summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/bpf-cgroup.h8
-rw-r--r--include/linux/bpf.h351
-rw-r--r--include/linux/bpf_local_storage.h4
-rw-r--r--include/linux/bpf_types.h1
-rw-r--r--include/linux/bpf_verifier.h23
-rw-r--r--include/linux/btf.h23
-rw-r--r--include/linux/btf_ids.h3
-rw-r--r--include/linux/can/dev.h10
-rw-r--r--include/linux/can/led.h51
-rw-r--r--include/linux/can/rx-offload.h4
-rw-r--r--include/linux/ethtool.h4
-rw-r--r--include/linux/fortify-string.h16
-rw-r--r--include/linux/ftrace.h6
-rw-r--r--include/linux/icmpv6.h11
-rw-r--r--include/linux/ieee802154.h81
-rw-r--r--include/linux/ipv6.h6
-rw-r--r--include/linux/kallsyms.h7
-rw-r--r--include/linux/list.h36
-rw-r--r--include/linux/mdio.h70
-rw-r--r--include/linux/mfd/idt8a340_reg.h12
-rw-r--r--include/linux/mlx5/accel.h156
-rw-r--r--include/linux/mlx5/driver.h17
-rw-r--r--include/linux/mlx5/fs.h12
-rw-r--r--include/linux/mlx5/mlx5_ifc.h23
-rw-r--r--include/linux/mlx5/mlx5_ifc_fpga.h211
-rw-r--r--include/linux/mlx5/port.h2
-rw-r--r--include/linux/netdevice.h378
-rw-r--r--include/linux/phy.h8
-rw-r--r--include/linux/phylink.h6
-rw-r--r--include/linux/ptp_clock_kernel.h42
-rw-r--r--include/linux/qed/qed_fcoe_if.h4
-rw-r--r--include/linux/qed/qed_iscsi_if.h4
-rw-r--r--include/linux/qed/qed_nvmetcp_if.h2
-rw-r--r--include/linux/qed/qed_nvmetcp_ip_services_if.h29
-rw-r--r--include/linux/rtnetlink.h1
-rw-r--r--include/linux/seq_file.h4
-rw-r--r--include/linux/skbuff.h419
-rw-r--r--include/linux/soc/mediatek/mtk_wed.h131
-rw-r--r--include/linux/socket.h6
-rw-r--r--include/linux/string.h4
-rw-r--r--include/linux/sysctl.h9
-rw-r--r--include/linux/usb/rndis_host.h1
-rw-r--r--include/linux/usb/usbnet.h1
-rw-r--r--include/net/act_api.h3
-rw-r--r--include/net/bluetooth/hci.h10
-rw-r--r--include/net/bluetooth/hci_core.h8
-rw-r--r--include/net/cfg80211.h16
-rw-r--r--include/net/cfg802154.h8
-rw-r--r--include/net/devlink.h48
-rw-r--r--include/net/dsa.h25
-rw-r--r--include/net/flow_dissector.h9
-rw-r--r--include/net/if_inet6.h8
-rw-r--r--include/net/inet6_hashtables.h28
-rw-r--r--include/net/inet_connection_sock.h5
-rw-r--r--include/net/inet_hashtables.h145
-rw-r--r--include/net/inet_sock.h5
-rw-r--r--include/net/ip.h2
-rw-r--r--include/net/ip_fib.h4
-rw-r--r--include/net/ipv6.h44
-rw-r--r--include/net/mac80211.h126
-rw-r--r--include/net/mac802154.h19
-rw-r--r--include/net/mptcp.h11
-rw-r--r--include/net/net_debug.h157
-rw-r--r--include/net/netfilter/nf_conntrack.h23
-rw-r--r--include/net/netfilter/nf_conntrack_core.h2
-rw-r--r--include/net/netfilter/nf_conntrack_count.h1
-rw-r--r--include/net/netfilter/nf_conntrack_ecache.h53
-rw-r--r--include/net/netfilter/nf_conntrack_extend.h31
-rw-r--r--include/net/netfilter/nf_conntrack_labels.h10
-rw-r--r--include/net/netfilter/nf_conntrack_timeout.h8
-rw-r--r--include/net/netfilter/nf_reject.h21
-rw-r--r--include/net/netns/conntrack.h8
-rw-r--r--include/net/page_pool.h21
-rw-r--r--include/net/ping.h4
-rw-r--r--include/net/pkt_cls.h6
-rw-r--r--include/net/route.h36
-rw-r--r--include/net/rtnetlink.h16
-rw-r--r--include/net/sctp/sctp.h2
-rw-r--r--include/net/sock.h64
-rw-r--r--include/net/strparser.h4
-rw-r--r--include/net/tc_act/tc_gact.h15
-rw-r--r--include/net/tc_act/tc_skbedit.h13
-rw-r--r--include/net/tcp.h45
-rw-r--r--include/net/tls.h16
-rw-r--r--include/net/udp.h8
-rw-r--r--include/net/xfrm.h20
-rw-r--r--include/rdma/ib_verbs.h8
-rw-r--r--include/soc/mscc/ocelot.h42
-rw-r--r--include/soc/mscc/ocelot_vcap.h2
-rw-r--r--include/trace/events/mptcp.h6
-rw-r--r--include/trace/events/rxrpc.h263
-rw-r--r--include/trace/events/skb.h21
-rw-r--r--include/trace/events/tcp.h47
-rw-r--r--include/uapi/asm-generic/socket.h2
-rw-r--r--include/uapi/linux/atm_zatm.h47
-rw-r--r--include/uapi/linux/bpf.h125
-rw-r--r--include/uapi/linux/btf.h4
-rw-r--r--include/uapi/linux/can/isotp.h25
-rw-r--r--include/uapi/linux/devlink.h23
-rw-r--r--include/uapi/linux/ethtool.h1
-rw-r--r--include/uapi/linux/ethtool_netlink.h1
-rw-r--r--include/uapi/linux/if_link.h7
-rw-r--r--include/uapi/linux/ipv6.h1
-rw-r--r--include/uapi/linux/mdio.h75
-rw-r--r--include/uapi/linux/mptcp.h8
-rw-r--r--include/uapi/linux/neighbour.h2
-rw-r--r--include/uapi/linux/netlink.h1
-rw-r--r--include/uapi/linux/nl80211.h2
-rw-r--r--include/uapi/linux/pkt_cls.h2
-rw-r--r--include/uapi/linux/tc_act/tc_skbedit.h2
-rw-r--r--include/uapi/linux/tipc_config.h28
-rw-r--r--include/uapi/linux/tls.h2
112 files changed, 2358 insertions, 1694 deletions
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 88a51b242adc..669d96d074ad 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -225,24 +225,20 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \
({ \
- u32 __unused_flags; \
int __ret = 0; \
if (cgroup_bpf_enabled(atype)) \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \
- NULL, \
- &__unused_flags); \
+ NULL, NULL); \
__ret; \
})
#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \
({ \
- u32 __unused_flags; \
int __ret = 0; \
if (cgroup_bpf_enabled(atype)) { \
lock_sock(sk); \
__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \
- t_ctx, \
- &__unused_flags); \
+ t_ctx, NULL); \
release_sock(sk); \
} \
__ret; \
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bdb5298735ce..a7080c86fa76 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <linux/percpu-refcount.h>
#include <linux/bpfptr.h>
+#include <linux/btf.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -88,6 +89,7 @@ struct bpf_map_ops {
int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
int (*map_pop_elem)(struct bpf_map *map, void *value);
int (*map_peek_elem)(struct bpf_map *map, void *value);
+ void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu);
/* funcs called by prog_array and perf_event_array map */
void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -147,14 +149,48 @@ struct bpf_map_ops {
bpf_callback_t callback_fn,
void *callback_ctx, u64 flags);
- /* BTF name and id of struct allocated by map_alloc */
- const char * const map_btf_name;
+ /* BTF id of struct allocated by map_alloc */
int *map_btf_id;
/* bpf_iter info used to open a seq_file */
const struct bpf_iter_seq_info *iter_seq_info;
};
+enum {
+ /* Support at most 8 pointers in a BPF map value */
+ BPF_MAP_VALUE_OFF_MAX = 8,
+ BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX +
+ 1 + /* for bpf_spin_lock */
+ 1, /* for bpf_timer */
+};
+
+enum bpf_kptr_type {
+ BPF_KPTR_UNREF,
+ BPF_KPTR_REF,
+};
+
+struct bpf_map_value_off_desc {
+ u32 offset;
+ enum bpf_kptr_type type;
+ struct {
+ struct btf *btf;
+ struct module *module;
+ btf_dtor_kfunc_t dtor;
+ u32 btf_id;
+ } kptr;
+};
+
+struct bpf_map_value_off {
+ u32 nr_off;
+ struct bpf_map_value_off_desc off[];
+};
+
+struct bpf_map_off_arr {
+ u32 cnt;
+ u32 field_off[BPF_MAP_OFF_ARR_MAX];
+ u8 field_sz[BPF_MAP_OFF_ARR_MAX];
+};
+
struct bpf_map {
/* The first two cachelines with read-mostly members of which some
* are also accessed in fast-path (e.g. ops, max_entries).
@@ -171,6 +207,7 @@ struct bpf_map {
u64 map_extra; /* any per-map-type extra fields */
u32 map_flags;
int spin_lock_off; /* >=0 valid offset, <0 error */
+ struct bpf_map_value_off *kptr_off_tab;
int timer_off; /* >=0 valid offset, <0 error */
u32 id;
int numa_node;
@@ -182,10 +219,7 @@ struct bpf_map {
struct mem_cgroup *memcg;
#endif
char name[BPF_OBJ_NAME_LEN];
- bool bypass_spec_v1;
- bool frozen; /* write-once; write-protected by freeze_mutex */
- /* 14 bytes hole */
-
+ struct bpf_map_off_arr *off_arr;
/* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting.
*/
@@ -205,6 +239,8 @@ struct bpf_map {
bool jited;
bool xdp_has_frags;
} owner;
+ bool bypass_spec_v1;
+ bool frozen; /* write-once; write-protected by freeze_mutex */
};
static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -217,43 +253,44 @@ static inline bool map_value_has_timer(const struct bpf_map *map)
return map->timer_off >= 0;
}
+static inline bool map_value_has_kptrs(const struct bpf_map *map)
+{
+ return !IS_ERR_OR_NULL(map->kptr_off_tab);
+}
+
static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
{
if (unlikely(map_value_has_spin_lock(map)))
memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock));
if (unlikely(map_value_has_timer(map)))
memset(dst + map->timer_off, 0, sizeof(struct bpf_timer));
+ if (unlikely(map_value_has_kptrs(map))) {
+ struct bpf_map_value_off *tab = map->kptr_off_tab;
+ int i;
+
+ for (i = 0; i < tab->nr_off; i++)
+ *(u64 *)(dst + tab->off[i].offset) = 0;
+ }
}
/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */
static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
{
- u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0;
+ u32 curr_off = 0;
+ int i;
- if (unlikely(map_value_has_spin_lock(map))) {
- s_off = map->spin_lock_off;
- s_sz = sizeof(struct bpf_spin_lock);
- }
- if (unlikely(map_value_has_timer(map))) {
- t_off = map->timer_off;
- t_sz = sizeof(struct bpf_timer);
+ if (likely(!map->off_arr)) {
+ memcpy(dst, src, map->value_size);
+ return;
}
- if (unlikely(s_sz || t_sz)) {
- if (s_off < t_off || !s_sz) {
- swap(s_off, t_off);
- swap(s_sz, t_sz);
- }
- memcpy(dst, src, t_off);
- memcpy(dst + t_off + t_sz,
- src + t_off + t_sz,
- s_off - t_off - t_sz);
- memcpy(dst + s_off + s_sz,
- src + s_off + s_sz,
- map->value_size - s_off - s_sz);
- } else {
- memcpy(dst, src, map->value_size);
+ for (i = 0; i < map->off_arr->cnt; i++) {
+ u32 next_off = map->off_arr->field_off[i];
+
+ memcpy(dst + curr_off, src + curr_off, next_off - curr_off);
+ curr_off += map->off_arr->field_sz[i];
}
+ memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off);
}
void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
bool lock_src);
@@ -342,9 +379,31 @@ enum bpf_type_flag {
*/
MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS),
- __BPF_TYPE_LAST_FLAG = MEM_PERCPU,
+ /* Indicates that the argument will be released. */
+ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS),
+
+ /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark
+ * unreferenced and referenced kptr loaded from map value using a load
+ * instruction, so that they can only be dereferenced but not escape the
+ * BPF program into the kernel (i.e. cannot be passed as arguments to
+ * kfunc or bpf helpers).
+ */
+ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS),
+
+ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS),
+
+ /* DYNPTR points to memory local to the bpf program. */
+ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS),
+
+ /* DYNPTR points to a ringbuf record. */
+ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS),
+
+ __BPF_TYPE_FLAG_MAX,
+ __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
+#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
+
/* Max number of base types. */
#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS)
@@ -361,16 +420,11 @@ enum bpf_arg_type {
ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */
ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
- ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */
- /* the following constraints used to prototype bpf_memcmp() and other
- * functions that access data on eBPF program stack
+ /* Used to prototype bpf_memcmp() and other functions that access data
+ * on eBPF program stack
*/
ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */
- ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized,
- * helper function must fill all bytes or clear
- * them in error case.
- */
ARG_CONST_SIZE, /* number of bytes accessed from memory */
ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */
@@ -391,6 +445,8 @@ enum bpf_arg_type {
ARG_PTR_TO_STACK, /* pointer to stack */
ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */
ARG_PTR_TO_TIMER, /* pointer to bpf_timer */
+ ARG_PTR_TO_KPTR, /* pointer to referenced kptr */
+ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
__BPF_ARG_TYPE_MAX,
/* Extended arg_types. */
@@ -400,6 +456,11 @@ enum bpf_arg_type {
ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
+ ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
+ /* pointer to memory does not need to be initialized, helper function must fill
+ * all bytes or clear them in error case.
+ */
+ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM,
/* This must be the last entry. Its purpose is to ensure the enum is
* wide enough to hold the higher bits reserved for bpf_type_flag.
@@ -427,6 +488,7 @@ enum bpf_return_type {
RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
+ RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
/* This must be the last entry. Its purpose is to ensure the enum is
@@ -672,15 +734,17 @@ struct btf_func_model {
#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4)
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
- * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2
+ * bytes on x86.
*/
-#define BPF_MAX_TRAMP_PROGS 38
+#define BPF_MAX_TRAMP_LINKS 38
-struct bpf_tramp_progs {
- struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS];
- int nr_progs;
+struct bpf_tramp_links {
+ struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
+ int nr_links;
};
+struct bpf_tramp_run_ctx;
+
/* Different use cases for BPF trampoline:
* 1. replace nop at the function entry (kprobe equivalent)
* flags = BPF_TRAMP_F_RESTORE_REGS
@@ -704,13 +768,14 @@ struct bpf_tramp_progs {
struct bpf_tramp_image;
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
- struct bpf_tramp_progs *tprogs,
+ struct bpf_tramp_links *tlinks,
void *orig_call);
/* these two functions are called from generated trampoline */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog);
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+ struct bpf_tramp_run_ctx *run_ctx);
void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
@@ -803,9 +868,10 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
{
return bpf_func(ctx, insnsi);
}
+
#ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -856,12 +922,12 @@ int bpf_jit_charge_modmem(u32 size);
void bpf_jit_uncharge_modmem(u32 size);
bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
#else
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr)
{
return -ENOTSUPP;
}
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
struct bpf_trampoline *tr)
{
return -ENOTSUPP;
@@ -960,7 +1026,6 @@ struct bpf_prog_aux {
bool tail_call_reachable;
bool xdp_has_frags;
bool use_bpf_prog_pack;
- struct hlist_node tramp_hlist;
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
/* function name for valid attach_btf_id */
@@ -1047,6 +1112,19 @@ struct bpf_link_ops {
struct bpf_link_info *info);
};
+struct bpf_tramp_link {
+ struct bpf_link link;
+ struct hlist_node tramp_hlist;
+ u64 cookie;
+};
+
+struct bpf_tracing_link {
+ struct bpf_tramp_link link;
+ enum bpf_attach_type attach_type;
+ struct bpf_trampoline *trampoline;
+ struct bpf_prog *tgt_prog;
+};
+
struct bpf_link_primer {
struct bpf_link *link;
struct file *file;
@@ -1084,8 +1162,8 @@ bool bpf_struct_ops_get(const void *kdata);
void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
-int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs,
- struct bpf_prog *prog,
+int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
+ struct bpf_tramp_link *link,
const struct btf_func_model *model,
void *image, void *image_end);
static inline bool bpf_try_module_get(const void *data, struct module *owner)
@@ -1221,7 +1299,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
/* an array of programs to be executed under rcu_lock.
*
* Typical usage:
- * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run);
+ * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run);
*
* the structure returned by bpf_prog_array_alloc() should be populated
* with program pointers and the last pointer must be NULL.
