRESS_BLOCK,
+ TCA_DUMP_FLAGS,
__TCA_MAX
};
#define TCA_MAX (__TCA_MAX - 1)
+#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic
+ * data necessary to identify the objects
+ * (handle, cookie, etc.) and stats.
+ */
+
#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index ad80a5c885d5..82cc58fe9368 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -123,7 +123,10 @@ struct statx {
__u32 stx_dev_major; /* ID of device containing file [uncond] */
__u32 stx_dev_minor;
/* 0x90 */
- __u64 __spare2[14]; /* Spare space for future expansion */
+ __u64 stx_mnt_id;
+ __u64 __spare2;
+ /* 0xa0 */
+ __u64 __spare3[12]; /* Spare space for future expansion */
/* 0x100 */
};
@@ -148,9 +151,19 @@ struct statx {
#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
-#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
+
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future. To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL 0x00000fffU
+#endif
+
/*
* Attributes to be found in stx_attributes and masked in stx_attributes_mask.
*
@@ -168,7 +181,9 @@ struct statx {
#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */
#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
+#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */
#endif /* _UAPI_LINUX_STAT_H */
diff --git a/include/uapi/linux/tc_act/tc_gate.h b/include/uapi/linux/tc_act/tc_gate.h
new file mode 100644
index 000000000000..f214b3a6d44f
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_gate.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2020 NXP */
+
+#ifndef __LINUX_TC_GATE_H
+#define __LINUX_TC_GATE_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_gate {
+ tc_gen;
+};
+
+enum {
+ TCA_GATE_ENTRY_UNSPEC,
+ TCA_GATE_ENTRY_INDEX,
+ TCA_GATE_ENTRY_GATE,
+ TCA_GATE_ENTRY_INTERVAL,
+ TCA_GATE_ENTRY_IPV,
+ TCA_GATE_ENTRY_MAX_OCTETS,
+ __TCA_GATE_ENTRY_MAX,
+};
+#define TCA_GATE_ENTRY_MAX (__TCA_GATE_ENTRY_MAX - 1)
+
+enum {
+ TCA_GATE_ONE_ENTRY_UNSPEC,
+ TCA_GATE_ONE_ENTRY,
+ __TCA_GATE_ONE_ENTRY_MAX,
+};
+#define TCA_GATE_ONE_ENTRY_MAX (__TCA_GATE_ONE_ENTRY_MAX - 1)
+
+enum {
+ TCA_GATE_UNSPEC,
+ TCA_GATE_TM,
+ TCA_GATE_PARMS,
+ TCA_GATE_PAD,
+ TCA_GATE_PRIORITY,
+ TCA_GATE_ENTRY_LIST,
+ TCA_GATE_BASE_TIME,
+ TCA_GATE_CYCLE_TIME,
+ TCA_GATE_CYCLE_TIME_EXT,
+ TCA_GATE_FLAGS,
+ TCA_GATE_CLOCKID,
+ __TCA_GATE_MAX,
+};
+#define TCA_GATE_MAX (__TCA_GATE_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h
index 6596f3a09e54..b619f37ee03e 100644
--- a/include/uapi/linux/tee.h
+++ b/include/uapi/linux/tee.h
@@ -173,6 +173,15 @@ struct tee_ioctl_buf_data {
#define TEE_IOCTL_LOGIN_APPLICATION 4
#define TEE_IOCTL_LOGIN_USER_APPLICATION 5
#define TEE_IOCTL_LOGIN_GROUP_APPLICATION 6
+/*
+ * Disallow user-space to use GP implementation specific login
+ * method range (0x80000000 - 0xBFFFFFFF). This range is rather
+ * being reserved for REE kernel clients or TEE implementation.