@@ -1290,6 +1368,12 @@ struct bpf_trace_run_ctx {
u64 bpf_cookie;
};
+struct bpf_tramp_run_ctx {
+ struct bpf_run_ctx run_ctx;
+ u64 bpf_cookie;
+ struct bpf_run_ctx *saved_run_ctx;
+};
+
static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
{
struct bpf_run_ctx *old_ctx = NULL;
@@ -1315,83 +1399,22 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
-static __always_inline int
-BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
- const void *ctx, bpf_prog_run_fn run_prog,
- int retval, u32 *ret_flags)
-{
- const struct bpf_prog_array_item *item;
- const struct bpf_prog *prog;
- const struct bpf_prog_array *array;
- struct bpf_run_ctx *old_run_ctx;
- struct bpf_cg_run_ctx run_ctx;
- u32 func_ret;
-
- run_ctx.retval = retval;
- migrate_disable();
- rcu_read_lock();
- array = rcu_dereference(array_rcu);
- item = &array->items[0];
- old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
- while ((prog = READ_ONCE(item->prog))) {
- run_ctx.prog_item = item;
- func_ret = run_prog(prog, ctx);
- if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
- run_ctx.retval = -EPERM;
- *(ret_flags) |= (func_ret >> 1);
- item++;
- }
- bpf_reset_run_ctx(old_run_ctx);
- rcu_read_unlock();
- migrate_enable();
- return run_ctx.retval;
-}
-
-static __always_inline int
-BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
- const void *ctx, bpf_prog_run_fn run_prog,
- int retval)
-{
- const struct bpf_prog_array_item *item;
- const struct bpf_prog *prog;
- const struct bpf_prog_array *array;
- struct bpf_run_ctx *old_run_ctx;
- struct bpf_cg_run_ctx run_ctx;
-
- run_ctx.retval = retval;
- migrate_disable();
- rcu_read_lock();
- array = rcu_dereference(array_rcu);
- item = &array->items[0];
- old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
- while ((prog = READ_ONCE(item->prog))) {
- run_ctx.prog_item = item;
- if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
- run_ctx.retval = -EPERM;
- item++;
- }
- bpf_reset_run_ctx(old_run_ctx);
- rcu_read_unlock();
- migrate_enable();
- return run_ctx.retval;
-}
-
static __always_inline u32
-BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array(const struct bpf_prog_array *array,
const void *ctx, bpf_prog_run_fn run_prog)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
- const struct bpf_prog_array *array;
struct bpf_run_ctx *old_run_ctx;
struct bpf_trace_run_ctx run_ctx;
u32 ret = 1;
- migrate_disable();
- rcu_read_lock();
- array = rcu_dereference(array_rcu);
+ RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held");
+
if (unlikely(!array))
- goto out;
+ return ret;
+
+ migrate_disable();
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
item = &array->items[0];
while ((prog = READ_ONCE(item->prog))) {
@@ -1400,50 +1423,10 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu,
item++;
}
bpf_reset_run_ctx(old_run_ctx);
-out:
- rcu_read_unlock();
migrate_enable();
return ret;
}
-/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
- * so BPF programs can request cwr for TCP packets.
- *
- * Current cgroup skb programs can only return 0 or 1 (0 to drop the
- * packet. This macro changes the behavior so the low order bit
- * indicates whether the packet should be dropped (0) or not (1)
- * and the next bit is a congestion notification bit. This could be
- * used by TCP to call tcp_enter_cwr()
- *
- * Hence, new allowed return values of CGROUP EGRESS BPF programs are:
- * 0: drop packet
- * 1: keep packet
- * 2: drop packet and cn
- * 3: keep packet and cn
- *
- * This macro then converts it to one of the NET_XMIT or an error
- * code that is then interpreted as drop packet (and no cn):
- * 0: NET_XMIT_SUCCESS skb should be transmitted
- * 1: NET_XMIT_DROP skb should be dropped and cn
- * 2: NET_XMIT_CN skb should be transmitted and cn
- * 3: -err skb should be dropped
- */
-#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \
- ({ \
- u32 _flags = 0; \
- bool _cn; \
- u32 _ret; \
- _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \
- _cn = _flags & BPF_RET_SET_CN; \
- if (_ret && !IS_ERR_VALUE((long)_ret)) \
- _ret = -EFAULT; \
- if (!_ret) \
- _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \
- else \
- _ret = (_cn ? NET_XMIT_DROP : _ret); \
- _ret; \
- })
-
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern struct mutex bpf_stats_enabled_mutex;
@@ -1497,6 +1480,12 @@ void bpf_prog_put(struct bpf_prog *prog);
void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
+struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset);
+void bpf_map_free_kptr_off_tab(struct bpf_map *map);
+struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map);
+bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b);
+void bpf_map_free_kptrs(struct bpf_map *map, void *map_value);
+
struct bpf_map *bpf_map_get(u32 ufd);
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
@@ -1590,6 +1579,7 @@ void bpf_link_put(struct bpf_link *link);
int bpf_link_new_fd(struct bpf_link *link);
struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
struct bpf_link *bpf_link_get_from_fd(u32 ufd);
+struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname, int flags);
@@ -1793,7 +1783,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
u32 *next_btf_id, enum bpf_type_flag *flag);
bool btf_struct_ids_match(struct bpf_verifier_log *log,
const struct btf *btf, u32 id, int off,
- const struct btf *need_btf, u32 need_type_id);
+ const struct btf *need_btf, u32 need_type_id,
+ bool strict);
int btf_distill_func_proto(struct bpf_verifier_log *log,
struct btf *btf,
@@ -2206,6 +2197,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto;
extern const struct bpf_func_proto bpf_map_push_elem_proto;
extern const struct bpf_func_proto bpf_map_pop_elem_proto;
extern const struct bpf_func_proto bpf_map_peek_elem_proto;
+extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto;
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
@@ -2243,12 +2235,16 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto;
+extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto;
extern const struct bpf_func_proto bpf_copy_from_user_proto;
extern const struct bpf_func_proto bpf_snprintf_btf_proto;
extern const struct bpf_func_proto bpf_snprintf_proto;
@@ -2268,6 +2264,7 @@ extern const struct bpf_func_proto bpf_find_vma_proto;
extern const struct bpf_func_proto bpf_loop_proto;
extern const struct bpf_func_proto bpf_strncmp_proto;
extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
+extern const struct bpf_func_proto bpf_kptr_xchg_proto;
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -2381,6 +2378,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
void *bpf_arch_text_copy(void *dst, void *src, size_t len);
+int bpf_arch_text_invalidate(void *dst, size_t len);
struct btf_id_set;
bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
@@ -2391,4 +2389,33 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
u32 **bin_buf, u32 num_args);
void bpf_bprintf_cleanup(void);
+/* the implementation of the opaque uapi struct bpf_dynptr */
+struct bpf_dynptr_kern {
+ void *data;
+ /* Size represents the number of usable bytes of dynptr data.
+ * If for example the offset is at 4 for a local dynptr whose data is
+ * of type u64, the number of usable bytes is 4.
+ *
+ * The upper 8 bits are reserved. It is as follows:
+ * Bits 0 - 23 = size
+ * Bits 24 - 30 = dynptr type
+ * Bit 31 = whether dynptr is read-only
+ */
+ u32 size;
+ u32 offset;
+} __aligned(8);
+
+enum bpf_dynptr_type {
+ BPF_DYNPTR_TYPE_INVALID,
+ /* Points to memory that is local to the bpf program */
+ BPF_DYNPTR_TYPE_LOCAL,
+ /* Underlying data is a ringbuf record */
+ BPF_DYNPTR_TYPE_RINGBUF,
+};
+
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+ enum bpf_dynptr_type type, u32 offset, u32 size);
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_check_size(u32 size);
+
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 493e63258497..7ea18d4da84b 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
struct bpf_local_storage_elem *selem,
- bool uncharge_omem);
+ bool uncharge_omem, bool use_trace_rcu);
-void bpf_selem_unlink(struct bpf_local_storage_elem *selem);
+void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu);
void bpf_selem_link_map(struct bpf_local_storage_map *smap,
struct bpf_local_storage_elem *selem);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 3e24ad0c4b3c..2b9112b80171 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -141,3 +141,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
#endif
BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
+BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3a9d2d7cc6b7..e8439f6cbe57 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -72,6 +72,18 @@ struct bpf_reg_state {
u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
+ /* For dynptr stack slots */
+ struct {
+ enum bpf_dynptr_type type;
+ /* A dynptr is 16 bytes so it takes up 2 stack slots.
+ * We need to track which slot is the first slot
+ * to protect against cases where the user may try to
+ * pass in an address starting at the second slot of the
+ * dynptr.
+ */
+ bool first_slot;
+ } dynptr;
+
/* Max size from any of the above. */
struct {
unsigned long raw1;
@@ -88,6 +100,8 @@ struct bpf_reg_state {
* for the purpose of tracking that it's freed.
* For PTR_TO_SOCKET this is used to share which pointers retain the
* same reference to the socket, to determine proper reference freeing.
+ * For stack slots that are dynptrs, this is used to track references to
+ * the dynptr to determine proper reference freeing.
*/
u32 id;
/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
@@ -174,9 +188,15 @@ enum bpf_stack_slot_type {
STACK_SPILL, /* register spilled into stack */
STACK_MISC, /* BPF program wrote some data into this slot */
STACK_ZERO, /* BPF program wrote constant zero */
+ /* A dynptr is stored in this stack slot. The type of dynptr
+ * is stored in bpf_stack_state->spilled_ptr.dynptr.type
+ */
+ STACK_DYNPTR,
};
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
+#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern)
+#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE)
struct bpf_stack_state {
struct bpf_reg_state spilled_ptr;
@@ -523,8 +543,7 @@ int check_ptr_off_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno);
int check_func_arg_reg_off(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno,
- enum bpf_arg_type arg_type,
- bool is_release_func);
+ enum bpf_arg_type arg_type);
int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno);
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 36bc09b8e890..2611cea2c2b6 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -17,6 +17,7 @@ enum btf_kfunc_type {
BTF_KFUNC_TYPE_ACQUIRE,
BTF_KFUNC_TYPE_RELEASE,
BTF_KFUNC_TYPE_RET_NULL,
+ BTF_KFUNC_TYPE_KPTR_ACQUIRE,
BTF_KFUNC_TYPE_MAX,
};
@@ -35,11 +36,19 @@ struct btf_kfunc_id_set {
struct btf_id_set *acquire_set;
struct btf_id_set *release_set;
struct btf_id_set *ret_null_set;
+ struct btf_id_set *kptr_acquire_set;
};
struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
};
};
+struct btf_id_dtor_kfunc {
+ u32 btf_id;
+ u32 kfunc_btf_id;
+};
+
+typedef void (*btf_dtor_kfunc_t)(void *);
+
extern const struct file_operations btf_fops;
void btf_get(struct btf *btf);
@@ -123,6 +132,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
u32 expected_offset, u32 expected_size);
int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
int btf_find_timer(const struct btf *btf, const struct btf_type *t);
+struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
+ const struct btf_type *t);
bool btf_type_is_void(const struct btf_type *t);
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
@@ -344,6 +355,9 @@ bool btf_kfunc_id_set_contains(const struct btf *btf,
enum btf_kfunc_type type, u32 kfunc_btf_id);
int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
const struct btf_kfunc_id_set *s);
+s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
+int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
+ struct module *owner);
#else
static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
u32 type_id)
@@ -367,6 +381,15 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
{
return 0;
}
+static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id)
+{
+ return -ENOENT;
+}
+static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors,
+ u32 add_cnt, struct module *owner)
+{
+ return 0;
+}
#endif
#endif
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index bc5d9cc34e4c..335a19092368 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -178,7 +178,8 @@ extern struct btf_id_set name;
BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \
BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \
BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \
- BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock)
enum {
#define BTF_SOCK_TYPE(name, str) name,
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index c2ea47f30046..e22dc03c850e 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -17,7 +17,6 @@
#include <linux/can.h>
#include <linux/can/bittiming.h>
#include <linux/can/error.h>
-#include <linux/can/led.h>
#include <linux/can/length.h>
#include <linux/can/netlink.h>
#include <linux/can/skb.h>
@@ -85,15 +84,6 @@ struct can_priv {
int (*do_get_berr_counter)(const struct net_device *dev,
struct can_berr_counter *bec);
int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
-
-#ifdef CONFIG_CAN_LEDS
- struct led_trigger *tx_led_trig;
- char tx_led_trig_name[CAN_LED_NAME_SZ];
- struct led_trigger *rx_led_trig;
- char rx_led_trig_name[CAN_LED_NAME_SZ];
- struct led_trigger *rxtx_led_trig;
- char rxtx_led_trig_name[CAN_LED_NAME_SZ];
-#endif
};
static inline bool can_tdc_is_enabled(const struct can_priv *priv)
diff --git a/include/linux/can/led.h b/include/linux/can/led.h
deleted file mode 100644
index 7c3cfd798c56..000000000000
--- a/include/linux/can/led.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2012, Fabio Baltieri <fabio.baltieri@gmail.com>
- */
-
-#ifndef _CAN_LED_H
-#define _CAN_LED_H
-
-#include <linux/if.h>
-#include <linux/leds.h>
-#include <linux/netdevice.h>
-
-enum can_led_event {
- CAN_LED_EVENT_OPEN,
- CAN_LED_EVENT_STOP,
- CAN_LED_EVENT_TX,
- CAN_LED_EVENT_RX,
-};
-
-#ifdef CONFIG_CAN_LEDS
-
-/* keep space for interface name + "-tx"/"-rx"/"-rxtx"
- * suffix and null terminator
- */
-#define CAN_LED_NAME_SZ (IFNAMSIZ + 6)
-
-void can_led_event(struct net_device *netdev, enum can_led_event event);
-void devm_can_led_init(struct net_device *netdev);
-int __init can_led_notifier_init(void);
-void __exit can_led_notifier_exit(void);
-
-#else
-
-static inline void can_led_event(struct net_device *netdev,
- enum can_led_event event)
-{
-}
-static inline void devm_can_led_init(struct net_device *netdev)
-{
-}
-static inline int can_led_notifier_init(void)
-{
- return 0;
-}
-static inline void can_led_notifier_exit(void)
-{
-}
-
-#endif
-
-#endif /* !_CAN_LED_H */
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index c11477620403..c205c51d79c9 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -42,8 +42,8 @@ int can_rx_offload_add_manual(struct net_device *dev,
int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
u64 reg);
int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
-int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
- struct sk_buff *skb, u32 timestamp);
+int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
+ struct sk_buff *skb, u32 timestamp);
unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
unsigned int idx, u32 timestamp,
unsigned int *frame_len_ptr);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 4af58459a1e7..99dc7bfbcd3c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -71,11 +71,13 @@ enum {
* struct kernel_ethtool_ringparam - RX/TX ring configuration
* @rx_buf_len: Current length of buffers on the rx ring.
* @tcp_data_split: Scatter packet headers and data to separate buffers
+ * @tx_push: The flag of tx push mode
* @cqe_size: Size of TX/RX completion queue event
*/
struct kernel_ethtool_ringparam {
u32 rx_buf_len;
u8 tcp_data_split;
+ u8 tx_push;
u32 cqe_size;
};
@@ -83,10 +85,12 @@ struct kernel_ethtool_ringparam {
* enum ethtool_supported_ring_param - indicator caps for setting ring params
* @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len
* @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size
+ * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
*/
enum ethtool_supported_ring_param {
ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
ETHTOOL_RING_USE_CQE_SIZE = BIT(1),
+ ETHTOOL_RING_USE_TX_PUSH = BIT(2),
};
#define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit))
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 295637a66c46..3b401fa0f374 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -52,6 +52,22 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
#define __underlying_strncpy __builtin_strncpy
#endif
+/**
+ * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking
+ *
+ * @dst: Destination memory address to write to
+ * @src: Source memory address to read from
+ * @bytes: How many bytes to write to @dst from @src
+ * @justification: Free-form text or comment describing why the use is needed
+ *
+ * This should be used for corner cases where the compiler cannot do the
+ * right thing, or during transitions between APIs, etc. It should be used
+ * very rarely, and includes a place for justification detailing where bounds
+ * checking has happened, and why existing solutions cannot be employed.
+ */
+#define unsafe_memcpy(dst, src, bytes, justification) \
+ __underlying_memcpy(dst, src, bytes)
+
/*
* Clang's use of __builtin_object_size() within inlines needs hinting via
* __pass_object_size(). The preference is to only ever use type 1 (member
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4816b7e11047..820500430eae 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -303,6 +303,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops);
extern void ftrace_stub(unsigned long a0, unsigned long a1,
struct ftrace_ops *op, struct ftrace_regs *fregs);
+
+int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs);
#else /* !CONFIG_FUNCTION_TRACER */
/*
* (un)register_ftrace_function must be a macro since the ops parameter
@@ -313,6 +315,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1,
static inline void ftrace_kill(void) { }
static inline void ftrace_free_init_mem(void) { }
static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
+static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
+{
+ return -EOPNOTSUPP;
+}
#endif /* CONFIG_FUNCTION_TRACER */
struct ftrace_func_entry {
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 9055cb380ee2..db0f4fcfdaf4 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -79,8 +79,9 @@ extern int icmpv6_init(void);
extern int icmpv6_err_convert(u8 type, u8 code,
int *err);
extern void icmpv6_cleanup(void);
-extern void icmpv6_param_prob(struct sk_buff *skb,
- u8 code, int pos);
+extern void icmpv6_param_prob_reason(struct sk_buff *skb,
+ u8 code, int pos,
+ enum skb_drop_reason reason);
struct flowi6;
struct in6_addr;
@@ -91,6 +92,12 @@ extern void icmpv6_flow_init(struct sock *sk,
const struct in6_addr *daddr,
int oif);
+static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
+{
+ icmpv6_param_prob_reason(skb, code, pos,
+ SKB_DROP_REASON_NOT_SPECIFIED);
+}
+
static inline bool icmpv6_is_err(int type)
{
switch (type) {
diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h
index 95c831162212..f1f9412b6ac6 100644
--- a/include/linux/ieee802154.h
+++ b/include/linux/ieee802154.h
@@ -134,18 +134,46 @@ enum {
* a successful transmission.
*/
IEEE802154_SUCCESS = 0x0,
-
+ /* The requested operation failed. */
+ IEEE802154_MAC_ERROR = 0x1,
+ /* The requested operation has been cancelled. */
+ IEEE802154_CANCELLED = 0x2,
+ /*
+ * Device is ready to poll the coordinator for data in a non beacon
+ * enabled PAN.
+ */
+ IEEE802154_READY_FOR_POLL = 0x3,
+ /* Wrong frame counter. */
+ IEEE802154_COUNTER_ERROR = 0xdb,
+ /*
+ * The frame does not conforms to the incoming key usage policy checking
+ * procedure.
+ */
+ IEEE802154_IMPROPER_KEY_TYPE = 0xdc,
+ /*
+ * The frame does not conforms to the incoming security level usage
+ * policy checking procedure.
+ */
+ IEEE802154_IMPROPER_SECURITY_LEVEL = 0xdd,
+ /* Secured frame received with an empty Frame Version field. */
+ IEEE802154_UNSUPPORTED_LEGACY = 0xde,
+ /*
+ * A secured frame is received or must be sent but security is not
+ * enabled in the device. Or, the Auxiliary Security Header has security
+ * level of zero in it.
+ */
+ IEEE802154_UNSUPPORTED_SECURITY = 0xdf,
/* The beacon was lost following a synchronization request. */
- IEEE802154_BEACON_LOSS = 0xe0,
+ IEEE802154_BEACON_LOST = 0xe0,
/*
* A transmission could not take place due to activity on the
* channel, i.e., the CSMA-CA mechanism has failed.