+ */
+#define TEE_IOCTL_LOGIN_REE_KERNEL_MIN 0x80000000
+#define TEE_IOCTL_LOGIN_REE_KERNEL_MAX 0xBFFFFFFF
+/* Private login method for REE kernel clients */
+#define TEE_IOCTL_LOGIN_REE_KERNEL 0x80000000
/**
* struct tee_ioctl_param - parameter
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 1a58d7cc4ccc..62271418c1be 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -473,6 +473,10 @@ enum v4l2_mpeg_video_h264_level {
V4L2_MPEG_VIDEO_H264_LEVEL_4_2 = 13,
V4L2_MPEG_VIDEO_H264_LEVEL_5_0 = 14,
V4L2_MPEG_VIDEO_H264_LEVEL_5_1 = 15,
+ V4L2_MPEG_VIDEO_H264_LEVEL_5_2 = 16,
+ V4L2_MPEG_VIDEO_H264_LEVEL_6_0 = 17,
+ V4L2_MPEG_VIDEO_H264_LEVEL_6_1 = 18,
+ V4L2_MPEG_VIDEO_H264_LEVEL_6_2 = 19,
};
#define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA (V4L2_CID_MPEG_BASE+360)
#define V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA (V4L2_CID_MPEG_BASE+361)
@@ -501,6 +505,7 @@ enum v4l2_mpeg_video_h264_profile {
V4L2_MPEG_VIDEO_H264_PROFILE_SCALABLE_HIGH_INTRA = 14,
V4L2_MPEG_VIDEO_H264_PROFILE_STEREO_HIGH = 15,
V4L2_MPEG_VIDEO_H264_PROFILE_MULTIVIEW_HIGH = 16,
+ V4L2_MPEG_VIDEO_H264_PROFILE_CONSTRAINED_HIGH = 17,
};
#define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_HEIGHT (V4L2_CID_MPEG_BASE+364)
#define V4L2_CID_MPEG_VIDEO_H264_VUI_EXT_SAR_WIDTH (V4L2_CID_MPEG_BASE+365)
@@ -918,6 +923,13 @@ enum v4l2_auto_focus_range {
#define V4L2_CID_PAN_SPEED (V4L2_CID_CAMERA_CLASS_BASE+32)
#define V4L2_CID_TILT_SPEED (V4L2_CID_CAMERA_CLASS_BASE+33)
+#define V4L2_CID_CAMERA_ORIENTATION (V4L2_CID_CAMERA_CLASS_BASE+34)
+#define V4L2_CAMERA_ORIENTATION_FRONT 0
+#define V4L2_CAMERA_ORIENTATION_BACK 1
+#define V4L2_CAMERA_ORIENTATION_EXTERNAL 2
+
+#define V4L2_CID_CAMERA_SENSOR_ROTATION (V4L2_CID_CAMERA_CLASS_BASE+35)
+
/* FM Modulator class control IDs */
#define V4L2_CID_FM_TX_CLASS_BASE (V4L2_CTRL_CLASS_FM_TX | 0x900)
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 03970ce30741..5d2a1dab7911 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -155,9 +155,25 @@ struct v4l2_subdev_selection {
__u32 reserved[8];
};
+/**
+ * struct v4l2_subdev_capability - subdev capabilities
+ * @version: the driver versioning number
+ * @capabilities: the subdev capabilities, see V4L2_SUBDEV_CAP_*
+ * @reserved: for future use, set to zero for now
+ */
+struct v4l2_subdev_capability {
+ __u32 version;
+ __u32 capabilities;
+ __u32 reserved[14];
+};
+
+/* The v4l2 sub-device video device node is registered in read-only mode. */
+#define V4L2_SUBDEV_CAP_RO_SUBDEV BIT(0)
+
/* Backwards compatibility define --- to be removed */
#define v4l2_subdev_edid v4l2_edid
+#define VIDIOC_SUBDEV_QUERYCAP _IOR('V', 0, struct v4l2_subdev_capability)
#define VIDIOC_SUBDEV_G_FMT _IOWR('V', 4, struct v4l2_subdev_format)
#define VIDIOC_SUBDEV_S_FMT _IOWR('V', 5, struct v4l2_subdev_format)
#define VIDIOC_SUBDEV_G_FRAME_INTERVAL _IOWR('V', 21, struct v4l2_subdev_frame_interval)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 015516bcfaa3..eca6692667a3 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -305,6 +305,7 @@ struct vfio_region_info_cap_type {
#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff)
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_TYPE_CCW (2)
+#define VFIO_REGION_TYPE_MIGRATION (3)
/* sub-types for VFIO_REGION_TYPE_PCI_* */
@@ -378,6 +379,235 @@ struct vfio_region_gfx_edid {
/* sub-types for VFIO_REGION_TYPE_CCW */
#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1)
+#define VFIO_REGION_SUBTYPE_CCW_SCHIB (2)
+#define VFIO_REGION_SUBTYPE_CCW_CRW (3)
+
+/* sub-types for VFIO_REGION_TYPE_MIGRATION */
+#define VFIO_REGION_SUBTYPE_MIGRATION (1)
+
+/*
+ * The structure vfio_device_migration_info is placed at the 0th offset of
+ * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related
+ * migration information. Field accesses from this structure are only supported
+ * at their native width and alignment. Otherwise, the result is undefined and
+ * vendor drivers should return an error.
+ *
+ * device_state: (read/write)
+ * - The user application writes to this field to inform the vendor driver
+ * about the device state to be transitioned to.
+ * - The vendor driver should take the necessary actions to change the
+ * device state. After successful transition to a given state, the
+ * vendor driver should return success on write(device_state, state)
+ * system call. If the device state transition fails, the vendor driver
+ * should return an appropriate -errno for the fault condition.
+ * - On the user application side, if the device state transition fails,
+ * that is, if write(device_state, state) returns an error, read
+ * device_state again to determine the current state of the device from
+ * the vendor driver.
+ * - The vendor driver should return previous state of the device unless
+ * the vendor driver has encountered an internal error, in which case
+ * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR.