*/
- IEEE802154_CHNL_ACCESS_FAIL = 0xe1,
+ IEEE802154_CHANNEL_ACCESS_FAILURE = 0xe1,
/* The GTS request has been denied by the PAN coordinator. */
- IEEE802154_DENINED = 0xe2,
+ IEEE802154_DENIED = 0xe2,
/* The attempt to disable the transceiver has failed. */
- IEEE802154_DISABLE_TRX_FAIL = 0xe3,
+ IEEE802154_DISABLE_TRX_FAILURE = 0xe3,
/*
* The received frame induces a failed security check according to
* the security suite.
@@ -185,9 +213,9 @@ enum {
* A PAN identifier conflict has been detected and communicated to the
* PAN coordinator.
*/
- IEEE802154_PANID_CONFLICT = 0xee,
+ IEEE802154_PAN_ID_CONFLICT = 0xee,
/* A coordinator realignment command has been received. */
- IEEE802154_REALIGMENT = 0xef,
+ IEEE802154_REALIGNMENT = 0xef,
/* The transaction has expired and its information discarded. */
IEEE802154_TRANSACTION_EXPIRED = 0xf0,
/* There is no capacity to store the transaction. */
@@ -203,12 +231,49 @@ enum {
* A SET/GET request was issued with the identifier of a PIB attribute
* that is not supported.
*/
- IEEE802154_UNSUPPORTED_ATTR = 0xf4,
+ IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4,
+ /* Missing source or destination address or address mode. */
+ IEEE802154_INVALID_ADDRESS = 0xf5,
+ /*
+ * MLME asked to turn the receiver on, but the on time duration is too
+ * big compared to the macBeaconOrder.
+ */
+ IEEE802154_ON_TIME_TOO_LONG = 0xf6,
+ /*
+ * MLME asaked to turn the receiver on, but the request was delayed for
+ * too long before getting processed.
+ */
+ IEEE802154_PAST_TIME = 0xf7,
+ /*
+ * The StartTime parameter is nonzero, and the MLME is not currently
+ * tracking the beacon of the coordinator through which it is
+ * associated.
+ */
+ IEEE802154_TRACKING_OFF = 0xf8,
+ /*
+ * The index inside the hierarchical values in PIBAttribute is out of
+ * range.
+ */
+ IEEE802154_INVALID_INDEX = 0xf9,
+ /*
+ * The number of PAN descriptors discovered during a scan has been
+ * reached.
+ */
+ IEEE802154_LIMIT_REACHED = 0xfa,
+ /*
+ * The PIBAttribute parameter specifies an attribute that is a read-only
+ * attribute.
+ */
+ IEEE802154_READ_ONLY = 0xfb,
/*
* A request to perform a scan operation failed because the MLME was
* in the process of performing a previously initiated scan operation.
*/
IEEE802154_SCAN_IN_PROGRESS = 0xfc,
+ /* The outgoing superframe overlaps the incoming superframe. */
+ IEEE802154_SUPERFRAME_OVERLAP = 0xfd,
+ /* Any other error situation. */
+ IEEE802154_SYSTEM_ERROR = 0xff,
};
/* frame control handling */
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 16870f86c74d..38c8203d52cb 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -61,6 +61,7 @@ struct ipv6_devconf {
__s32 suppress_frag_ndisc;
__s32 accept_ra_mtu;
__s32 drop_unsolicited_na;
+ __s32 accept_unsolicited_na;
struct ipv6_stable_secret {
bool initialized;
struct in6_addr secret;
@@ -144,6 +145,7 @@ struct inet6_skb_parm {
#define IP6SKB_L3SLAVE 64
#define IP6SKB_JUMBOGRAM 128
#define IP6SKB_SEG6 256
+#define IP6SKB_FAKEJUMBO 512
};
#if defined(CONFIG_NET_L3_MASTER_DEV)
@@ -339,8 +341,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
return (struct raw6_sock *)sk;
}
-#define __ipv6_only_sock(sk) (sk->sk_ipv6only)
-#define ipv6_only_sock(sk) (__ipv6_only_sock(sk))
+#define ipv6_only_sock(sk) (sk->sk_ipv6only)
#define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \
inet6_sk(sk)->rxopt.bits.rxinfo)
@@ -357,7 +358,6 @@ static inline int inet_v6_ipv6only(const struct sock *sk)
return ipv6_only_sock(sk);
}
#else
-#define __ipv6_only_sock(sk) 0
#define ipv6_only_sock(sk) 0
#define ipv6_sk_rxinfo(sk) 0
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index ce1bd2fbf23e..ad39636e0c3f 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -65,11 +65,11 @@ static inline void *dereference_symbol_descriptor(void *ptr)
return ptr;
}
+#ifdef CONFIG_KALLSYMS
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
void *data);
-#ifdef CONFIG_KALLSYMS
/* Lookup the address for a symbol. Returns 0 if not found. */
unsigned long kallsyms_lookup_name(const char *name);
@@ -163,6 +163,11 @@ static inline bool kallsyms_show_value(const struct cred *cred)
return false;
}
+static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+ unsigned long), void *data)
+{
+ return -EOPNOTSUPP;
+}
#endif /*CONFIG_KALLSYMS*/
static inline void print_ip_sym(const char *loglvl, unsigned long ip)
diff --git a/include/linux/list.h b/include/linux/list.h
index dd6c2041d09c..57e8b559cdf6 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -564,6 +564,19 @@ static inline void list_splice_tail_init(struct list_head *list,
list_entry((pos)->member.next, typeof(*(pos)), member)
/**
+ * list_next_entry_circular - get the next element in list
+ * @pos: the type * to cursor.
+ * @head: the list head to take the element from.
+ * @member: the name of the list_head within the struct.
+ *
+ * Wraparound if pos is the last element (return the first element).
+ * Note, that list is expected to be not empty.
+ */
+#define list_next_entry_circular(pos, head, member) \
+ (list_is_last(&(pos)->member, head) ? \
+ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member))
+
+/**
* list_prev_entry - get the prev element in list
* @pos: the type * to cursor
* @member: the name of the list_head within the struct.
@@ -572,6 +585,19 @@ static inline void list_splice_tail_init(struct list_head *list,
list_entry((pos)->member.prev, typeof(*(pos)), member)
/**
+ * list_prev_entry_circular - get the prev element in list
+ * @pos: the type * to cursor.
+ * @head: the list head to take the element from.
+ * @member: the name of the list_head within the struct.
+ *
+ * Wraparound if pos is the first element (return the last element).
+ * Note, that list is expected to be not empty.
+ */
+#define list_prev_entry_circular(pos, head, member) \
+ (list_is_first(&(pos)->member, head) ? \
+ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member))
+
+/**
* list_for_each - iterate over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
@@ -580,6 +606,16 @@ static inline void list_splice_tail_init(struct list_head *list,
for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
/**
+ * list_for_each_rcu - Iterate over a list in an RCU-safe fashion
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each_rcu(pos, head) \
+ for (pos = rcu_dereference((head)->next); \
+ !list_is_head(pos, (head)); \
+ pos = rcu_dereference(pos->next))
+
+/**
* list_for_each_continue - continue iteration over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index ecac96d52e01..00177567cfef 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -340,6 +340,76 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising,
advertising, lpa & MDIO_AN_10GBT_STAT_LP10G);
}
+/**
+ * mii_t1_adv_l_mod_linkmode_t
+ * @advertising: target the linkmode advertisement settings
+ * @lpa: value of the BASE-T1 Autonegotiation Advertisement [15:0] Register
+ *
+ * A small helper function that translates BASE-T1 Autonegotiation
+ * Advertisement [15:0] Register bits to linkmode advertisement settings.
+ * Other bits in advertising aren't changed.
+ */
+static inline void mii_t1_adv_l_mod_linkmode_t(unsigned long *advertising, u32 lpa)
+{
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising,
+ lpa & MDIO_AN_T1_ADV_L_PAUSE_CAP);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising,
+ lpa & MDIO_AN_T1_ADV_L_PAUSE_ASYM);
+}
+
+/**
+ * mii_t1_adv_m_mod_linkmode_t
+ * @advertising: target the linkmode advertisement settings
+ * @lpa: value of the BASE-T1 Autonegotiation Advertisement [31:16] Register
+ *
+ * A small helper function that translates BASE-T1 Autonegotiation
+ * Advertisement [31:16] Register bits to linkmode advertisement settings.
+ * Other bits in advertising aren't changed.
+ */
+static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 lpa)
+{
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
+ advertising, lpa & MDIO_AN_T1_ADV_M_B10L);
+}
+
+/**
+ * linkmode_adv_to_mii_t1_adv_l_t
+ * @advertising: the linkmode advertisement settings
+ *
+ * A small helper function that translates linkmode advertisement
+ * settings to phy autonegotiation advertisements for the
+ * BASE-T1 Autonegotiation Advertisement [15:0] Register.
+ */
+static inline u32 linkmode_adv_to_mii_t1_adv_l_t(unsigned long *advertising)
+{
+ u32 result = 0;
+
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising))
+ result |= MDIO_AN_T1_ADV_L_PAUSE_CAP;
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising))
+ result |= MDIO_AN_T1_ADV_L_PAUSE_ASYM;
+
+ return result;
+}
+
+/**
+ * linkmode_adv_to_mii_t1_adv_m_t
+ * @advertising: the linkmode advertisement settings
+ *
+ * A small helper function that translates linkmode advertisement
+ * settings to phy autonegotiation advertisements for the
+ * BASE-T1 Autonegotiation Advertisement [31:16] Register.
+ */
+static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
+{
+ u32 result = 0;
+
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising))
+ result |= MDIO_AN_T1_ADV_M_B10L;
+
+ return result;
+}
+
int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum,
diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h
index a18c1539a152..0c706085c205 100644
--- a/include/linux/mfd/idt8a340_reg.h
+++ b/include/linux/mfd/idt8a340_reg.h
@@ -407,7 +407,7 @@
#define TOD_READ_PRIMARY_0 0xcc40
#define TOD_READ_PRIMARY_0_V520 0xcc50
/* 8-bit subns, 32-bit ns, 48-bit seconds */
-#define TOD_READ_PRIMARY 0x0000
+#define TOD_READ_PRIMARY_BASE 0x0000
/* Counter increments after TOD write is completed */
#define TOD_READ_PRIMARY_COUNTER 0x000b
/* Read trigger configuration */
@@ -424,6 +424,16 @@
#define TOD_READ_SECONDARY_0 0xcc90
#define TOD_READ_SECONDARY_0_V520 0xcca0
+/* 8-bit subns, 32-bit ns, 48-bit seconds */
+#define TOD_READ_SECONDARY_BASE 0x0000
+/* Counter increments after TOD write is completed */
+#define TOD_READ_SECONDARY_COUNTER 0x000b
+/* Read trigger configuration */
+#define TOD_READ_SECONDARY_SEL_CFG_0 0x000c
+/* Read trigger selection */
+#define TOD_READ_SECONDARY_CMD 0x000e
+#define TOD_READ_SECONDARY_CMD_V520 0x000f
+
#define TOD_READ_SECONDARY_1 0xcca0
#define TOD_READ_SECONDARY_1_V520 0xccb0
#define TOD_READ_SECONDARY_2 0xccb0
diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h
deleted file mode 100644
index dacf69516002..000000000000
--- a/include/linux/mlx5/accel.h
+++ /dev/null
@@ -1,156 +0,0 @@
-/*
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses. You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- * Redistribution and use in source and binary forms, with or
- * without modification, are permitted provided that the following
- * conditions are met:
- *
- * - Redistributions of source code must retain the above
- * copyright notice, this list of conditions and the following
- * disclaimer.
- *
- * - Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following
- * disclaimer in the documentation and/or other materials
- * provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#ifndef __MLX5_ACCEL_H__
-#define __MLX5_ACCEL_H__
-
-#include <linux/mlx5/driver.h>
-
-enum mlx5_accel_esp_aes_gcm_keymat_iv_algo {
- MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ,
-};
-
-enum mlx5_accel_esp_flags {
- MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */
- MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0,
- MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED = 1UL << 1,
- MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2,
-};
-
-enum mlx5_accel_esp_action {
- MLX5_ACCEL_ESP_ACTION_DECRYPT,
- MLX5_ACCEL_ESP_ACTION_ENCRYPT,
-};
-
-enum mlx5_accel_esp_keymats {
- MLX5_ACCEL_ESP_KEYMAT_AES_NONE,
- MLX5_ACCEL_ESP_KEYMAT_AES_GCM,
-};
-
-enum mlx5_accel_esp_replay {
- MLX5_ACCEL_ESP_REPLAY_NONE,
- MLX5_ACCEL_ESP_REPLAY_BMP,
-};
-
-struct aes_gcm_keymat {
- u64 seq_iv;
- enum mlx5_accel_esp_aes_gcm_keymat_iv_algo iv_algo;
-
- u32 salt;
- u32 icv_len;
-
- u32 key_len;
- u32 aes_key[256 / 32];
-};
-
-struct mlx5_accel_esp_xfrm_attrs {
- enum mlx5_accel_esp_action action;
- u32 esn;
- __be32 spi;
- u32 seq;
- u32 tfc_pad;
- u32 flags;
- u32 sa_handle;
- enum mlx5_accel_esp_replay replay_type;
- union {
- struct {
- u32 size;
-
- } bmp;
- } replay;
- enum mlx5_accel_esp_keymats keymat_type;
- union {
- struct aes_gcm_keymat aes_gcm;
- } keymat;
-
- union {
- __be32 a4;
- __be32 a6[4];
- } saddr;
-
- union {
- __be32 a4;
- __be32 a6[4];
- } daddr;
-
- u8 is_ipv6;
-};
-
-struct mlx5_accel_esp_xfrm {
- struct mlx5_core_dev *mdev;
- struct mlx5_accel_esp_xfrm_attrs attrs;
-};
-
-enum {
- MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA = 1UL << 0,
-};
-
-enum mlx5_accel_ipsec_cap {
- MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0,
- MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1,
- MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 2,
- MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 3,
- MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 4,
- MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER = 1 << 5,
- MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 6,
- MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7,
-};
-
-#ifdef CONFIG_MLX5_ACCEL
-
-u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev);
-
-struct mlx5_accel_esp_xfrm *
-mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
- const struct mlx5_accel_esp_xfrm_attrs *attrs,
- u32 flags);
-void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm);
-int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
- const struct mlx5_accel_esp_xfrm_attrs *attrs);
-
-#else
-
-static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; }
-
-static inline struct mlx5_accel_esp_xfrm *
-mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev,
- const struct mlx5_accel_esp_xfrm_attrs *attrs,
- u32 flags) { return ERR_PTR(-EOPNOTSUPP); }
-static inline void
-mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {}
-static inline int
-mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
- const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; }
-
-#endif /* CONFIG_MLX5_ACCEL */
-#endif /* __MLX5_ACCEL_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 9424503eb8d3..b064bc278f52 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -84,7 +84,7 @@ enum mlx5_sqp_t {
};
enum {
- MLX5_MAX_PORTS = 2,
+ MLX5_MAX_PORTS = 4,
};
enum {
@@ -272,6 +272,8 @@ struct mlx5_cmd_stats {
u32 last_failed_errno;
/* last bad status returned by FW */
u8 last_failed_mbox_status;
+ /* last command failed syndrome returned by FW */
+ u32 last_failed_syndrome;
struct dentry *root;
/* protect command average calculations */
spinlock_t lock;
@@ -558,6 +560,7 @@ struct mlx5_debugfs_entries {
struct dentry *cq_debugfs;
struct dentry *cmdif_debugfs;
struct dentry *pages_debugfs;
+ struct dentry *lag_debugfs;
};
struct mlx5_ft_pool;
@@ -632,6 +635,7 @@ enum mlx5_device_state {
enum mlx5_interface_state {
MLX5_INTERFACE_STATE_UP = BIT(0),
+ MLX5_BREAK_FW_WAIT = BIT(1),
};
enum mlx5_pci_status {
@@ -778,9 +782,6 @@ struct mlx5_core_dev {
#ifdef CONFIG_MLX5_FPGA
struct mlx5_fpga_device *fpga;
#endif
-#ifdef CONFIG_MLX5_ACCEL
- const struct mlx5_accel_ipsec_ops *ipsec_ops;
-#endif
struct mlx5_clock clock;
struct mlx5_ib_clock_info *clock_info;
struct mlx5_fw_tracer *tracer;
@@ -1052,9 +1053,14 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
int size_in, void *data_out, int size_out,
u16 reg_num, int arg, int write);
-int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db);
int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db,
int node);
+
+static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
+{
+ return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