+ * - The user application must use the device reset ioctl to recover the
+ * device from VFIO_DEVICE_STATE_ERROR state. If the device is
+ * indicated to be in a valid device state by reading device_state, the
+ * user application may attempt to transition the device to any valid
+ * state reachable from the current state or terminate itself.
+ *
+ * device_state consists of 3 bits:
+ * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear,
+ * it indicates the _STOP state. When the device state is changed to
+ * _STOP, driver should stop the device before write() returns.
+ * - If bit 1 is set, it indicates the _SAVING state, which means that the
+ * driver should start gathering device state information that will be
+ * provided to the VFIO user application to save the device's state.
+ * - If bit 2 is set, it indicates the _RESUMING state, which means that
+ * the driver should prepare to resume the device. Data provided through
+ * the migration region should be used to resume the device.
+ * Bits 3 - 31 are reserved for future use. To preserve them, the user
+ * application should perform a read-modify-write operation on this
+ * field when modifying the specified bits.
+ *
+ * +------- _RESUMING
+ * |+------ _SAVING
+ * ||+----- _RUNNING
+ * |||
+ * 000b => Device Stopped, not saving or resuming
+ * 001b => Device running, which is the default state
+ * 010b => Stop the device & save the device state, stop-and-copy state
+ * 011b => Device running and save the device state, pre-copy state
+ * 100b => Device stopped and the device state is resuming
+ * 101b => Invalid state
+ * 110b => Error state
+ * 111b => Invalid state
+ *
+ * State transitions:
+ *
+ * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP
+ * (100b) (001b) (011b) (010b) (000b)
+ * 0. Running or default state
+ * |
+ *
+ * 1. Normal Shutdown (optional)
+ * |------------------------------------->|
+ *
+ * 2. Save the state or suspend
+ * |------------------------->|---------->|
+ *
+ * 3. Save the state during live migration
+ * |----------->|------------>|---------->|
+ *
+ * 4. Resuming
+ * |<---------|
+ *
+ * 5. Resumed
+ * |--------->|
+ *
+ * 0. Default state of VFIO device is _RUNNNG when the user application starts.
+ * 1. During normal shutdown of the user application, the user application may
+ * optionally change the VFIO device state from _RUNNING to _STOP. This
+ * transition is optional. The vendor driver must support this transition but
+ * must not require it.
+ * 2. When the user application saves state or suspends the application, the
+ * device state transitions from _RUNNING to stop-and-copy and then to _STOP.
+ * On state transition from _RUNNING to stop-and-copy, driver must stop the
+ * device, save the device state and send it to the application through the
+ * migration region. The sequence to be followed for such transition is given
+ * below.
+ * 3. In live migration of user application, the state transitions from _RUNNING
+ * to pre-copy, to stop-and-copy, and to _STOP.
+ * On state transition from _RUNNING to pre-copy, the driver should start
+ * gathering the device state while the application is still running and send
+ * the device state data to application through the migration region.
+ * On state transition from pre-copy to stop-and-copy, the driver must stop
+ * the device, save the device state and send it to the user application
+ * through the migration region.
+ * Vendor drivers must support the pre-copy state even for implementations
+ * where no data is provided to the user before the stop-and-copy state. The
+ * user must not be required to consume all migration data before the device
+ * transitions to a new state, including the stop-and-copy state.
+ * The sequence to be followed for above two transitions is given below.
+ * 4. To start the resuming phase, the device state should be transitioned from
+ * the _RUNNING to the _RESUMING state.
+ * In the _RESUMING state, the driver should use the device state data
+ * received through the migration region to resume the device.
+ * 5. After providing saved device data to the driver, the application should
+ * change the state from _RESUMING to _RUNNING.
+ *
+ * reserved:
+ * Reads on this field return zero and writes are ignored.
+ *
+ * pending_bytes: (read only)
+ * The number of pending bytes still to be migrated from the vendor driver.
+ *
+ * data_offset: (read only)
+ * The user application should read data_offset field from the migration
+ * region. The user application should read the device data from this
+ * offset within the migration region during the _SAVING state or write
+ * the device data during the _RESUMING state. See below for details of
+ * sequence to be followed.
+ *
+ * data_size: (read/write)
+ * The user application should read data_size to get the size in bytes of
+ * the data copied in the migration region during the _SAVING state and
+ * write the size in bytes of the data copied in the migration region
+ * during the _RESUMING state.
+ *
+ * The format of the migration region is as follows:
+ * ------------------------------------------------------------------
+ * |vfio_device_migration_info| data section |
+ * | | /////////////////////////////// |
+ * ------------------------------------------------------------------
+ * ^ ^
+ * offset 0-trapped part data_offset
+ *
+ * The structure vfio_device_migration_info is always followed by the data
+ * section in the region, so data_offset will always be nonzero. The offset
+ * from where the data is copied is decided by the kernel driver. The data
+ * section can be trapped, mmapped, or partitioned, depending on how the kernel
+ * driver defines the data section. The data section partition can be defined
+ * as mapped by the sparse mmap capability. If mmapped, data_offset must be
+ * page aligned, whereas initial section which contains the
+ * vfio_device_migration_info structure, might not end at the offset, which is
+ * page aligned. The user is not required to access through mmap regardless
+ * of the capabilities of the region mmap.
+ * The vendor driver should determine whether and how to partition the data
+ * section. The vendor driver should return data_offset accordingly.
+ *
+ * The sequence to be followed while in pre-copy state and stop-and-copy state
+ * is as follows:
+ * a. Read pending_bytes, indicating the start of a new iteration to get device
+ * data. Repeated read on pending_bytes at this stage should have no side
+ * effects.
+ * If pending_bytes == 0, the user application should not iterate to get data
+ * for that device.
+ * If pending_bytes > 0, perform the following steps.
+ * b. Read data_offset, indicating that the vendor driver should make data
+ * available through the data section. The vendor driver should return this
+ * read operation only after data is available from (region + data_offset)
+ * to (region + data_offset + data_size).
+ * c. Read data_size, which is the amount of data in bytes available through
+ * the migration region.
+ * Read on data_offset and data_size should return the offset and size of
+ * the current buffer if the user application reads data_offset and
+ * data_size more than once here.
+ * d. Read data_size bytes of data from (region + data_offset) from the
+ * migration region.
+ * e. Process the data.
+ * f. Read pending_bytes, which indicates that the data from the previous
+ * iteration has been read. If pending_bytes > 0, go to step b.
+ *
+ * The user application can transition from the _SAVING|_RUNNING
+ * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the
+ * number of pending bytes. The user application should iterate in _SAVING
+ * (stop-and-copy) until pending_bytes is 0.
+ *
+ * The sequence to be followed while _RESUMING device state is as follows:
+ * While data for this device is available, repeat the following steps:
+ * a. Read data_offset from where the user application should write data.
+ * b. Write migration data starting at the migration region + data_offset for
+ * the length determined by data_size from the migration source.
+ * c. Write data_size, which indicates to the vendor driver that data is
+ * written in the migration region. Vendor driver must return this write
+ * operations on consuming data. Vendor driver should apply the
+ * user-provided migration region data to the device resume state.
+ *
+ * If an error occurs during the above sequences, the vendor driver can return
+ * an error code for next read() or write() operation, which will terminate the
+ * loop. The user application should then take the next necessary action, for
+ * example, failing migration or terminating the user application.
+ *
+ * For the user application, data is opaque. The user application should write
+ * data in the same order as the data is received and the data should be of
+ * same transaction size at the source.
+ */
+
+struct vfio_device_migration_info {
+ __u32 device_state; /* VFIO device state */
+#define VFIO_DEVICE_STATE_STOP (0)
+#define VFIO_DEVICE_STATE_RUNNING (1 << 0)
+#define VFIO_DEVICE_STATE_SAVING (1 << 1)
+#define VFIO_DEVICE_STATE_RESUMING (1 << 2)
+#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \
+ VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+#define VFIO_DEVICE_STATE_VALID(state) \
+ (state & VFIO_DEVICE_STATE_RESUMING ? \
+ (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1)
+
+#define VFIO_DEVICE_STATE_IS_ERROR(state) \
+ ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING))
+
+#define VFIO_DEVICE_STATE_SET_ERROR(state) \
+ ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+ __u32 reserved;
+ __u64 pending_bytes;
+ __u64 data_offset;
+ __u64 data_size;
+};
/*
* The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
@@ -577,6 +807,7 @@ enum {
enum {
VFIO_CCW_IO_IRQ_INDEX,
+ VFIO_CCW_CRW_IRQ_INDEX,
VFIO_CCW_NUM_IRQS
};
@@ -785,6 +1016,29 @@ struct vfio_iommu_type1_info_cap_iova_range {
struct vfio_iova_range iova_ranges[];
};
+/*
+ * The migration capability allows to report supported features for migration.
+ *
+ * The structures below define version 1 of this capability.
+ *
+ * The existence of this capability indicates that IOMMU kernel driver supports
+ * dirty page logging.
+ *
+ * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty
+ * page logging.
+ * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap
+ * size in bytes that can be used by user applications when getting the dirty
+ * bitmap.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 1
+
+struct vfio_iommu_type1_info_cap_migration {
+ struct vfio_info_cap_header header;
+ __u32 flags;
+ __u64 pgsize_bitmap;
+ __u64 max_dirty_bitmap_size; /* in bytes */
+};
+
#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
/**
@@ -805,6 +1059,12 @@ struct vfio_iommu_type1_dma_map {
#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
+struct vfio_bitmap {
+ __u64 pgsize; /* page size for bitmap in bytes */
+ __u64 size; /* in bytes */
+ __u64 __user *data; /* one bit per page */
+};
+
/**
* VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
* struct vfio_dma_unmap)
@@ -814,12 +1074,23 @@ struct vfio_iommu_type1_dma_map {
* field. No guarantee is made to the user that arbitrary unmaps of iova
* or size different from those used in the original mapping call will
* succeed.