+}
+
void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
const char *mlx5_command_str(int command);
@@ -1144,6 +1150,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
int num_counters,
size_t *offsets);
struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev);
+u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev);
struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index e3bfed68b08a..8135713b0d2d 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,18 @@
#define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
+enum mlx5_flow_destination_type {
+ MLX5_FLOW_DESTINATION_TYPE_NONE,
+ MLX5_FLOW_DESTINATION_TYPE_VPORT,
+ MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE,
+ MLX5_FLOW_DESTINATION_TYPE_TIR,
+ MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER,
+ MLX5_FLOW_DESTINATION_TYPE_UPLINK,
+ MLX5_FLOW_DESTINATION_TYPE_PORT,
+ MLX5_FLOW_DESTINATION_TYPE_COUNTER,
+ MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM,
+};
+
enum {
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16,
MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7d2d0ba82144..78b3d3465dd7 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1359,7 +1359,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 vhca_resource_manager[0x1];
u8 hca_cap_2[0x1];
- u8 reserved_at_21[0x1];
+ u8 create_lag_when_not_master_up[0x1];
u8 dtor[0x1];
u8 event_on_vhca_state_teardown_request[0x1];
u8 event_on_vhca_state_in_use[0x1];
@@ -1806,16 +1806,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
u8 reserved_at_c0[0x740];
};
-enum mlx5_flow_destination_type {
- MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0,
- MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1,
- MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2,
- MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
- MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8,
-
- MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99,
- MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100,
- MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101,
+enum mlx5_ifc_flow_destination_type {
+ MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT = 0x0,
+ MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1,
+ MLX5_IFC_FLOW_DESTINATION_TYPE_TIR = 0x2,
+ MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
+ MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK = 0x8,
};
enum mlx5_flow_table_miss_action {
@@ -10820,7 +10816,8 @@ struct mlx5_ifc_dcbx_param_bits {
enum {
MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0,
- MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT,
+ MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT = 1,
+ MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW = 2,
};
struct mlx5_ifc_lagc_bits {
@@ -11383,8 +11380,6 @@ enum {
enum {
MLX5_IPSEC_OBJECT_ICV_LEN_16B,
- MLX5_IPSEC_OBJECT_ICV_LEN_12B,
- MLX5_IPSEC_OBJECT_ICV_LEN_8B,
};
struct mlx5_ifc_ipsec_obj_bits {
diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h
index 07d77323f78a..45c7c0d67635 100644
--- a/include/linux/mlx5/mlx5_ifc_fpga.h
+++ b/include/linux/mlx5/mlx5_ifc_fpga.h
@@ -54,7 +54,6 @@ enum {
enum {
MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2,
- MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3,
};
struct mlx5_ifc_fpga_shell_caps_bits {
@@ -387,89 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits {
u8 reserved_at_40[0x40];
};
-struct mlx5_ifc_tls_extended_cap_bits {
- u8 aes_gcm_128[0x1];
- u8 aes_gcm_256[0x1];
- u8 reserved_at_2[0x1e];
- u8 reserved_at_20[0x20];
- u8 context_capacity_total[0x20];
- u8 context_capacity_rx[0x20];
- u8 context_capacity_tx[0x20];
- u8 reserved_at_a0[0x10];
- u8 tls_counter_size[0x10];
- u8 tls_counters_addr_low[0x20];
- u8 tls_counters_addr_high[0x20];
- u8 rx[0x1];
- u8 tx[0x1];
- u8 tls_v12[0x1];
- u8 tls_v13[0x1];
- u8 lro[0x1];
- u8 ipv6[0x1];
- u8 reserved_at_106[0x1a];
-};
-
-struct mlx5_ifc_ipsec_extended_cap_bits {
- u8 encapsulation[0x20];
-
- u8 reserved_0[0x12];
- u8 v2_command[0x1];
- u8 udp_encap[0x1];
- u8 rx_no_trailer[0x1];
- u8 ipv4_fragment[0x1];
- u8 ipv6[0x1];
- u8 esn[0x1];
- u8 lso[0x1];
- u8 transport_and_tunnel_mode[0x1];
- u8 tunnel_mode[0x1];
- u8 transport_mode[0x1];
- u8 ah_esp[0x1];
- u8 esp[0x1];
- u8 ah[0x1];
- u8 ipv4_options[0x1];
-
- u8 auth_alg[0x20];
-
- u8 enc_alg[0x20];
-
- u8 sa_cap[0x20];
-
- u8 reserved_1[0x10];
- u8 number_of_ipsec_counters[0x10];
-
- u8 ipsec_counters_addr_low[0x20];
- u8 ipsec_counters_addr_high[0x20];
-};
-
-struct mlx5_ifc_ipsec_counters_bits {
- u8 dec_in_packets[0x40];
-
- u8 dec_out_packets[0x40];
-
- u8 dec_bypass_packets[0x40];
-
- u8 enc_in_packets[0x40];
-
- u8 enc_out_packets[0x40];
-
- u8 enc_bypass_packets[0x40];
-
- u8 drop_dec_packets[0x40];
-
- u8 failed_auth_dec_packets[0x40];
-
- u8 drop_enc_packets[0x40];
-
- u8 success_add_sa[0x40];
-
- u8 fail_add_sa[0x40];
-
- u8 success_delete_sa[0x40];
-
- u8 fail_delete_sa[0x40];
-
- u8 dropped_cmd[0x40];
-};
-
enum {
MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED = 0x1,
MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED = 0x2,
@@ -486,131 +402,4 @@ struct mlx5_ifc_fpga_qp_error_event_bits {
u8 reserved_at_c0[0x8];
u8 fpga_qpn[0x18];
};
-enum mlx5_ifc_fpga_ipsec_response_syndrome {
- MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0,
- MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1,
- MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE = 2,
- MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE = 3,
-};
-
-struct mlx5_ifc_fpga_ipsec_cmd_resp {
- __be32 syndrome;
- union {
- __be32 sw_sa_handle;
- __be32 flags;
- };
- u8 reserved[24];
-} __packed;
-
-enum mlx5_ifc_fpga_ipsec_cmd_opcode {
- MLX5_FPGA_IPSEC_CMD_OP_ADD_SA = 0,
- MLX5_FPGA_IPSEC_CMD_OP_DEL_SA = 1,
- MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 = 2,
- MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 = 3,
- MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2 = 4,
- MLX5_FPGA_IPSEC_CMD_OP_SET_CAP = 5,
-};
-
-enum mlx5_ifc_fpga_ipsec_cap {
- MLX5_FPGA_IPSEC_CAP_NO_TRAILER = BIT(0),
-};
-
-struct mlx5_ifc_fpga_ipsec_cmd_cap {
- __be32 cmd;
- __be32 flags;
- u8 reserved[24];
-} __packed;
-
-enum mlx5_ifc_fpga_ipsec_sa_flags {
- MLX5_FPGA_IPSEC_SA_ESN_EN = BIT(0),
- MLX5_FPGA_IPSEC_SA_ESN_OVERLAP = BIT(1),
- MLX5_FPGA_IPSEC_SA_IPV6 = BIT(2),
- MLX5_FPGA_IPSEC_SA_DIR_SX = BIT(3),
- MLX5_FPGA_IPSEC_SA_SPI_EN = BIT(4),
- MLX5_FPGA_IPSEC_SA_SA_VALID = BIT(5),
- MLX5_FPGA_IPSEC_SA_IP_ESP = BIT(6),
- MLX5_FPGA_IPSEC_SA_IP_AH = BIT(7),
-};
-
-enum mlx5_ifc_fpga_ipsec_sa_enc_mode {
- MLX5_FPGA_IPSEC_SA_ENC_MODE_NONE = 0,
- MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128 = 1,
- MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128 = 3,
-};
-
-struct mlx5_ifc_fpga_ipsec_sa_v1 {
- __be32 cmd;
- u8 key_enc[32];
- u8 key_auth[32];
- __be32 sip[4];
- __be32 dip[4];
- union {
- struct {
- __be32 reserved;
- u8 salt_iv[8];
- __be32 salt;
- } __packed gcm;
- struct {
- u8 salt[16];
- } __packed cbc;
- };
- __be32 spi;
- __be32 sw_sa_handle;
- __be16 tfclen;
- u8 enc_mode;
- u8 reserved1[2];
- u8 flags;
- u8 reserved2[2];
-};
-
-struct mlx5_ifc_fpga_ipsec_sa {
- struct mlx5_ifc_fpga_ipsec_sa_v1 ipsec_sa_v1;
- __be16 udp_sp;
- __be16 udp_dp;
- u8 reserved1[4];
- __be32 esn;
- __be16 vid; /* only 12 bits, rest is reserved */
- __be16 reserved2;
-} __packed;
-
-enum fpga_tls_cmds {
- CMD_SETUP_STREAM = 0x1001,
- CMD_TEARDOWN_STREAM = 0x1002,
- CMD_RESYNC_RX = 0x1003,
-};
-
-#define MLX5_TLS_1_2 (0)
-
-#define MLX5_TLS_ALG_AES_GCM_128 (0)
-#define MLX5_TLS_ALG_AES_GCM_256 (1)
-
-struct mlx5_ifc_tls_cmd_bits {
- u8 command_type[0x20];
- u8 ipv6[0x1];
- u8 direction_sx[0x1];
- u8 tls_version[0x2];
- u8 reserved[0x1c];
- u8 swid[0x20];
- u8 src_port[0x10];
- u8 dst_port[0x10];
- union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6;
- union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6;
- u8 tls_rcd_sn[0x40];
- u8 tcp_sn[0x20];
- u8 tls_implicit_iv[0x20];
- u8 tls_xor_iv[0x40];
- u8 encryption_key[0x100];
- u8 alg[4];
- u8 reserved2[0x1c];
- u8 reserved3[0x4a0];
-};
-
-struct mlx5_ifc_tls_resp_bits {
- u8 syndrome[0x20];
- u8 stream_id[0x20];
- u8 reserved[0x40];
-};
-
-#define MLX5_TLS_COMMAND_SIZE (0x100)
-
#endif /* MLX5_IFC_FPGA_H */
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 28a928b0684b..e96ee1e348cb 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -141,7 +141,7 @@ enum mlx5_ptys_width {
MLX5_PTYS_WIDTH_12X = 1 << 4,
};
-#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+#define MLX5E_PROT_MASK(link_mode) (1U << link_mode)
#define MLX5_GET_ETH_PROTO(reg, out, ext, field) \
(ext ? MLX5_GET(reg, out, ext_##field) : \
MLX5_GET(reg, out, field))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f736c020cde2..f615a66c89e9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -50,6 +50,7 @@
#include <linux/hashtable.h>
#include <linux/rbtree.h>
#include <net/net_trackers.h>
+#include <net/net_debug.h>
struct netpoll_info;
struct device;
@@ -59,7 +60,8 @@ struct dsa_port;
struct ip_tunnel_parm;
struct macsec_context;
struct macsec_ops;
-
+struct netdev_name_node;
+struct sd_flow_limit;
struct sfp_bus;
/* 802.11 specific */
struct wireless_dev;
@@ -202,6 +204,7 @@ struct net_device_core_stats {
unsigned long rx_dropped;
unsigned long tx_dropped;
unsigned long rx_nohandler;
+ unsigned long rx_otherhost_dropped;
} __aligned(4 * sizeof(unsigned long));
#include <linux/cache.h>
@@ -862,6 +865,7 @@ enum net_device_path_type {
DEV_PATH_BRIDGE,
DEV_PATH_PPPOE,
DEV_PATH_DSA,
+ DEV_PATH_MTK_WDMA,
};
struct net_device_path {
@@ -887,6 +891,12 @@ struct net_device_path {
int port;
u16 proto;
} dsa;
+ struct {
+ u8 wdma_idx;
+ u8 queue;
+ u16 wcid;
+ u8 bss;
+ } mtk_wdma;
};
};
@@ -1013,16 +1023,6 @@ struct dev_ifalias {
struct devlink;
struct tlsdev_ops;
-struct netdev_name_node {
- struct hlist_node hlist;
- struct list_head list;
- struct net_device *dev;
- const char *name;
-};
-
-int netdev_name_node_alt_create(struct net_device *dev, const char *name);
-int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
-
struct netdev_net_notifier {
struct list_head list;
struct notifier_block *nb;
@@ -1261,6 +1261,10 @@ struct netdev_net_notifier {
* struct net_device *dev,
* const unsigned char *addr, u16 vid)
* Deletes the FDB entry from dev coresponding to addr.
+ * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[],
+ * struct net_device *dev,
+ * u16 vid,
+ * struct netlink_ext_ack *extack);
* int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
* struct net_device *dev, struct net_device *filter_dev,
* int *idx)
@@ -1353,6 +1357,12 @@ struct netdev_net_notifier {
* The caller must be under RCU read context.
* int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
* Get the forwarding path to reach the real device from the HW destination address
+ * ktime_t (*ndo_get_tstamp)(struct net_device *dev,
+ * const struct skb_shared_hwtstamps *hwtstamps,
+ * bool cycles);
+ * Get hardware timestamp based on normal/adjustable time or free running
+ * cycle counter. This function is required if physical clock supports a
+ * free running cycle counter.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1510,7 +1520,12 @@ struct net_device_ops {
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
- u16 vid);
+ u16 vid, struct netlink_ext_ack *extack);
+ int (*ndo_fdb_del_bulk)(struct ndmsg *ndm,
+ struct nlattr *tb[],
+ struct net_device *dev,
+ u16 vid,
+ struct netlink_ext_ack *extack);
int (*ndo_fdb_dump)(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
@@ -1570,6 +1585,9 @@ struct net_device_ops {
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
struct net_device_path *path);
+ ktime_t (*ndo_get_tstamp)(struct net_device *dev,
+ const struct skb_shared_hwtstamps *hwtstamps,
+ bool cycles);
};
/**
@@ -1909,8 +1927,10 @@ enum netdev_ml_priv_type {
* @rtnl_link_ops: Rtnl_link_ops
*
* @gso_max_size: Maximum size of generic segmentation offload
+ * @tso_max_size: Device (as in HW) limit on the max TSO request size
* @gso_max_segs: Maximum number of segments that can be passed to the
* NIC for GSO
+ * @tso_max_segs: Device (as in HW) limit on the max TSO segment count
*
* @dcbnl_ops: Data Center Bridging netlink ops
* @num_tc: Number of traffic classes in the net device
@@ -2099,6 +2119,8 @@ struct net_device {
/* Protocol-specific pointers */
+ struct in_device __rcu *ip_ptr;
+ struct inet6_dev __rcu *ip6_ptr;
#if IS_ENABLED(CONFIG_VLAN_8021Q)
struct vlan_info __rcu *vlan_info;
#endif
@@ -2111,16 +2133,18 @@ struct net_device {
#if IS_ENABLED(CONFIG_ATALK)
void *atalk_ptr;
#endif
- struct in_device __rcu *ip_ptr;
#if IS_ENABLED(CONFIG_DECNET)
struct dn_dev __rcu *dn_ptr;
#endif
- struct inet6_dev __rcu *ip6_ptr;
#if IS_ENABLED(CONFIG_AX25)
void *ax25_ptr;
#endif
+#if IS_ENABLED(CONFIG_CFG80211)
struct wireless_dev *ieee80211_ptr;
+#endif
+#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN)
struct wpan_dev *ieee802154_ptr;
+#endif
#if IS_ENABLED(CONFIG_MPLS_ROUTING)
struct mpls_dev __rcu *mpls_ptr;
#endif
@@ -2141,7 +2165,11 @@ struct net_device {
struct bpf_prog __rcu *xdp_prog;
unsigned long gro_flush_timeout;
int napi_defer_hard_irqs;
-#define GRO_MAX_SIZE 65536
+#define GRO_LEGACY_MAX_SIZE 65536u
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GRO_MAX_SIZE (8 * 65535u)
unsigned int gro_max_size;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
@@ -2252,10 +2280,20 @@ struct net_device {
const struct rtnl_link_ops *rtnl_link_ops;
/* for setting kernel sock attribute on TCP connection setup */
-#define GSO_MAX_SIZE 65536
+#define GSO_MAX_SEGS 65535u
+#define GSO_LEGACY_MAX_SIZE 65536u
+/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
+ * and shinfo->gso_segs is a 16bit field.
+ */
+#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS)
+
unsigned int gso_max_size;
-#define GSO_MAX_SEGS 65535
+#define TSO_LEGACY_MAX_SIZE 65536
+#define TSO_MAX_SIZE UINT_MAX
+ unsigned int tso_max_size;
u16 gso_max_segs;
+#define TSO_MAX_SEGS U16_MAX
+ u16 tso_max_segs;
#ifdef CONFIG_DCB
const struct dcbnl_rtnl_ops *dcbnl_ops;
@@ -2491,37 +2529,53 @@ static inline void *netdev_priv(const struct net_device *dev)
*/
#define NAPI_POLL_WEIGHT 64
+void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight);
+
/**
- * netif_napi_add - initialize a NAPI context
- * @dev: network device
- * @napi: NAPI context
- * @poll: polling function
- * @weight: default weight
+ * netif_napi_add() - initialize a NAPI context
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @weight: default weight
*
* netif_napi_add() must be used to initialize a NAPI context prior to calling
* *any* of the other NAPI-related functions.
*/
-void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
- int (*poll)(struct napi_struct *, int), int weight);
+static inline void
+netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
+{
+ netif_napi_add_weight(dev, napi, poll, weight);
+}
+
+static inline void
+netif_napi_add_tx_weight(struct net_device *dev,
+ struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int),
+ int weight)
+{
+ set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
+ netif_napi_add_weight(dev, napi, poll, weight);
+}
+
+#define netif_tx_napi_add netif_napi_add_tx_weight
/**
- * netif_tx_napi_add - initialize a NAPI context
- * @dev: network device
- * @napi: NAPI context
- * @poll: polling function
- * @weight: default weight
+ * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
*
* This variant of netif_napi_add() should be used from drivers using NAPI
* to exclusively poll a TX queue.
* This will avoid we add it into napi_hash[], thus polluting this hash table.