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap
+ * before unmapping IO virtual addresses. When this flag is set, the user must
+ * provide a struct vfio_bitmap in data[]. User must provide zero-allocated
+ * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field.
+ * A bit in the bitmap represents one page, of user provided page size in
+ * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set
+ * indicates that the page at that offset from iova is dirty. A Bitmap of the
+ * pages in the range of unmapped size is returned in the user-provided
+ * vfio_bitmap.data.
*/
struct vfio_iommu_type1_dma_unmap {
__u32 argsz;
__u32 flags;
+#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
__u64 iova; /* IO virtual address */
__u64 size; /* Size of mapping (bytes) */
+ __u8 data[];
};
#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
@@ -831,6 +1102,57 @@ struct vfio_iommu_type1_dma_unmap {
#define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15)
#define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16)
+/**
+ * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
+ * struct vfio_iommu_type1_dirty_bitmap)
+ * IOCTL is used for dirty pages logging.
+ * Caller should set flag depending on which operation to perform, details as
+ * below:
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs
+ * the IOMMU driver to log pages that are dirtied or potentially dirtied by
+ * the device; designed to be used when a migration is in progress. Dirty pages
+ * are logged until logging is disabled by user application by calling the IOCTL
+ * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs
+ * the IOMMU driver to stop logging dirtied pages.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set
+ * returns the dirty pages bitmap for IOMMU container for a given IOVA range.
+ * The user must specify the IOVA range and the pgsize through the structure
+ * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface
+ * supports getting a bitmap of the smallest supported pgsize only and can be
+ * modified in future to get a bitmap of any specified supported pgsize. The
+ * user must provide a zeroed memory area for the bitmap memory and specify its
+ * size in bitmap.size. One bit is used to represent one page consecutively
+ * starting from iova offset. The user should provide page size in bitmap.pgsize
+ * field. A bit set in the bitmap indicates that the page at that offset from
+ * iova is dirty. The caller must set argsz to a value including the size of
+ * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the
+ * actual bitmap. If dirty pages logging is not enabled, an error will be
+ * returned.
+ *
+ * Only one of the flags _START, _STOP and _GET may be specified at a time.
+ *
+ */
+struct vfio_iommu_type1_dirty_bitmap {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2)
+ __u8 data[];
+};
+
+struct vfio_iommu_type1_dirty_bitmap_get {
+ __u64 iova; /* IO virtual address */
+ __u64 size; /* Size of iova range */
+ struct vfio_bitmap bitmap;
+};
+
+#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
+
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*
diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h
index cbecbf0cd54f..aa04f3aa6db0 100644
--- a/include/uapi/linux/vfio_ccw.h
+++ b/include/uapi/linux/vfio_ccw.h
@@ -34,4 +34,23 @@ struct ccw_cmd_region {
__u32 ret_code;
} __packed;
+/*
+ * Used for processing commands that read the subchannel-information block
+ * Reading this region triggers a stsch() to hardware
+ * Note: this is controlled by a capability
+ */
+struct ccw_schib_region {
+#define SCHIB_AREA_SIZE 52
+ __u8 schib_area[SCHIB_AREA_SIZE];
+} __packed;
+
+/*
+ * Used for returning a Channel Report Word to userspace.
+ * Note: this is controlled by a capability
+ */
+struct ccw_crw_region {
+ __u32 crw;
+ __u32 pad;
+} __packed;
+
#endif
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 9fe72e4b1373..0c2349612e77 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -15,6 +15,8 @@
#include <linux/types.h>
#include <linux/ioctl.h>
+#define VHOST_FILE_UNBIND -1
+
/* ioctls */
#define VHOST_VIRTIO 0xAF
@@ -140,4 +142,6 @@
/* Get the max ring size. */
#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16)
+/* Set event fd for config interrupt*/
+#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
#endif
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 9817b7e2c968..c3a1cf1c507f 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -487,6 +487,8 @@ struct v4l2_capability {
#define V4L2_CAP_TOUCH 0x10000000 /* Is a touch device */
+#define V4L2_CAP_IO_MC 0x20000000 /* Is input/output controlled by the media controller */
+
#define V4L2_CAP_DEVICE_CAPS 0x80000000 /* sets device capabilities field */
/*
@@ -782,7 +784,8 @@ struct v4l2_fmtdesc {
__u32 flags;
__u8 description[32]; /* Description string */
__u32 pixelformat; /* Format fourcc */
- __u32 reserved[4];
+ __u32 mbus_code; /* Media bus code */
+ __u32 reserved[3];
};
#define V4L2_FMT_FLAG_COMPRESSED 0x0001
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index ecc27a17401a..b052355ac7a3 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -44,6 +44,7 @@
#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */
#define VIRTIO_ID_CRYPTO 20 /* virtio crypto */
#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM 24 /* virtio mem */
#define VIRTIO_ID_FS 26 /* virtio filesystem */
#define VIRTIO_ID_PMEM 27 /* virtio pmem */
#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h
new file mode 100644
index 000000000000..a9ffe041843c
--- /dev/null
+++ b/include/uapi/linux/virtio_mem.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/*
+ * Virtio Mem Device
+ *
+ * Copyright Red Hat, Inc. 2020
+ *
+ * Authors:
+ * David Hildenbrand <david@redhat.com>
+ *
+ * This header is BSD licensed so anyone can use the definitions
+ * to implement compatible drivers/servers:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+ * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_MEM_H
+#define _LINUX_VIRTIO_MEM_H
+
+#include <linux/types.h>
+#include <linux/virtio_types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+
+/*
+ * Each virtio-mem device manages a dedicated region in physical address
+ * space. Each device can belong to a single NUMA node, multiple devices
+ * for a single NUMA node are possible. A virtio-mem device is like a
+ * "resizable DIMM" consisting of small memory blocks that can be plugged
+ * or unplugged. The device driver is responsible for (un)plugging memory
+ * blocks on demand.