*/
-static inline void netif_tx_napi_add(struct net_device *dev,
+static inline void netif_napi_add_tx(struct net_device *dev,
struct napi_struct *napi,
- int (*poll)(struct napi_struct *, int),
- int weight)
+ int (*poll)(struct napi_struct *, int))
{
- set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state);
- netif_napi_add(dev, napi, poll, weight);
+ netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
}
/**
@@ -2932,10 +2986,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
-int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+static inline int dev_queue_xmit(struct sk_buff *skb)
+{
+ return __dev_queue_xmit(skb, NULL);
+}
+
+static inline int dev_queue_xmit_accel(struct sk_buff *skb,
+ struct net_device *sb_dev)
+{
+ return __dev_queue_xmit(skb, sb_dev);
+}
+
static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
int ret;
@@ -2968,7 +3032,6 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex);
struct net_device *__dev_get_by_index(struct net *net, int ifindex);
struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
struct net_device *dev_get_by_napi_id(unsigned int napi_id);
-int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_restart(struct net_device *dev);
@@ -3027,19 +3090,6 @@ static inline bool dev_has_header(const struct net_device *dev)
return dev->header_ops && dev->header_ops->create;
}
-#ifdef CONFIG_NET_FLOW_LIMIT
-#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */
-struct sd_flow_limit {
- u64 count;
- unsigned int num_buckets;
- unsigned int history_head;
- u16 history[FLOW_LIMIT_HISTORY];
- u8 buckets[];
-};
-
-extern int netdev_flow_limit_table_len;
-#endif /* CONFIG_NET_FLOW_LIMIT */
-
/*
* Incoming packets are placed on per-CPU queues
*/
@@ -3067,6 +3117,9 @@ struct softnet_data {
struct {
u16 recursion;
u8 more;
+#ifdef CONFIG_NET_EGRESS
+ u8 skip_txqueue;
+#endif
} xmit;
#ifdef CONFIG_RPS
/* input_queue_head should be written by cpu owning this struct,
@@ -3084,6 +3137,12 @@ struct softnet_data {
struct sk_buff_head input_pkt_queue;
struct napi_struct backlog;
+ /* Another possibly contended cache line */
+ spinlock_t defer_lock ____cacheline_aligned_in_smp;
+ int defer_count;
+ int defer_ipi_scheduled;
+ struct sk_buff *defer_list;
+ call_single_data_t defer_csd;
};
static inline void input_queue_head_incr(struct softnet_data *sd)
@@ -3763,7 +3822,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
struct netlink_ext_ack *extack);
void __dev_notify_flags(struct net_device *, unsigned int old_flags,
unsigned int gchanges);
-int dev_change_name(struct net_device *, const char *);
int dev_set_alias(struct net_device *, const char *, size_t);
int dev_get_alias(const struct net_device *, char *, size_t);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
@@ -3775,13 +3833,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net,
return __dev_change_net_namespace(dev, net, pat, 0);
}
int __dev_set_mtu(struct net_device *, int);
-int dev_validate_mtu(struct net_device *dev, int mtu,
- struct netlink_ext_ack *extack);
-int dev_set_mtu_ext(struct net_device *dev, int mtu,
- struct netlink_ext_ack *extack);
int dev_set_mtu(struct net_device *, int);
-int dev_change_tx_queue_len(struct net_device *, unsigned long);
-void dev_set_group(struct net_device *, int);
int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
struct netlink_ext_ack *extack);
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
@@ -3789,24 +3841,13 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack);
int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
-int dev_change_carrier(struct net_device *, bool new_carrier);
-int dev_get_phys_port_id(struct net_device *dev,
- struct netdev_phys_item_id *ppid);
-int dev_get_phys_port_name(struct net_device *dev,
- char *name, size_t len);
int dev_get_port_parent_id(struct net_device *dev,
struct netdev_phys_item_id *ppid, bool recurse);
bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
-int dev_change_proto_down(struct net_device *dev, bool proto_down);
-void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
- u32 value);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
-typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
-int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, int expected_fd, u32 flags);
int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
u8 dev_xdp_prog_count(struct net_device *dev);
u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
@@ -3868,6 +3909,7 @@ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \
DEV_CORE_STATS_INC(rx_dropped)
DEV_CORE_STATS_INC(tx_dropped)
DEV_CORE_STATS_INC(rx_nohandler)
+DEV_CORE_STATS_INC(rx_otherhost_dropped)
static __always_inline int ____dev_forward_skb(struct net_device *dev,
struct sk_buff *skb,
@@ -3888,12 +3930,6 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
bool dev_nit_active(struct net_device *dev);
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
-extern int netdev_budget;
-extern unsigned int netdev_budget_usecs;
-
-/* Called by rtnetlink.c:rtnl_unlock() */
-void netdev_run_todo(void);
-
static inline void __dev_put(struct net_device *dev)
{
if (dev) {
@@ -4010,10 +4046,7 @@ static inline void dev_replace_track(struct net_device *odev,
* called netif_lowerlayer_*() because they represent the state of any
* kind of lower layer not just hardware media.
*/
-
-void linkwatch_init_dev(struct net_device *dev);
void linkwatch_fire_event(struct net_device *dev);
-void linkwatch_forget_dev(struct net_device *dev);
/**
* netif_carrier_ok - test if carrier present
@@ -4459,9 +4492,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
int dev_addr_del(struct net_device *dev, const unsigned char *addr,
unsigned char addr_type);
-void dev_addr_flush(struct net_device *dev);
-int dev_addr_init(struct net_device *dev);
-void dev_addr_check(struct net_device *dev);
/* Functions used for unicast addresses handling */
int dev_uc_add(struct net_device *dev, const unsigned char *addr);
@@ -4551,7 +4581,6 @@ static inline void __dev_mc_unsync(struct net_device *dev,
/* Functions used for secondary unicast and multicast support */
void dev_set_rx_mode(struct net_device *dev);
-void __dev_set_rx_mode(struct net_device *dev);
int dev_set_promiscuity(struct net_device *dev, int inc);
int dev_set_allmulti(struct net_device *dev, int inc);
void netdev_state_change(struct net_device *dev);
@@ -4569,11 +4598,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
extern int netdev_max_backlog;
-extern int netdev_tstamp_prequeue;
-extern int netdev_unregister_timeout_secs;
-extern int weight_p;
-extern int dev_weight_rx_bias;
-extern int dev_weight_tx_bias;
extern int dev_rx_weight;
extern int dev_tx_weight;
extern int gro_normal_batch;
@@ -4761,11 +4785,17 @@ static inline void netdev_rx_csum_fault(struct net_device *dev,
void net_enable_timestamp(void);
void net_disable_timestamp(void);
-#ifdef CONFIG_PROC_FS
-int __init dev_proc_init(void);
-#else
-#define dev_proc_init() 0
-#endif
+static inline ktime_t netdev_get_tstamp(struct net_device *dev,
+ const struct skb_shared_hwtstamps *hwtstamps,
+ bool cycles)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_get_tstamp)
+ return ops->ndo_get_tstamp(dev, hwtstamps, cycles);
+
+ return hwtstamps->hwtstamp;
+}
static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
struct sk_buff *skb, struct net_device *dev,
@@ -4802,8 +4832,6 @@ extern const struct kobj_ns_type_operations net_ns_type_operations;
const char *netdev_drivername(const struct net_device *dev);
-void linkwatch_run_queue(void);
-
static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
netdev_features_t f2)
{
@@ -4889,26 +4917,10 @@ static inline bool netif_needs_gso(struct sk_buff *skb,
(skb->ip_summed != CHECKSUM_UNNECESSARY)));
}
-static inline void netif_set_gso_max_size(struct net_device *dev,
- unsigned int size)
-{
- /* dev->gso_max_size is read locklessly from sk_setup_caps() */
- WRITE_ONCE(dev->gso_max_size, size);
-}
-
-static inline void netif_set_gso_max_segs(struct net_device *dev,
- unsigned int segs)
-{
- /* dev->gso_max_segs is read locklessly from sk_setup_caps() */
- WRITE_ONCE(dev->gso_max_segs, segs);
-}
-
-static inline void netif_set_gro_max_size(struct net_device *dev,
- unsigned int size)
-{
- /* This pairs with the READ_ONCE() in skb_gro_receive() */
- WRITE_ONCE(dev->gro_max_size, size);
-}
+void netif_set_tso_max_size(struct net_device *dev, unsigned int size);
+void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
+void netif_inherit_tso_max(struct net_device *to,
+ const struct net_device *from);
static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
int pulled_hlen, u16 mac_offset,
@@ -5074,81 +5086,9 @@ static inline const char *netdev_reg_state(const struct net_device *dev)
return " (unknown)";
}
-__printf(3, 4) __cold
-void netdev_printk(const char *level, const struct net_device *dev,
- const char *format, ...);
-__printf(2, 3) __cold
-void netdev_emerg(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_alert(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_crit(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_err(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_warn(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_notice(const struct net_device *dev, const char *format, ...);
-__printf(2, 3) __cold
-void netdev_info(const struct net_device *dev, const char *format, ...);
-
-#define netdev_level_once(level, dev, fmt, ...) \
-do { \
- static bool __section(".data.once") __print_once; \
- \
- if (!__print_once) { \
- __print_once = true; \
- netdev_printk(level, dev, fmt, ##__VA_ARGS__); \
- } \
-} while (0)
-
-#define netdev_emerg_once(dev, fmt, ...) \
- netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
-#define netdev_alert_once(dev, fmt, ...) \
- netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
-#define netdev_crit_once(dev, fmt, ...) \
- netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
-#define netdev_err_once(dev, fmt, ...) \
- netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
-#define netdev_warn_once(dev, fmt, ...) \
- netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
-#define netdev_notice_once(dev, fmt, ...) \
- netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
-#define netdev_info_once(dev, fmt, ...) \
- netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
-
#define MODULE_ALIAS_NETDEV(device) \
MODULE_ALIAS("netdev-" device)
-#if defined(CONFIG_DYNAMIC_DEBUG) || \
- (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
-#define netdev_dbg(__dev, format, args...) \
-do { \
- dynamic_netdev_dbg(__dev, format, ##args); \
-} while (0)
-#elif defined(DEBUG)
-#define netdev_dbg(__dev, format, args...) \
- netdev_printk(KERN_DEBUG, __dev, format, ##args)
-#else
-#define netdev_dbg(__dev, format, args...) \
-({ \
- if (0) \
- netdev_printk(KERN_DEBUG, __dev, format, ##args); \
-})
-#endif
-
-#if defined(VERBOSE_DEBUG)
-#define netdev_vdbg netdev_dbg
-#else
-
-#define netdev_vdbg(dev, format, args...) \
-({ \
- if (0) \
- netdev_printk(KERN_DEBUG, dev, format, ##args); \
- 0; \
-})
-#endif
-
/*
* netdev_WARN() acts like dev_printk(), but with the key difference
* of using a WARN/WARN_ON to get the message out, including the
@@ -5162,74 +5102,6 @@ do { \
WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \
netdev_reg_state(dev), ##args)
-/* netif printk helpers, similar to netdev_printk */
-
-#define netif_printk(priv, type, level, dev, fmt, args...) \
-do { \
- if (netif_msg_##type(priv)) \
- netdev_printk(level, (dev), fmt, ##args); \
-} while (0)
-
-#define netif_level(level, priv, type, dev, fmt, args...) \
-do { \
- if (netif_msg_##type(priv)) \
- netdev_##level(dev, fmt, ##args); \
-} while (0)
-
-#define netif_emerg(priv, type, dev, fmt, args...) \
- netif_level(emerg, priv, type, dev, fmt, ##args)
-#define netif_alert(priv, type, dev, fmt, args...) \
- netif_level(alert, priv, type, dev, fmt, ##args)
-#define netif_crit(priv, type, dev, fmt, args...) \
- netif_level(crit, priv, type, dev, fmt, ##args)
-#define netif_err(priv, type, dev, fmt, args...) \
- netif_level(err, priv, type, dev, fmt, ##args)
-#define netif_warn(priv, type, dev, fmt, args...) \
- netif_level(warn, priv, type, dev, fmt, ##args)
-#define netif_notice(priv, type, dev, fmt, args...) \
- netif_level(notice, priv, type, dev, fmt, ##args)
-#define netif_info(priv, type, dev, fmt, args...) \
- netif_level(info, priv, type, dev, fmt, ##args)
-
-#if defined(CONFIG_DYNAMIC_DEBUG) || \
- (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
-#define netif_dbg(priv, type, netdev, format, args...) \
-do { \
- if (netif_msg_##type(priv)) \
- dynamic_netdev_dbg(netdev, format, ##args); \
-} while (0)
-#elif defined(DEBUG)
-#define netif_dbg(priv, type, dev, format, args...) \
- netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
-#else
-#define netif_dbg(priv, type, dev, format, args...) \
-({ \
- if (0) \
- netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
- 0; \
-})
-#endif
-
-/* if @cond then downgrade to debug, else print at @level */
-#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \
- do { \
- if (cond) \
- netif_dbg(priv, type, netdev, fmt, ##args); \
- else \
- netif_ ## level(priv, type, netdev, fmt, ##args); \
- } while (0)
-
-#if defined(VERBOSE_DEBUG)
-#define netif_vdbg netif_dbg
-#else
-#define netif_vdbg(priv, type, dev, format, args...) \
-({ \
- if (0) \
- netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
- 0; \
-})
-#endif
-
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 36ca2b5c2253..508f1149665b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -65,7 +65,7 @@ extern const int phy_basic_ports_array[3];
extern const int phy_fibre_port_array[1];
extern const int phy_all_ports_features_array[7];
extern const int phy_10_100_features_array[4];
-extern const int phy_basic_t1_features_array[2];
+extern const int phy_basic_t1_features_array[3];
extern const int phy_gbit_features_array[2];
extern const int phy_10gbit_features_array[1];
@@ -570,6 +570,7 @@ struct macsec_ops;
* @autoneg_complete: Flag auto negotiation of the link has completed
* @mdix: Current crossover
* @mdix_ctrl: User setting of crossover
+ * @pma_extable: Cached value of PMA/PMD Extended Abilities Register
* @interrupts: Flag interrupts have been enabled
* @interface: enum phy_interface_t value
* @skb: Netlink message for cable diagnostics
@@ -698,6 +699,8 @@ struct phy_device {
u8 mdix;
u8 mdix_ctrl;
+ int pma_extable;
+
void (*phy_link_change)(struct phy_device *phydev, bool up);
void (*adjust_link)(struct net_device *dev);
@@ -1611,11 +1614,14 @@ int genphy_c45_read_link(struct phy_device *phydev);
int genphy_c45_read_lpa(struct phy_device *phydev);
int genphy_c45_read_pma(struct phy_device *phydev);
int genphy_c45_pma_setup_forced(struct phy_device *phydev);
+int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev);
int genphy_c45_an_config_aneg(struct phy_device *phydev);
int genphy_c45_an_disable_aneg(struct phy_device *phydev);
int genphy_c45_read_mdix(struct phy_device *phydev);
int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
int genphy_c45_read_status(struct phy_device *phydev);
+int genphy_c45_baset1_read_status(struct phy_device *phydev);
int genphy_c45_config_aneg(struct phy_device *phydev);
int genphy_c45_loopback(struct phy_device *phydev, bool enable);
int genphy_c45_pma_resume(struct phy_device *phydev);
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 223781622b33..6d06896fc20d 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -160,11 +160,6 @@ struct phylink_mac_ops {
* clearing unsupported speeds and duplex settings. The port modes
* should not be cleared; phylink_set_port_modes() will help with this.
*
- * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX
- * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode
- * based on @state->advertising and/or @state->speed and update
- * @state->interface accordingly. See phylink_helper_basex_speed().
- *
* When @config->supported_interfaces has been set, phylink will iterate
* over the supported interfaces to determine the full capability of the
* MAC. The validation function must not print errors if @state->interface
@@ -579,7 +574,6 @@ int phylink_speed_up(struct phylink *pl);
#define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode)
void phylink_set_port_modes(unsigned long *bits);
-void phylink_helper_basex_speed(struct phylink_link_state *state);
void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state,
u16 bmsr, u16 lpa);
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 554454cb8693..92b44161408e 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -108,6 +108,32 @@ struct ptp_system_timestamp {
* @settime64: Set the current time on the hardware clock.
* parameter ts: Time value to set.
*
+ * @getcycles64: Reads the current free running cycle counter from the hardware
+ * clock.
+ * If @getcycles64 and @getcyclesx64 are not supported, then
+ * @gettime64 or @gettimex64 will be used as default
+ * implementation.
+ * parameter ts: Holds the result.
+ *
+ * @getcyclesx64: Reads the current free running cycle counter from the
+ * hardware clock and optionally also the system clock.
+ * If @getcycles64 and @getcyclesx64 are not supported, then
+ * @gettimex64 will be used as default implementation if
+ * available.
+ * parameter ts: Holds the PHC timestamp.
+ * parameter sts: If not NULL, it holds a pair of timestamps
+ * from the system clock. The first reading is made right before
+ * reading the lowest bits of the PHC timestamp and the second
+ * reading immediately follows that.
+ *
+ * @getcrosscycles: Reads the current free running cycle counter from the
+ * hardware clock and system clock simultaneously.
+ * If @getcycles64 and @getcyclesx64 are not supported, then
+ * @getcrosststamp will be used as default implementation if
+ * available.
+ * parameter cts: Contains timestamp (device,system) pair,
+ * where system time is realtime and monotonic.
+ *
* @enable: Request driver to enable or disable an ancillary feature.
* parameter request: Desired resource to enable or disable.
* parameter on: Caller passes one to enable or zero to disable.
@@ -155,6 +181,11 @@ struct ptp_clock_info {
int (*getcrosststamp)(struct ptp_clock_info *ptp,
struct system_device_crosststamp *cts);
int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts);
+ int (*getcycles64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
+ int (*getcyclesx64)(struct ptp_clock_info *ptp, struct timespec64 *ts,
+ struct ptp_system_timestamp *sts);
+ int (*getcrosscycles)(struct ptp_clock_info *ptp,
+ struct system_device_crosststamp *cts);
int (*enable)(struct ptp_clock_info *ptp,
struct ptp_clock_request *request, int on);
int (*verify)(struct ptp_clock_info *ptp, unsigned int pin,
@@ -321,6 +352,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp)
static inline int ptp_find_pin(struct ptp_clock *ptp,
enum ptp_pin_function func, unsigned int chan)
{ return -1; }
+static inline int ptp_find_pin_unlocked(struct ptp_clock *ptp,
+ enum ptp_pin_function func,
+ unsigned int chan)
+{ return -1; }
static inline int ptp_schedule_worker(struct ptp_clock *ptp,
unsigned long delay)
{ return -EOPNOTSUPP; }
@@ -349,17 +384,16 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index);
/**
* ptp_convert_timestamp() - convert timestamp to a ptp vclock time
*
- * @hwtstamps: skb_shared_hwtstamps structure pointer
+ * @hwtstamp: timestamp
* @vclock_index: phc index of ptp vclock.
*
* Returns converted timestamp, or 0 on error.
*/
-ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
- int vclock_index);
+ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index);
#else
static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
{ return 0; }
-static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps,
+static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp,
int vclock_index)
{ return 0; }
diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h
index 16752eca5cbd..90e3045b2dcb 100644
--- a/include/linux/qed/qed_fcoe_if.h
+++ b/include/linux/qed/qed_fcoe_if.h
@@ -76,7 +76,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev,
* @fill_dev_info: fills FCoE specific information
* @param cdev
* @param info
- * @return 0 on sucesss, otherwise error value.
+ * @return 0 on success, otherwise error value.
* @register_ops: register FCoE operations
* @param cdev
* @param ops - specified using qed_iscsi_cb_ops
@@ -96,7 +96,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev,
* connection.
* @param p_doorbell - qed will fill the address of the
* doorbell.
- * return 0 on sucesss, otherwise error value.
+ * return 0 on success, otherwise error value.
* @release_conn: release a previously acquired fcoe connection
* @param cdev
* @param handle - the connection handle.
diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h
index 494cdc3cd840..fbf7973ae9ba 100644
--- a/include/linux/qed/qed_iscsi_if.h
+++ b/include/linux/qed/qed_iscsi_if.h
@@ -133,7 +133,7 @@ struct qed_iscsi_cb_ops {
* @fill_dev_info: fills iSCSI specific information
* @param cdev
* @param info
- * @return 0 on sucesss, otherwise error value.