+ *
+ * Virtio-mem devices can only operate on their assigned memory region in
+ * order to (un)plug memory. A device cannot (un)plug memory belonging to
+ * other devices.
+ *
+ * The "region_size" corresponds to the maximum amount of memory that can
+ * be provided by a device. The "size" corresponds to the amount of memory
+ * that is currently plugged. "requested_size" corresponds to a request
+ * from the device to the device driver to (un)plug blocks. The
+ * device driver should try to (un)plug blocks in order to reach the
+ * "requested_size". It is impossible to plug more memory than requested.
+ *
+ * The "usable_region_size" represents the memory region that can actually
+ * be used to (un)plug memory. It is always at least as big as the
+ * "requested_size" and will grow dynamically. It will only shrink when
+ * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG).
+ *
+ * There are no guarantees what will happen if unplugged memory is
+ * read/written. Such memory should, in general, not be touched. E.g.,
+ * even writing might succeed, but the values will simply be discarded at
+ * random points in time.
+ *
+ * It can happen that the device cannot process a request, because it is
+ * busy. The device driver has to retry later.
+ *
+ * Usually, during system resets all memory will get unplugged, so the
+ * device driver can start with a clean state. However, in specific
+ * scenarios (if the device is busy) it can happen that the device still
+ * has memory plugged. The device driver can request to unplug all memory
+ * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the
+ * device is busy.
+ */
+
+/* --- virtio-mem: feature bits --- */
+
+/* node_id is an ACPI PXM and is valid */
+#define VIRTIO_MEM_F_ACPI_PXM 0
+
+
+/* --- virtio-mem: guest -> host requests --- */
+
+/* request to plug memory blocks */
+#define VIRTIO_MEM_REQ_PLUG 0
+/* request to unplug memory blocks */
+#define VIRTIO_MEM_REQ_UNPLUG 1
+/* request to unplug all blocks and shrink the usable size */
+#define VIRTIO_MEM_REQ_UNPLUG_ALL 2
+/* request information about the plugged state of memory blocks */
+#define VIRTIO_MEM_REQ_STATE 3
+
+struct virtio_mem_req_plug {
+ __virtio64 addr;
+ __virtio16 nb_blocks;
+ __virtio16 padding[3];
+};
+
+struct virtio_mem_req_unplug {
+ __virtio64 addr;
+ __virtio16 nb_blocks;
+ __virtio16 padding[3];
+};
+
+struct virtio_mem_req_state {
+ __virtio64 addr;
+ __virtio16 nb_blocks;
+ __virtio16 padding[3];
+};
+
+struct virtio_mem_req {
+ __virtio16 type;
+ __virtio16 padding[3];
+
+ union {
+ struct virtio_mem_req_plug plug;
+ struct virtio_mem_req_unplug unplug;
+ struct virtio_mem_req_state state;
+ } u;
+};
+
+
+/* --- virtio-mem: host -> guest response --- */
+
+/*
+ * Request processed successfully, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_UNPLUG_ALL
+ * - VIRTIO_MEM_REQ_STATE
+ */
+#define VIRTIO_MEM_RESP_ACK 0
+/*
+ * Request denied - e.g. trying to plug more than requested, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ */
+#define VIRTIO_MEM_RESP_NACK 1
+/*
+ * Request cannot be processed right now, try again later, applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_UNPLUG_ALL
+ */
+#define VIRTIO_MEM_RESP_BUSY 2
+/*
+ * Error in request (e.g. addresses/alignment), applicable for
+ * - VIRTIO_MEM_REQ_PLUG
+ * - VIRTIO_MEM_REQ_UNPLUG
+ * - VIRTIO_MEM_REQ_STATE
+ */
+#define VIRTIO_MEM_RESP_ERROR 3
+
+
+/* State of memory blocks is "plugged" */
+#define VIRTIO_MEM_STATE_PLUGGED 0
+/* State of memory blocks is "unplugged" */
+#define VIRTIO_MEM_STATE_UNPLUGGED 1
+/* State of memory blocks is "mixed" */
+#define VIRTIO_MEM_STATE_MIXED 2
+
+struct virtio_mem_resp_state {
+ __virtio16 state;
+};
+
+struct virtio_mem_resp {
+ __virtio16 type;
+ __virtio16 padding[3];
+
+ union {
+ struct virtio_mem_resp_state state;
+ } u;
+};
+
+/* --- virtio-mem: configuration --- */
+
+struct virtio_mem_config {
+ /* Block size and alignment. Cannot change. */
+ __u64 block_size;
+ /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */
+ __u16 node_id;
+ __u8 padding[6];
+ /* Start address of the memory region. Cannot change. */
+ __u64 addr;
+ /* Region size (maximum). Cannot change. */
+ __u64 region_size;
+ /*
+ * Currently usable region size. Can grow up to region_size. Can
+ * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config
+ * update will be sent).