+ * @return 0 on success, otherwise error value.
* @register_ops: register iscsi operations
* @param cdev
* @param ops - specified using qed_iscsi_cb_ops
@@ -152,7 +152,7 @@ struct qed_iscsi_cb_ops {
* connection.
* @param p_doorbell - qed will fill the address of the
* doorbell.
- * @return 0 on sucesss, otherwise error value.
+ * @return 0 on success, otherwise error value.
* @release_conn: release a previously acquired iscsi connection
* @param cdev
* @param handle - the connection handle.
diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h
index 1d51df347560..bbfbfba51f37 100644
--- a/include/linux/qed/qed_nvmetcp_if.h
+++ b/include/linux/qed/qed_nvmetcp_if.h
@@ -132,7 +132,7 @@ struct nvmetcp_task_params {
* connection.
* @param p_doorbell - qed will fill the address of the
* doorbell.
- * @return 0 on sucesss, otherwise error value.
+ * @return 0 on success, otherwise error value.
* @release_conn: release a previously acquired nvmetcp connection
* @param cdev
* @param handle - the connection handle.
diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h
deleted file mode 100644
index 3604aee53796..000000000000
--- a/include/linux/qed/qed_nvmetcp_ip_services_if.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */
-/*
- * Copyright 2021 Marvell. All rights reserved.
- */
-
-#ifndef _QED_IP_SERVICES_IF_H
-#define _QED_IP_SERVICES_IF_H
-
-#include <linux/types.h>
-#include <net/route.h>
-#include <net/ip6_route.h>
-#include <linux/inetdevice.h>
-
-int qed_route_ipv4(struct sockaddr_storage *local_addr,
- struct sockaddr_storage *remote_addr,
- struct sockaddr *hardware_address,
- struct net_device **ndev);
-int qed_route_ipv6(struct sockaddr_storage *local_addr,
- struct sockaddr_storage *remote_addr,
- struct sockaddr *hardware_address,
- struct net_device **ndev);
-void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id);
-struct pci_dev *qed_validate_ndev(struct net_device *ndev);
-void qed_return_tcp_port(struct socket *sock);
-int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr,
- struct socket **sock, u16 *port);
-__be16 qed_get_in_port(struct sockaddr_storage *sa);
-
-#endif /* _QED_IP_SERVICES_IF_H */
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 7f970b16da3a..ae2c6a3cec5d 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -100,6 +100,7 @@ void net_dec_ingress_queue(void);
#ifdef CONFIG_NET_EGRESS
void net_inc_egress_queue(void);
void net_dec_egress_queue(void);
+void netdev_xmit_skip_txqueue(bool skip);
#endif
void rtnetlink_init(void);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 60820ab511d2..bd023dd38ae6 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -277,6 +277,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head,
extern struct list_head *seq_list_next(void *v, struct list_head *head,
loff_t *ppos);
+extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos);
+
/*
* Helpers for iteration over hlist_head-s in seq_files
*/
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a30cae8b0a5..da96f0d3e753 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -42,99 +42,114 @@
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <linux/netfilter/nf_conntrack_common.h>
#endif
+#include <net/net_debug.h>
-/* The interface for checksum offload between the stack and networking drivers
+/**
+ * DOC: skb checksums
+ *
+ * The interface for checksum offload between the stack and networking drivers
* is as follows...
*
- * A. IP checksum related features
+ * IP checksum related features
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* Drivers advertise checksum offload capabilities in the features of a device.
* From the stack's point of view these are capabilities offered by the driver.
* A driver typically only advertises features that it is capable of offloading
* to its device.
*
- * The checksum related features are:
- *
- * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one
- * IP (one's complement) checksum for any combination
- * of protocols or protocol layering. The checksum is
- * computed and set in a packet per the CHECKSUM_PARTIAL
- * interface (see below).
- *
- * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain
- * TCP or UDP packets over IPv4. These are specifically
- * unencapsulated packets of the form IPv4|TCP or
- * IPv4|UDP where the Protocol field in the IPv4 header
- * is TCP or UDP. The IPv4 header may contain IP options.
- * This feature cannot be set in features for a device
- * with NETIF_F_HW_CSUM also set. This feature is being
- * DEPRECATED (see below).
- *
- * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain
- * TCP or UDP packets over IPv6. These are specifically
- * unencapsulated packets of the form IPv6|TCP or
- * IPv6|UDP where the Next Header field in the IPv6
- * header is either TCP or UDP. IPv6 extension headers
- * are not supported with this feature. This feature
- * cannot be set in features for a device with
- * NETIF_F_HW_CSUM also set. This feature is being
- * DEPRECATED (see below).
- *
- * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload.
- * This flag is only used to disable the RX checksum
- * feature for a device. The stack will accept receive
- * checksum indication in packets received on a device
- * regardless of whether NETIF_F_RXCSUM is set.
- *
- * B. Checksumming of received packets by device. Indication of checksum
- * verification is set in skb->ip_summed. Possible values are:
- *
- * CHECKSUM_NONE:
+ * .. flat-table:: Checksum related device features
+ * :widths: 1 10
+ *
+ * * - %NETIF_F_HW_CSUM
+ * - The driver (or its device) is able to compute one
+ * IP (one's complement) checksum for any combination
+ * of protocols or protocol layering. The checksum is
+ * computed and set in a packet per the CHECKSUM_PARTIAL
+ * interface (see below).
+ *
+ * * - %NETIF_F_IP_CSUM
+ * - Driver (device) is only able to checksum plain
+ * TCP or UDP packets over IPv4. These are specifically
+ * unencapsulated packets of the form IPv4|TCP or
+ * IPv4|UDP where the Protocol field in the IPv4 header
+ * is TCP or UDP. The IPv4 header may contain IP options.
+ * This feature cannot be set in features for a device
+ * with NETIF_F_HW_CSUM also set. This feature is being
+ * DEPRECATED (see below).
+ *
+ * * - %NETIF_F_IPV6_CSUM
+ * - Driver (device) is only able to checksum plain
+ * TCP or UDP packets over IPv6. These are specifically
+ * unencapsulated packets of the form IPv6|TCP or
+ * IPv6|UDP where the Next Header field in the IPv6
+ * header is either TCP or UDP. IPv6 extension headers
+ * are not supported with this feature. This feature
+ * cannot be set in features for a device with
+ * NETIF_F_HW_CSUM also set. This feature is being
+ * DEPRECATED (see below).
+ *
+ * * - %NETIF_F_RXCSUM
+ * - Driver (device) performs receive checksum offload.
+ * This flag is only used to disable the RX checksum
+ * feature for a device. The stack will accept receive
+ * checksum indication in packets received on a device
+ * regardless of whether NETIF_F_RXCSUM is set.
+ *
+ * Checksumming of received packets by device
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * Indication of checksum verification is set in &sk_buff.ip_summed.
+ * Possible values are:
+ *
+ * - %CHECKSUM_NONE
*
* Device did not checksum this packet e.g. due to lack of capabilities.
* The packet contains full (though not verified) checksum in packet but
* not in skb->csum. Thus, skb->csum is undefined in this case.
*
- * CHECKSUM_UNNECESSARY:
+ * - %CHECKSUM_UNNECESSARY
*
* The hardware you're dealing with doesn't calculate the full checksum
- * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums
- * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY
- * if their checksums are okay. skb->csum is still undefined in this case
+ * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums
+ * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY
+ * if their checksums are okay. &sk_buff.csum is still undefined in this case
* though. A driver or device must never modify the checksum field in the
* packet even if checksum is verified.
*
- * CHECKSUM_UNNECESSARY is applicable to following protocols:
- * TCP: IPv6 and IPv4.
- * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
+ * %CHECKSUM_UNNECESSARY is applicable to following protocols:
+ *
+ * - TCP: IPv6 and IPv4.
+ * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a
* zero UDP checksum for either IPv4 or IPv6, the networking stack
* may perform further validation in this case.
- * GRE: only if the checksum is present in the header.
- * SCTP: indicates the CRC in SCTP header has been validated.
- * FCOE: indicates the CRC in FC frame has been validated.
+ * - GRE: only if the checksum is present in the header.
+ * - SCTP: indicates the CRC in SCTP header has been validated.
+ * - FCOE: indicates the CRC in FC frame has been validated.
*
- * skb->csum_level indicates the number of consecutive checksums found in
- * the packet minus one that have been verified as CHECKSUM_UNNECESSARY.
+ * &sk_buff.csum_level indicates the number of consecutive checksums found in
+ * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY.
* For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet
* and a device is able to verify the checksums for UDP (possibly zero),
- * GRE (checksum flag is set) and TCP, skb->csum_level would be set to
+ * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to
* two. If the device were only able to verify the UDP checksum and not
* GRE, either because it doesn't support GRE checksum or because GRE
* checksum is bad, skb->csum_level would be set to zero (TCP checksum is
* not considered in this case).
*
- * CHECKSUM_COMPLETE:
+ * - %CHECKSUM_COMPLETE
*
* This is the most generic way. The device supplied checksum of the _whole_
- * packet as seen by netif_rx() and fills in skb->csum. This means the
+ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the
* hardware doesn't need to parse L3/L4 headers to implement this.
*
* Notes:
+ *
* - Even if device supports only some protocols, but is able to produce
* skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY.
* - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols.
*
- * CHECKSUM_PARTIAL:
+ * - %CHECKSUM_PARTIAL
*
* A checksum is set up to be offloaded to a device as described in the
* output description for CHECKSUM_PARTIAL. This may occur on a packet
@@ -146,14 +161,18 @@
* packet that are after the checksum being offloaded are not considered to
* be verified.
*
- * C. Checksumming on transmit for non-GSO. The stack requests checksum offload
- * in the skb->ip_summed for a packet. Values are:
+ * Checksumming on transmit for non-GSO
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
- * CHECKSUM_PARTIAL:
+ * The stack requests checksum offload in the &sk_buff.ip_summed for a packet.
+ * Values are:
+ *
+ * - %CHECKSUM_PARTIAL
*
* The driver is required to checksum the packet as seen by hard_start_xmit()
- * from skb->csum_start up to the end, and to record/write the checksum at
- * offset skb->csum_start + skb->csum_offset. A driver may verify that the
+ * from &sk_buff.csum_start up to the end, and to record/write the checksum at
+ * offset &sk_buff.csum_start + &sk_buff.csum_offset.
+ * A driver may verify that the
* csum_start and csum_offset values are valid values given the length and
* offset of the packet, but it should not attempt to validate that the
* checksum refers to a legitimate transport layer checksum -- it is the
@@ -165,55 +184,66 @@
* checksum calculation to the device, or call skb_checksum_help (in the case
* that the device does not support offload for a particular checksum).
*
- * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of
- * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate
+ * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of
+ * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate
* checksum offload capability.
- * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based
+ * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based
* on network device checksumming capabilities: if a packet does not match
- * them, skb_checksum_help or skb_crc32c_help (depending on the value of
- * csum_not_inet, see item D.) is called to resolve the checksum.
+ * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of
+ * &sk_buff.csum_not_inet, see :ref:`crc`)
+ * is called to resolve the checksum.
*
- * CHECKSUM_NONE:
+ * - %CHECKSUM_NONE
*
* The skb was already checksummed by the protocol, or a checksum is not
* required.
*
- * CHECKSUM_UNNECESSARY:
+ * - %CHECKSUM_UNNECESSARY
*
* This has the same meaning as CHECKSUM_NONE for checksum offload on
* output.
*
- * CHECKSUM_COMPLETE:
+ * - %CHECKSUM_COMPLETE
+ *
* Not used in checksum output. If a driver observes a packet with this value
- * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set.
- *
- * D. Non-IP checksum (CRC) offloads
- *
- * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of
- * offloading the SCTP CRC in a packet. To perform this offload the stack
- * will set csum_start and csum_offset accordingly, set ip_summed to
- * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in
- * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c.
- * A driver that supports both IP checksum offload and SCTP CRC32c offload
- * must verify which offload is configured for a packet by testing the
- * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve
- * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1.
- *
- * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of
- * offloading the FCOE CRC in a packet. To perform this offload the stack
- * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset
- * accordingly. Note that there is no indication in the skbuff that the
- * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports
- * both IP checksum offload and FCOE CRC offload must verify which offload
- * is configured for a packet, presumably by inspecting packet headers.
- *
- * E. Checksumming on output with GSO.
- *
- * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload
+ * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set.
+ *
+ * .. _crc:
+ *
+ * Non-IP checksum (CRC) offloads
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * .. flat-table::
+ * :widths: 1 10
+ *
+ * * - %NETIF_F_SCTP_CRC
+ * - This feature indicates that a device is capable of
+ * offloading the SCTP CRC in a packet. To perform this offload the stack
+ * will set csum_start and csum_offset accordingly, set ip_summed to
+ * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication
+ * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c.
+ * A driver that supports both IP checksum offload and SCTP CRC32c offload
+ * must verify which offload is configured for a packet by testing the
+ * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to
+ * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1.
+ *
+ * * - %NETIF_F_FCOE_CRC
+ * - This feature indicates that a device is capable of offloading the FCOE
+ * CRC in a packet. To perform this offload the stack will set ip_summed
+ * to %CHECKSUM_PARTIAL and set csum_start and csum_offset
+ * accordingly. Note that there is no indication in the skbuff that the
+ * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports
+ * both IP checksum offload and FCOE CRC offload must verify which offload
+ * is configured for a packet, presumably by inspecting packet headers.
+ *
+ * Checksumming on output with GSO
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * In the case of a GSO packet (skb_is_gso() is true), checksum offload
* is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the
- * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as
+ * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as
* part of the GSO operation is implied. If a checksum is being offloaded
- * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and
+ * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and
* csum_offset are set to refer to the outermost checksum being offloaded
* (two offloaded checksums are possible with UDP encapsulation).
*/
@@ -381,6 +411,19 @@ enum skb_drop_reason {
* the ofo queue, corresponding to
* LINUX_MIB_TCPOFOMERGE
*/
+ SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to
+ * LINUX_MIB_PAWSESTABREJECTED
+ */
+ SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */
+ SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */
+ SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */
+ SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */
+ SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */
+ SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */
+ SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */
+ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */
+ SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */
+ SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */
SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */
SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by
* BPF_PROG_TYPE_CGROUP_SKB
@@ -408,11 +451,9 @@ enum skb_drop_reason {
*/
SKB_DROP_REASON_XDP, /* dropped by XDP in input path */
SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */
- SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle
- * the skb. For an etner packet,
- * this means that L3 protocol is
- * not supported
- */
+ SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented
+ * or not supported
+ */
SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation
* error
*/
@@ -444,9 +485,36 @@ enum skb_drop_reason {
SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented
* at tun/tap, e.g., check_filter()
*/
+ SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */
+ SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC
+ * 2211, such as a broadcasts
+ * ICMP_TIMESTAMP
+ */
+ SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding
+ * to IPSTATS_MIB_INADDRERRORS
+ */
+ SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding
+ * to IPSTATS_MIB_INADDRERRORS
+ */
+ SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed
+ * the MTU)
+ */
SKB_DROP_REASON_MAX,
};
+#define SKB_DR_INIT(name, reason) \
+ enum skb_drop_reason name = SKB_DROP_REASON_##reason
+#define SKB_DR(name) \
+ SKB_DR_INIT(name, NOT_SPECIFIED)
+#define SKB_DR_SET(name, reason) \
+ (name = SKB_DROP_REASON_##reason)
+#define SKB_DR_OR(name, reason) \
+ do { \
+ if (name == SKB_DROP_REASON_NOT_SPECIFIED || \
+ name == SKB_NOT_DROPPED_YET) \
+ SKB_DR_SET(name, reason); \
+ } while (0)
+
/* To allow 64K frame to be packed as single skb without frag_list we
* require 64K/PAGE_SIZE pages plus 1 additional page to allow for
* buffers which do not start on a page boundary.
@@ -551,8 +619,10 @@ static inline bool skb_frag_must_loop(struct page *p)
/**
* struct skb_shared_hwtstamps - hardware time stamps
- * @hwtstamp: hardware time stamp transformed into duration
- * since arbitrary point in time
+ * @hwtstamp: hardware time stamp transformed into duration
+ * since arbitrary point in time
+ * @netdev_data: address/cookie of network device driver used as
+ * reference to actual hardware time stamp
*
* Software time stamps generated by ktime_get_real() are stored in
* skb->tstamp.
@@ -564,7 +634,10 @@ static inline bool skb_frag_must_loop(struct page *p)
* &skb_shared_info. Use skb_hwtstamps() to get a pointer.
*/
struct skb_shared_hwtstamps {
- ktime_t hwtstamp;
+ union {
+ ktime_t hwtstamp;
+ void *netdev_data;
+ };
};
/* Definitions for tx_flags in struct skb_shared_info */
@@ -578,16 +651,24 @@ enum {
/* device driver is going to provide hardware time stamp */
SKBTX_IN_PROGRESS = 1 << 2,
+ /* generate hardware time stamp based on cycles if supported */
+ SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3,
+
/* generate wifi status information (where possible) */
SKBTX_WIFI_STATUS = 1 << 4,
+ /* determine hardware time stamp based on time or cycles */
+ SKBTX_HW_TSTAMP_NETDEV = 1 << 5,
+
/* generate software time stamp when entering packet scheduling */
SKBTX_SCHED_TSTAMP = 1 << 6,
};
#define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \
SKBTX_SCHED_TSTAMP)
-#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP)
+#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \
+ SKBTX_HW_TSTAMP_USE_CYCLES | \
+ SKBTX_ANY_SW_TSTAMP)
/* Definitions for flags in struct skb_shared_info */
enum {
@@ -647,20 +728,6 @@ struct ubuf_info {
int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
void mm_unaccount_pinned_pages(struct mmpin *mmp);
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size);
-struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
- struct ubuf_info *uarg);
-
-void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
-
-void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
- bool success);
-
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len);
-int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
- struct msghdr *msg, int len,
- struct ubuf_info *uarg);
-
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
*/
@@ -691,16 +758,32 @@ struct skb_shared_info {
skb_frag_t frags[MAX_SKB_FRAGS];
};
-/* We divide dataref into two halves. The higher 16 bits hold references
- * to the payload part of skb->data. The lower 16 bits hold references to
- * the entire skb->data. A clone of a headerless skb holds the length of
- * the header in skb->hdr_len.
- *
- * All users must obey the rule that the skb->data reference count must be
- * greater than or equal to the payload reference count.
- *
- * Holding a reference to the payload part means that the user does not
- * care about modifications to the header part of skb->data.
+/**
+ * DOC: dataref and headerless skbs
+ *
+ * Transport layers send out clones of payload skbs they hold for
+ * retransmissions. To allow lower layers of the stack to prepend their headers
+ * we split &skb_shared_info.dataref into two halves.
+ * The lower 16 bits count the overall number of references.
+ * The higher 16 bits indicate how many of the references are payload-only.
+ * skb_header_cloned() checks if skb is allowed to add / write the headers.
+ *
+ * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr
+ * (via __skb_header_release()). Any clone created from marked skb will get
+ * &sk_buff.hdr_len populated with the available headroom.
+ * If there's the only clone in existence it's able to modify the headroom
+ * at will. The sequence of calls inside the transport layer is::
+ *
+ * <alloc skb>
+ * skb_reserve()
+ * __skb_header_release()
+ * skb_clone()
+ * // send the clone down the stack
+ *
+ * This is not a very generic construct and it depends on the transport layers
+ * doing the right thing. In practice there's usually only one payload-only skb.
+ * Having multiple payload-only skbs with different lengths of hdr_len is not
+ * possible. The payload-only skbs should never leave their owner.
*/
#define SKB_DATAREF_SHIFT 16
#define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1)
@@ -765,6 +848,46 @@ typedef unsigned char *sk_buff_data_t;
#endif
/**
+ * DOC: Basic sk_buff geometry
+ *
+ * struct sk_buff itself is a metadata structure and does not hold any packet
+ * data. All the data is held in associated buffers.
+ *
+ * &sk_buff.head points to the main "head" buffer. The head buffer is divided
+ * into two parts:
+ *
+ * - data buffer, containing headers and sometimes payload;
+ * this is the part of the skb operated on by the common helpers
+ * such as skb_put() or skb_pull();
+ * - shared info (struct skb_shared_info) which holds an array of pointers
+ * to read-only data in the (page, offset, length) format.
+ *
+ * Optionally &skb_shared_info.frag_list may point to another skb.
+ *
+ * Basic diagram may look like this::
+ *
+ * ---------------
+ * | sk_buff |
+ * ---------------
+ * ,--------------------------- + head
+ * / ,----------------- + data
+ * / / ,----------- + tail
+ * | | | , + end
+ * | | | |
+ * v v v v
+ * -----------------------------------------------
+ * | headroom | data | tailroom | skb_shared_info |
+ * -----------------------------------------------
+ * + [page frag]
+ * + [page frag]
+ * + [page frag]
+ * + [page frag] ---------
+ * + frag_list --> | sk_buff |
+ * ---------
+ *
+ */
+
+/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
* @prev: Previous buffer in list
@@ -851,6 +974,7 @@ typedef unsigned char *sk_buff_data_t;
* delivery_time at egress.
* @napi_id: id of the NAPI struct this skb came from
* @sender_cpu: (aka @napi_id) source CPU in XPS
+ * @alloc_cpu: CPU which did the skb allocation.
* @secmark: security marking
* @mark: Generic packet mark
* @reserved_tailroom: (aka @mark) number of bytes of free space available
@@ -1043,6 +1167,7 @@ struct sk_buff {
unsigned int sender_cpu;
};
#endif
+ u16 alloc_cpu;
#ifdef CONFIG_NETWORK_SECMARK
__u32 secmark;
#endif
@@ -1284,6 +1409,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size);
struct sk_buff *build_skb(void *data, unsigned int frag_size);
struct sk_buff *build_skb_around(struct sk_buff *skb,
void *data, unsigned int frag_size);
+void skb_attempt_defer_free(struct sk_buff *skb);
struct sk_buff *napi_build_skb(void *data, unsigned int frag_size);
@@ -1639,6 +1765,27 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset)
}
#endif
+struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
+ struct ubuf_info *uarg);
+
+void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
+
+void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg,
+ bool success);
+
+int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *from, size_t length);
+
+static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
+ struct msghdr *msg, int len)
+{
+ return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+
+int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
+ struct msghdr *msg, int len,
+ struct ubuf_info *uarg);
+
/* Internal */
#define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
@@ -1922,8 +2069,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri)
}
/**
- * __skb_header_release - release reference to header
- * @skb: buffer to operate on
+ * __skb_header_release() - allow clones to use the headroom
+ * @skb: buffer to operate on
+ *
+ * See "DOC: dataref and headerless skbs".
*/
static inline void __skb_header_release(struct sk_buff *skb)
{
@@ -2752,6 +2901,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb)
static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
{
+ DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb));
return skb->head + skb->transport_header;
}
@@ -3836,8 +3986,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk,
struct sk_buff *__skb_recv_datagram(struct sock *sk,
struct sk_buff_head *sk_queue,
unsigned int flags, int *off, int *err);
-struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
- int *err);
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err);
__poll_t datagram_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int skb_copy_datagram_iter(const struct sk_buff *from, int offset,
@@ -3886,7 +4035,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features,
unsigned int offset);
struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
-int skb_ensure_writable(struct sk_buff *skb, int write_len);
+int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
int skb_vlan_pop(struct sk_buff *skb);
int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
@@ -4895,9 +5044,7 @@ static inline void skb_forward_csum(struct sk_buff *skb)
*/
static inline void skb_checksum_none_assert(const struct sk_buff *skb)
{
-#ifdef DEBUG
- BUG_ON(skb->ip_summed != CHECKSUM_NONE);
-#endif
+ DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE);
}
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h
new file mode 100644
index 000000000000..7e00cca06709
--- /dev/null
+++ b/include/linux/soc/mediatek/mtk_wed.h
@@ -0,0 +1,131 @@
+#ifndef __MTK_WED_H
+#define __MTK_WED_H
+
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
+#include <linux/regmap.h>
+#include <linux/pci.h>
+
+#define MTK_WED_TX_QUEUES 2
+
+struct mtk_wed_hw;
+struct mtk_wdma_desc;
+
+struct mtk_wed_ring {
+ struct mtk_wdma_desc *desc;
+ dma_addr_t desc_phys;
+ int size;
+
+ u32 reg_base;
+ void __iomem *wpdma;
+};
+
+struct mtk_wed_device {
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+ const struct mtk_wed_ops *ops;
+ struct device *dev;
+ struct mtk_wed_hw *hw;
+ bool init_done, running;
+ int wdma_idx;
+ int irq;
+
+ struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES];
+ struct mtk_wed_ring txfree_ring;
+ struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES];
+
+ struct {
+ int size;
+ void **pages;
+ struct mtk_wdma_desc *desc;
+ dma_addr_t desc_phys;
+ } buf_ring;
+
+ /* filled by driver: */
+ struct {
+ struct pci_dev *pci_dev;
+
+ u32 wpdma_phys;
+
+ u16 token_start;
+ unsigned int nbuf;
+
+ u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id);
+ int (*offload_enable)(struct mtk_wed_device *wed);
+ void (*offload_disable)(struct mtk_wed_device *wed);
+ } wlan;
+#endif
+};
+
+struct mtk_wed_ops {
+ int (*attach)(struct mtk_wed_device *dev);
+ int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring,
+ void __iomem *regs);
+ int (*txfree_ring_setup)(struct mtk_wed_device *dev,
+ void __iomem *regs);
+ void (*detach)(struct mtk_wed_device *dev);
+
+ void (*stop)(struct mtk_wed_device *dev);
+ void (*start)(struct mtk_wed_device *dev, u32 irq_mask);
+ void (*reset_dma)(struct mtk_wed_device *dev);
+
+ u32 (*reg_read)(struct mtk_wed_device *dev, u32 reg);
+ void (*reg_write)(struct mtk_wed_device *dev, u32 reg, u32 val);
+
+ u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask);
+ void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask);
+};
+
+extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops;
+
+static inline int
+mtk_wed_device_attach(struct mtk_wed_device *dev)
+{
+ int ret = -ENODEV;
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+ rcu_read_lock();
+ dev->ops = rcu_dereference(mtk_soc_wed_ops);
+ if (dev->ops)
+ ret = dev->ops->attach(dev);
+ else
+ rcu_read_unlock();
+
+ if (ret)
+ dev->ops = NULL;
+#endif
+
+ return ret;
+}
+
+#ifdef CONFIG_NET_MEDIATEK_SOC_WED
+#define mtk_wed_device_active(_dev) !!(_dev)->ops
+#define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev)
+#define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask)
+#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \
+ (_dev)->ops->tx_ring_setup(_dev, _ring, _regs)
+#define mtk_wed_device_txfree_ring_setup(_dev, _regs) \
+ (_dev)->ops->txfree_ring_setup(_dev, _regs)
+#define mtk_wed_device_reg_read(_dev, _reg) \
+ (_dev)->ops->reg_read(_dev, _reg)
+#define mtk_wed_device_reg_write(_dev, _reg, _val) \
+ (_dev)->ops->reg_write(_dev, _reg, _val)
+#define mtk_wed_device_irq_get(_dev, _mask) \
+ (_dev)->ops->irq_get(_dev, _mask)
+#define mtk_wed_device_irq_set_mask(_dev, _mask) \
+ (_dev)->ops->irq_set_mask(_dev, _mask)
+#else
+static inline bool mtk_wed_device_active(struct mtk_wed_device *dev)
+{
+ return false;
+}
+#define mtk_wed_device_detach(_dev) do {} while (0)
+#define mtk_wed_device_start(_dev, _mask) do {} while (0)
+#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV
+#define mtk_wed_device_reg_read(_dev, _reg) 0
+#define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0)
+#define mtk_wed_device_irq_get(_dev, _mask) 0
+#define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0)
+#endif
+
+#endif
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6f85f5d957ef..12085c9a8544 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -50,6 +50,9 @@ struct linger {
struct msghdr {
void *msg_name; /* ptr to socket address structure */
int msg_namelen; /* size of socket address structure */
+
+ int msg_inq; /* output, data left in socket */
+
struct iov_iter msg_iter; /* data */
/*
@@ -62,8 +65,9 @@ struct msghdr {
void __user *msg_control_user;
};
bool msg_control_is_user : 1;
- __kernel_size_t msg_controllen; /* ancillary data buffer length */
+ bool msg_get_inq : 1;/* return INQ after receive */
unsigned int msg_flags; /* flags on received message */
+ __kernel_size_t msg_controllen; /* ancillary data buffer length */
struct kiocb *msg_iocb; /* ptr to iocb for async requests */
};
diff --git a/include/linux/string.h b/include/linux/string.h
index b6572aeca2f5..61ec7e4f6311 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -252,6 +252,10 @@ static inline const char *kbasename(const char *path)
#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
#include <linux/fortify-string.h>
#endif
+#ifndef unsafe_memcpy
+#define unsafe_memcpy(dst, src, bytes, justification) \
+ memcpy(dst, src, bytes)
+#endif
void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
int pad);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 6353d6db69b2..80263f7cdb77 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -38,10 +38,10 @@ struct ctl_table_header;
struct ctl_dir;
/* Keep the same order as in fs/proc/proc_sysctl.c */
-#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0])
-#define SYSCTL_ZERO ((void *)&sysctl_vals[1])
-#define SYSCTL_ONE ((void *)&sysctl_vals[2])
-#define SYSCTL_TWO ((void *)&sysctl_vals[3])
+#define SYSCTL_ZERO ((void *)&sysctl_vals[0])
+#define SYSCTL_ONE ((void *)&sysctl_vals[1])
+#define SYSCTL_TWO ((void *)&sysctl_vals[2])
+#define SYSCTL_THREE ((void *)&sysctl_vals[3])
#define SYSCTL_FOUR ((void *)&sysctl_vals[4])
#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5])
#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6])
@@ -51,6 +51,7 @@ struct ctl_dir;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10])
+#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11])
extern const int sysctl_vals[];
diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h
index 809bccd08455..cc42db51bbba 100644
--- a/include/linux/usb/rndis_host.h
+++ b/include/linux/usb/rndis_host.h
@@ -197,6 +197,7 @@ struct rndis_keepalive_c { /* IN (optionally OUT) */
/* Flags for driver_info::data */
#define RNDIS_DRIVER_DATA_POLL_STATUS 1 /* poll status before control */
+#define RNDIS_DRIVER_DATA_DST_MAC_FIXUP 2 /* device ignores configured MAC address */
extern void rndis_status(struct usbnet *dev, struct urb *urb);
extern int
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 8336e86ce606..1b4d72d5e891 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -214,6 +214,7 @@ extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf)
extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *);
extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *);
extern void usbnet_cdc_status(struct usbnet *, struct urb *);
+extern int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb);
/* CDC and RNDIS support the same host-chosen packet filters for IN transfers */
#define DEFAULT_FILTER (USB_CDC_PACKET_TYPE_BROADCAST \
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3049cb69c025..9cf6870b526e 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -134,7 +134,8 @@ struct tc_action_ops {
(*get_psample_group)(const struct tc_action *a,
tc_action_priv_destructor *destructor);
int (*offload_act_setup)(struct tc_action *act, void *entry_data,
- u32 *index_inc, bool bind);
+ u32 *index_inc, bool bind,
+ struct netlink_ext_ack *extack);
};
struct tc_action_net {
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 69ef31cea582..fe7935be7dc4 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -265,6 +265,15 @@ enum {
* runtime suspend, because event filtering takes place there.
*/
HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL,
+
+ /*
+ * When this quirk is set, disables the use of
+ * HCI_OP_ENHANCED_SETUP_SYNC_CONN command to setup SCO connections.
+ *
+ * This quirk can be set before hci_register_dev is called or
+ * during the hdev->setup vendor callback.
+ */
+ HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN,
};
/* HCI device flags */
@@ -616,6 +625,7 @@ enum {
#define EIR_SSP_RAND_R192 0x0F /* Simple Pairing Randomizer R-192 */
#define EIR_DEVICE_ID 0x10 /* device ID */
#define EIR_APPEARANCE 0x19 /* Device appearance */
+#define EIR_SERVICE_DATA 0x16 /* Service Data */
#define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */
#define EIR_LE_ROLE 0x1C /* LE role */
#define EIR_SSP_HASH_C256 0x1D /* Simple Pairing Hash C-256 */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 62d7b81b1cb7..5a52a2018b56 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1495,8 +1495,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \
(hdev->commands[39] & 0x04))
-/* Use enhanced synchronous connection if command is supported */
-#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08)
+/* Use enhanced synchronous connection if command is supported and its quirk
+ * has not been set.
+ */
+#define enhanced_sync_conn_capable(dev) \
+ (((dev)->commands[29] & 0x08) && \
+ !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks))
/* Use ext scanning if set ext scan param and ext scan enable is supported */
#define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 68713388b617..6d02e12e4702 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1183,6 +1183,9 @@ struct cfg80211_mbssid_elems {
* Token (measurement type 11)
* @lci_len: LCI data length
* @civicloc_len: Civic location data length
+ * @he_bss_color: BSS Color settings
+ * @he_bss_color_valid: indicates whether bss color
+ * attribute is present in beacon data or not.
*/
struct cfg80211_beacon_data {
const u8 *head, *tail;
@@ -1202,6 +1205,8 @@ struct cfg80211_beacon_data {
size_t probe_resp_len;
size_t lci_len;
size_t civicloc_len;
+ struct cfg80211_he_bss_color he_bss_color;
+ bool he_bss_color_valid;
};
struct mac_address {
@@ -1292,7 +1297,6 @@ struct cfg80211_unsol_bcast_probe_resp {
* @sae_h2e_required: stations must support direct H2E technique in SAE
* @flags: flags, as defined in enum cfg80211_ap_settings_flags
* @he_obss_pd: OBSS Packet Detection settings
- * @he_bss_color: BSS Color settings
* @he_oper: HE operation IE (or %NULL if HE isn't enabled)
* @fils_discovery: FILS discovery transmission parameters
* @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters
@@ -1326,7 +1330,6 @@ struct cfg80211_ap_settings {
bool twt_responder;
u32 flags;
struct ieee80211_he_obss_pd he_obss_pd;
- struct cfg80211_he_bss_color he_bss_color;
struct cfg80211_fils_discovery fils_discovery;
struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp;
struct cfg80211_mbssid_config mbssid_config;
@@ -2735,6 +2738,7 @@ struct cfg80211_auth_request {
* userspace if this flag is set. Only applicable for cfg80211_connect()
* request (connect callback).
* @ASSOC_REQ_DISABLE_HE: Disable HE
+ * @ASSOC_REQ_DISABLE_EHT: Disable EHT
*/
enum cfg80211_assoc_req_flags {
ASSOC_REQ_DISABLE_HT = BIT(0),
@@ -2742,6 +2746,7 @@ enum cfg80211_assoc_req_flags {
ASSOC_REQ_USE_RRM = BIT(2),
CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3),
ASSOC_REQ_DISABLE_HE = BIT(4),
+ ASSOC_REQ_DISABLE_EHT = BIT(5),
};
/**
@@ -5549,8 +5554,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy)
* @conn_owner_nlportid: (private) connection owner socket port ID
* @disconnect_wk: (private) auto-disconnect work
* @disconnect_bssid: (private) the BSSID to use for auto-disconnect
- * @ibss_fixed: (private) IBSS is using fixed BSSID
- * @ibss_dfs_possible: (private) IBSS may change to a DFS channel
* @event_list: (private) list for internal event processing
* @event_lock: (private) lock for event list
* @owner_nlportid: (private) owner socket port ID
@@ -5599,9 +5602,6 @@ struct wireless_dev {
struct cfg80211_chan_def preset_chandef;
struct cfg80211_chan_def chandef;
- bool ibss_fixed;
- bool ibss_dfs_possible;
-
bool ps;
int ps_timeout;
@@ -8006,7 +8006,9 @@ int cfg80211_register_netdevice(struct net_device *dev);
*/
static inline void cfg80211_unregister_netdevice(struct net_device *dev)
{
+#if IS_ENABLED(CONFIG_CFG80211)
cfg80211_unregister_wdev(dev->ieee80211_ptr);
+#endif
}
/**
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 833672d6fbe4..d8d8719315fd 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -203,8 +203,8 @@ struct wpan_phy {
/* PHY depended MAC PIB values */
- /* 802.15.4 acronym: Tdsym in usec */
- u8 symbol_duration;
+ /* 802.15.4 acronym: Tdsym in nsec */
+ u32 symbol_duration;
/* lifs and sifs periods timing */
u16 lifs_period;
u16 sifs_period;
@@ -373,6 +373,7 @@ struct wpan_dev {
#define to_phy(_dev) container_of(_dev, struct wpan_phy, dev)
+#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN)
static inline int
wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
const struct ieee802154_addr *daddr,
@@ -383,6 +384,7 @@ wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len);
}
+#endif
struct wpan_phy *
wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size);
@@ -415,4 +417,6 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy)
return dev_name(&phy->dev);
}
+void ieee802154_configure_durations(struct wpan_phy *phy);
+
#endif /* __NET_CFG802154_H */
diff --git a/include/net/devlink.h b/include/net/devlink.h
index a30180c0988a..2a2a2a0c93f7 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -22,6 +22,7 @@
#include <linux/firmware.h>
struct devlink;
+struct devlink_linecard;
struct devlink_port_phys_attrs {
u32 port_number; /* Same value as "split group".