+ */
+ __u64 usable_region_size;
+ /*
+ * Currently used size. Changes due to plug/unplug requests, but no
+ * config updates will be sent.
+ */
+ __u64 plugged_size;
+ /* Requested size. New plug requests cannot exceed it. Can change. */
+ __u64 requested_size;
+};
+
+#endif /* _LINUX_VIRTIO_MEM_H */
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 559f42e73315..476d3e5c0fe7 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -86,6 +86,13 @@
* at the end of the used ring. Guest should ignore the used->flags field. */
#define VIRTIO_RING_F_EVENT_IDX 29
+/* Alignment requirements for vring elements.
+ * When using pre-virtio 1.0 layout, these fall out naturally.
+ */
+#define VRING_AVAIL_ALIGN_SIZE 2
+#define VRING_USED_ALIGN_SIZE 4
+#define VRING_DESC_ALIGN_SIZE 16
+
/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */
struct vring_desc {
/* Address (guest-physical). */
@@ -112,28 +119,47 @@ struct vring_used_elem {
__virtio32 len;
};
+typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+ vring_used_elem_t;
+
struct vring_used {
__virtio16 flags;
__virtio16 idx;
- struct vring_used_elem ring[];
+ vring_used_elem_t ring[];
};
+/*
+ * The ring element addresses are passed between components with different
+ * alignments assumptions. Thus, we might need to decrease the compiler-selected
+ * alignment, and so must use a typedef to make sure the aligned attribute
+ * actually takes hold:
+ *
+ * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes
+ *
+ * When used on a struct, or struct member, the aligned attribute can only
+ * increase the alignment; in order to decrease it, the packed attribute must
+ * be specified as well. When used as part of a typedef, the aligned attribute
+ * can both increase and decrease alignment, and specifying the packed
+ * attribute generates a warning.
+ */
+typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE)))
+ vring_desc_t;
+typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE)))
+ vring_avail_t;
+typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+ vring_used_t;
+
struct vring {
unsigned int num;
- struct vring_desc *desc;
+ vring_desc_t *desc;
- struct vring_avail *avail;
+ vring_avail_t *avail;
- struct vring_used *used;
+ vring_used_t *used;
};
-/* Alignment requirements for vring elements.
- * When using pre-virtio 1.0 layout, these fall out naturally.
- */
-#define VRING_AVAIL_ALIGN_SIZE 2
-#define VRING_USED_ALIGN_SIZE 4
-#define VRING_DESC_ALIGN_SIZE 16
+#ifndef VIRTIO_RING_NO_LEGACY
/* The standard layout for the ring is a continuous chunk of memory which looks
* like this. We assume num is a power of 2.
@@ -181,6 +207,8 @@ static inline unsigned vring_size(unsigned int num, unsigned long align)
+ sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
}
+#endif /* VIRTIO_RING_NO_LEGACY */
+
/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
/* Assuming a given event_idx value from the other side, if
* we have just incremented index from old to new_idx,
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
new file mode 100644
index 000000000000..c3d8320b5d3a
--- /dev/null
+++ b/include/uapi/linux/watch_queue.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_WATCH_QUEUE_H
+#define _UAPI_LINUX_WATCH_QUEUE_H
+
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/ioctl.h>
+
+#define O_NOTIFICATION_PIPE O_EXCL /* Parameter to pipe2() selecting notification pipe */
+
+#define IOC_WATCH_QUEUE_SET_SIZE _IO('W', 0x60) /* Set the size in pages */
+#define IOC_WATCH_QUEUE_SET_FILTER _IO('W', 0x61) /* Set the filter */
+
+enum watch_notification_type {
+ WATCH_TYPE_META = 0, /* Special record */
+ WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */
+ WATCH_TYPE__NR = 2
+};
+
+enum watch_meta_notification_subtype {
+ WATCH_META_REMOVAL_NOTIFICATION = 0, /* Watched object was removed */
+ WATCH_META_LOSS_NOTIFICATION = 1, /* Data loss occurred */
+};
+
+/*
+ * Notification record header. This is aligned to 64-bits so that subclasses
+ * can contain __u64 fields.
+ */
+struct watch_notification {
+ __u32 type:24; /* enum watch_notification_type */
+ __u32 subtype:8; /* Type-specific subtype (filterable) */
+ __u32 info;
+#define WATCH_INFO_LENGTH 0x0000007f /* Length of record */
+#define WATCH_INFO_LENGTH__SHIFT 0
+#define WATCH_INFO_ID 0x0000ff00 /* ID of watchpoint */
+#define WATCH_INFO_ID__SHIFT 8
+#define WATCH_INFO_TYPE_INFO 0xffff0000 /* Type-specific info */
+#define WATCH_INFO_TYPE_INFO__SHIFT 16
+#define WATCH_INFO_FLAG_0 0x00010000 /* Type-specific info, flag bit 0 */
+#define WATCH_INFO_FLAG_1 0x00020000 /* ... */
+#define WATCH_INFO_FLAG_2 0x00040000
+#define WATCH_INFO_FLAG_3 0x00080000
+#define WATCH_INFO_FLAG_4 0x00100000
+#define WATCH_INFO_FLAG_5 0x00200000
+#define WATCH_INFO_FLAG_6 0x00400000
+#define WATCH_INFO_FLAG_7 0x00800000
+};
+
+/*
+ * Notification filtering rules (IOC_WATCH_QUEUE_SET_FILTER).
+ */
+struct watch_notification_type_filter {
+ __u32 type; /* Type to apply filter to */
+ __u32 info_filter; /* Filter on watch_notification::info */
+ __u32 info_mask; /* Mask of relevant bits in info_filter */
+ __u32 subtype_filter[8]; /* Bitmask of subtypes to filter on */
+};
+
+struct watch_notification_filter {
+ __u32 nr_filters; /* Number of filters */
+ __u32 __reserved; /* Must be 0 */
+ struct watch_notification_type_filter filters[];
+};
+
+
+/*
+ * Extended watch removal notification. This is used optionally if the type
+ * wants to indicate an identifier for the object being watched, if there is
+ * such. This can be distinguished by the length.
+ *
+ * type -> WATCH_TYPE_META
+ * subtype -> WATCH_META_REMOVAL_NOTIFICATION
+ */
+struct watch_notification_removal {
+ struct watch_notification watch;
+ __u64 id; /* Type-dependent identifier */
+};
+
+/*
+ * Type of key/keyring change notification.
+ */
+enum key_notification_subtype {
+ NOTIFY_KEY_INSTANTIATED = 0, /* Key was instantiated (aux is error code) */
+ NOTIFY_KEY_UPDATED = 1, /* Key was updated */
+ NOTIFY_KEY_LINKED = 2, /* Key (aux) was added to watched keyring */
+ NOTIFY_KEY_UNLINKED = 3, /* Key (aux) was removed from watched keyring */
+ NOTIFY_KEY_CLEARED = 4, /* Keyring was cleared */
+ NOTIFY_KEY_REVOKED = 5, /* Key was revoked */
+ NOTIFY_KEY_INVALIDATED = 6, /* Key was invalidated */
+ NOTIFY_KEY_SETATTR = 7, /* Key's attributes got changed */
+};
+
+/*
+ * Key/keyring notification record.
+ * - watch.type = WATCH_TYPE_KEY_NOTIFY
+ * - watch.subtype = enum key_notification_type
+ */
+struct key_notification {
+ struct watch_notification watch;
+ __u32 key_id; /* The key/keyring affected */
+ __u32 aux; /* Per-type auxiliary data */
+};
+
+#endif /* _UAPI_LINUX_WATCH_QUEUE_H */
diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h
index a2c006a364e0..24f3371ad826 100644
--- a/include/uapi/linux/wireless.h
+++ b/include/uapi/linux/wireless.h
@@ -74,7 +74,11 @@
#include <linux/socket.h> /* for "struct sockaddr" et al */
#include <linux/if.h> /* for IFNAMSIZ and co... */
-#include <stddef.h> /* for offsetof */
+#ifdef __KERNEL__
+# include <linux/stddef.h> /* for offsetof */
+#else
+# include <stddef.h> /* for offsetof */
+#endif
/***************************** VERSION *****************************/
/*
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5f3b9fec7b5f..ff7cfdc6cb44 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -304,7 +304,7 @@ enum xfrm_attr_type_t {
XFRMA_PROTO, /* __u8 */
XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */
XFRMA_PAD,
- XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */
+ XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */
XFRMA_SET_MARK, /* __u32 */
XFRMA_SET_MARK_MASK, /* __u32 */
XFRMA_IF_ID, /* __u32 */