@@ -135,6 +136,7 @@ struct devlink_port {
struct mutex reporters_lock; /* Protects reporter_list */
struct devlink_rate *devlink_rate;
+ struct devlink_linecard *linecard;
};
struct devlink_port_new_attrs {
@@ -148,6 +150,40 @@ struct devlink_port_new_attrs {
sfnum_valid:1;
};
+/**
+ * struct devlink_linecard_ops - Linecard operations
+ * @provision: callback to provision the linecard slot with certain
+ * type of linecard. As a result of this operation,
+ * driver is expected to eventually (could be after
+ * the function call returns) call one of:
+ * devlink_linecard_provision_set()
+ * devlink_linecard_provision_fail()
+ * @unprovision: callback to unprovision the linecard slot. As a result
+ * of this operation, driver is expected to eventually
+ * (could be after the function call returns) call
+ * devlink_linecard_provision_clear()
+ * devlink_linecard_provision_fail()
+ * @same_provision: callback to ask the driver if linecard is already
+ * provisioned in the same way user asks this linecard to be
+ * provisioned.
+ * @types_count: callback to get number of supported types
+ * @types_get: callback to get next type in list
+ */
+struct devlink_linecard_ops {
+ int (*provision)(struct devlink_linecard *linecard, void *priv,
+ const char *type, const void *type_priv,
+ struct netlink_ext_ack *extack);
+ int (*unprovision)(struct devlink_linecard *linecard, void *priv,
+ struct netlink_ext_ack *extack);
+ bool (*same_provision)(struct devlink_linecard *linecard, void *priv,
+ const char *type, const void *type_priv);
+ unsigned int (*types_count)(struct devlink_linecard *linecard,
+ void *priv);
+ void (*types_get)(struct devlink_linecard *linecard,
+ void *priv, unsigned int index, const char **type,
+ const void **type_priv);
+};
+
struct devlink_sb_pool_info {
enum devlink_sb_pool_type pool_type;
u32 size;
@@ -1536,6 +1572,18 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
int devlink_rate_leaf_create(struct devlink_port *port, void *priv);
void devlink_rate_leaf_destroy(struct devlink_port *devlink_port);
void devlink_rate_nodes_destroy(struct devlink *devlink);
+void devlink_port_linecard_set(struct devlink_port *devlink_port,
+ struct devlink_linecard *linecard);
+struct devlink_linecard *
+devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index,
+ const struct devlink_linecard_ops *ops, void *priv);
+void devlink_linecard_destroy(struct devlink_linecard *linecard);
+void devlink_linecard_provision_set(struct devlink_linecard *linecard,
+ const char *type);
+void devlink_linecard_provision_clear(struct devlink_linecard *linecard);
+void devlink_linecard_provision_fail(struct devlink_linecard *linecard);
+void devlink_linecard_activate(struct devlink_linecard *linecard);
+void devlink_linecard_deactivate(struct devlink_linecard *linecard);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 934958fda962..14f07275852b 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -579,6 +579,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p)
dsa_switch_for_each_port((_dp), (_ds)) \
if (dsa_port_is_cpu((_dp)))
+#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \
+ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \
+ if (dsa_port_is_cpu((_dp)))
+
static inline u32 dsa_user_ports(struct dsa_switch *ds)
{
struct dsa_port *dp;
@@ -590,6 +594,17 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds)
return mask;
}
+static inline u32 dsa_cpu_ports(struct dsa_switch *ds)
+{
+ struct dsa_port *cpu_dp;
+ u32 mask = 0;
+
+ dsa_switch_for_each_cpu_port(cpu_dp, ds)
+ mask |= BIT(cpu_dp->index);
+
+ return mask;
+}
+
/* Return the local port used to reach an arbitrary switch device */
static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device)
{
@@ -792,7 +807,7 @@ struct dsa_switch_ops {
enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
int port,
enum dsa_tag_protocol mprot);
- int (*change_tag_protocol)(struct dsa_switch *ds, int port,
+ int (*change_tag_protocol)(struct dsa_switch *ds,
enum dsa_tag_protocol proto);
/*
* Method for switch drivers to connect to the tagging protocol driver
@@ -967,6 +982,8 @@ struct dsa_switch_ops {
int (*port_bridge_flags)(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack);
+ void (*port_set_host_flood)(struct dsa_switch *ds, int port,
+ bool uc, bool mc);
/*
* VLAN support
@@ -1239,12 +1256,6 @@ struct dsa_switch_driver {
struct net_device *dsa_dev_to_net_device(struct device *dev);
-typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port,
- const unsigned char *addr, u16 vid,
- struct dsa_db db);
-
-int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb);
-int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb);
bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid,
struct dsa_db db);
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 9f65f1bfbd24..a4c6057c7097 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -253,6 +253,14 @@ struct flow_dissector_key_hash {
u32 hash;
};
+/**
+ * struct flow_dissector_key_num_of_vlans:
+ * @num_of_vlans: num_of_vlans value
+ */
+struct flow_dissector_key_num_of_vlans {
+ u8 num_of_vlans;
+};
+
enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
@@ -282,6 +290,7 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */
FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */
FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */
+ FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */
FLOW_DISSECTOR_KEY_MAX,
};
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 4cfdef6ca4f6..c8490729b4ae 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -64,6 +64,14 @@ struct inet6_ifaddr {
struct hlist_node addr_lst;
struct list_head if_list;
+ /*
+ * Used to safely traverse idev->addr_list in process context
+ * if the idev->lock needed to protect idev->addr_list cannot be held.
+ * In that case, add the items to this list temporarily and iterate
+ * without holding idev->lock.
+ * See addrconf_ifdown and dev_forward_change.
+ */
+ struct list_head if_list_aux;
struct list_head tmp_list;
struct inet6_ifaddr *ifpub;
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 81b965953036..f259e1ae14ba 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -103,15 +103,25 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
const int dif);
int inet6_hash(struct sock *sk);
-#endif /* IS_ENABLED(CONFIG_IPV6) */
-#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \
- (((__sk)->sk_portpair == (__ports)) && \
- ((__sk)->sk_family == AF_INET6) && \
- ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
- ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
- (((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
- net_eq(sock_net(__sk), (__net)))
+static inline bool inet6_match(struct net *net, const struct sock *sk,
+ const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ const __portpair ports,
+ const int dif, const int sdif)
+{
+ int bound_dev_if;
+
+ if (!net_eq(sock_net(sk), net) ||
+ sk->sk_family != AF_INET6 ||
+ sk->sk_portpair != ports ||
+ !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
+ !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+ return false;
+
+ bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+ return bound_dev_if == dif || bound_dev_if == sdif;
+}
+#endif /* IS_ENABLED(CONFIG_IPV6) */
#endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3908296d103f..077cd730ce2f 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -25,6 +25,7 @@
#undef INET_CSK_CLEAR_TIMERS
struct inet_bind_bucket;
+struct inet_bind2_bucket;
struct tcp_congestion_ops;
/*
@@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops {
*
* @icsk_accept_queue: FIFO of established children
* @icsk_bind_hash: Bind node
+ * @icsk_bind2_hash: Bind node in the bhash2 table
* @icsk_timeout: Timeout
* @icsk_retransmit_timer: Resend (no ack)
* @icsk_rto: Retransmit timeout
@@ -66,7 +68,6 @@ struct inet_connection_sock_af_ops {
* @icsk_ulp_ops Pluggable ULP control hook
* @icsk_ulp_data ULP private data
* @icsk_clean_acked Clean acked data hook
- * @icsk_listen_portaddr_node hash to the portaddr listener hashtable
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
@@ -84,6 +85,7 @@ struct inet_connection_sock {
struct inet_sock icsk_inet;
struct request_sock_queue icsk_accept_queue;
struct inet_bind_bucket *icsk_bind_hash;
+ struct inet_bind2_bucket *icsk_bind2_hash;
unsigned long icsk_timeout;
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
@@ -96,7 +98,6 @@ struct inet_connection_sock {
const struct tcp_ulp_ops *icsk_ulp_ops;
void __rcu *icsk_ulp_data;
void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
- struct hlist_node icsk_listen_portaddr_node;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:5,
icsk_ca_initialized:1,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 98e1ec1a14f0..a0887b70967b 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -90,11 +90,32 @@ struct inet_bind_bucket {
struct hlist_head owners;
};
+struct inet_bind2_bucket {
+ possible_net_t ib_net;
+ int l3mdev;
+ unsigned short port;
+ union {
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr v6_rcv_saddr;
+#endif
+ __be32 rcv_saddr;
+ };
+ /* Node in the inet2_bind_hashbucket chain */
+ struct hlist_node node;
+ /* List of sockets hashed to this bucket */
+ struct hlist_head owners;
+};
+
static inline struct net *ib_net(struct inet_bind_bucket *ib)
{
return read_pnet(&ib->ib_net);
}
+static inline struct net *ib2_net(struct inet_bind2_bucket *ib)
+{
+ return read_pnet(&ib->ib_net);
+}
+
#define inet_bind_bucket_for_each(tb, head) \
hlist_for_each_entry(tb, head, node)
@@ -103,6 +124,15 @@ struct inet_bind_hashbucket {
struct hlist_head chain;
};
+/* This is synchronized using the inet_bind_hashbucket's spinlock.
+ * Instead of having separate spinlocks, the inet_bind2_hashbucket can share
+ * the inet_bind_hashbucket's given that in every case where the bhash2 table
+ * is useful, a lookup in the bhash table also occurs.
+ */
+struct inet_bind2_hashbucket {
+ struct hlist_head chain;
+};
+
/* Sockets can be hashed in established or listening table.
* We must use different 'nulls' end-of-chain value for all hash buckets :
* A socket might transition from ESTABLISH to LISTEN state without
@@ -111,11 +141,7 @@ struct inet_bind_hashbucket {
#define LISTENING_NULLS_BASE (1U << 29)
struct inet_listen_hashbucket {
spinlock_t lock;
- unsigned int count;
- union {
- struct hlist_head head;
- struct hlist_nulls_head nulls_head;
- };
+ struct hlist_nulls_head nulls_head;
};
/* This is for listening sockets, thus all sockets which possess wildcards. */
@@ -138,37 +164,19 @@ struct inet_hashinfo {
*/
struct kmem_cache *bind_bucket_cachep;
struct inet_bind_hashbucket *bhash;
+ /* The 2nd binding table hashed by port and address.
+ * This is used primarily for expediting the resolution of bind
+ * conflicts.
+ */
+ struct kmem_cache *bind2_bucket_cachep;
+ struct inet_bind2_hashbucket *bhash2;
unsigned int bhash_size;
/* The 2nd listener table hashed by local port and address */
unsigned int lhash2_mask;
struct inet_listen_hashbucket *lhash2;
-
- /* All the above members are written once at bootup and
- * never written again _or_ are predominantly read-access.
- *
- * Now align to a new cache line as all the following members
- * might be often dirty.
- */
- /* All sockets in TCP_LISTEN state will be in listening_hash.
- * This is the only table where wildcard'd TCP sockets can
- * exist. listening_hash is only hashed by local port number.
- * If lhash2 is initialized, the same socket will also be hashed
- * to lhash2 by port and address.
- */
- struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE]
- ____cacheline_aligned_in_smp;
};
-#define inet_lhash2_for_each_icsk_continue(__icsk) \
- hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node)
-
-#define inet_lhash2_for_each_icsk(__icsk, list) \
- hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node)
-
-#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \
- hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node)
-
static inline struct inet_listen_hashbucket *
inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash)
{
@@ -221,32 +229,50 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
-static inline u32 inet_bhashfn(const struct net *net, const __u16 lport,
- const u32 bhash_size)
+static inline bool check_bind_bucket_match(struct inet_bind_bucket *tb,
+ struct net *net,
+ const unsigned short port,
+ int l3mdev)
{
- return (lport + net_hash_mix(net)) & (bhash_size - 1);
+ return net_eq(ib_net(tb), net) && tb->port == port &&
+ tb->l3mdev == l3mdev;
}
-void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
- const unsigned short snum);
+struct inet_bind2_bucket *
+inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net,
+ struct inet_bind2_hashbucket *head,
+ const unsigned short port, int l3mdev,
+ const struct sock *sk);
-/* These can have wildcards, don't try too hard. */
-static inline u32 inet_lhashfn(const struct net *net, const unsigned short num)
-{
- return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);
-}
+void inet_bind2_bucket_destroy(struct kmem_cache *cachep,
+ struct inet_bind2_bucket *tb);
+
+struct inet_bind2_bucket *
+inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net,
+ const unsigned short port, int l3mdev,
+ struct sock *sk,
+ struct inet_bind2_hashbucket **head);
-static inline int inet_sk_listen_hashfn(const struct sock *sk)
+bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb,
+ struct net *net,
+ const unsigned short port,
+ int l3mdev,
+ const struct sock *sk);
+
+static inline u32 inet_bhashfn(const struct net *net, const __u16 lport,
+ const u32 bhash_size)
{
- return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num);
+ return (lport + net_hash_mix(net)) & (bhash_size - 1);
}
+void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
+ struct inet_bind2_bucket *tb2, const unsigned short snum);
+
/* Caller must disable local BH processing. */
int __inet_inherit_port(const struct sock *sk, struct sock *child);
void inet_put_port(struct sock *sk);
-void inet_hashinfo_init(struct inet_hashinfo *h);
void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
unsigned long numentries, int scale,
unsigned long low_limit,
@@ -295,7 +321,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport)))
#endif
-#if (BITS_PER_LONG == 64)
#ifdef __BIG_ENDIAN
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
const __addrpair __name = (__force __addrpair) ( \
@@ -307,24 +332,22 @@ static inline struct sock *inet_lookup_listener(struct net *net,
(((__force __u64)(__be32)(__daddr)) << 32) | \
((__force __u64)(__be32)(__saddr)))
#endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
- (((__sk)->sk_portpair == (__ports)) && \
- ((__sk)->sk_addrpair == (__cookie)) && \
- (((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
- net_eq(sock_net(__sk), (__net)))
-#else /* 32-bit arch */
-#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
- const int __name __deprecated __attribute__((unused))
-
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
- (((__sk)->sk_portpair == (__ports)) && \
- ((__sk)->sk_daddr == (__saddr)) && \
- ((__sk)->sk_rcv_saddr == (__daddr)) && \
- (((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
- net_eq(sock_net(__sk), (__net)))
-#endif /* 64-bit arch */
+
+static inline bool inet_match(struct net *net, const struct sock *sk,
+ const __addrpair cookie, const __portpair ports,
+ int dif, int sdif)
+{
+ int bound_dev_if;
+
+ if (!net_eq(sock_net(sk), net) ||
+ sk->sk_portpair != ports ||
+ sk->sk_addrpair != cookie)
+ return false;
+
+ /* Paired with WRITE_ONCE() from sock_bindtoindex_locked() */
+ bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
+ return bound_dev_if == dif || bound_dev_if == sdif;
+}
/* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
* not check it for lookups anymore, thanks Alexey. -DaveM
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 234d70ae5f4c..c1b5dcd6597c 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -116,14 +116,15 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
static inline int inet_request_bound_dev_if(const struct sock *sk,
struct sk_buff *skb)
{
+ int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
#ifdef CONFIG_NET_L3_MASTER_DEV
struct net *net = sock_net(sk);
- if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
+ if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
#endif
- return sk->sk_bound_dev_if;
+ return bound_dev_if;
}
static inline int inet_sk_bound_l3mdev(const struct sock *sk)
diff --git a/include/net/ip.h b/include/net/ip.h
index 0161137914cf..26fffda78cca 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -94,7 +94,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm->sockc.mark = inet->sk.sk_mark;
ipcm->sockc.tsflags = inet->sk.sk_tsflags;
- ipcm->oif = inet->sk.sk_bound_dev_if;
+ ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
}
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 6a82bcb8813b..a378eff827c7 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -212,7 +212,7 @@ struct fib_rt_info {
u32 tb_id;
__be32 dst;
int dst_len;
- u8 tos;
+ dscp_t dscp;
u8 type;
u8 offload:1,
trap:1,
@@ -225,7 +225,7 @@ struct fib_entry_notifier_info {
u32 dst;
int dst_len;
struct fib_info *fi;
- u8 tos;
+ dscp_t dscp;
u8 type;
u32 tb_id;
};
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 213612f1680c..5b38bf1a586b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -151,6 +151,17 @@ struct frag_hdr {
__be32 identification;
};
+/*
+ * Jumbo payload option, as described in RFC 2675 2.
+ */
+struct hop_jumbo_hdr {
+ u8 nexthdr;
+ u8 hdrlen;
+ u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */
+ u8 tlv_len; /* 4 */
+ __be32 jumbo_payload_len;
+};
+
#define IP6_MF 0x0001
#define IP6_OFFSET 0xFFF8
@@ -456,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
struct ipv6_txoptions *opt);
+/* This helper is specialized for BIG TCP needs.
+ * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header.
+ * It assumes headers are already in skb->head.
+ * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there.
+ */
+static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb)
+{
+ const struct hop_jumbo_hdr *jhdr;
+ const struct ipv6hdr *nhdr;
+
+ if (likely(skb->len <= GRO_LEGACY_MAX_SIZE))
+ return 0;
+
+ if (skb->protocol != htons(ETH_P_IPV6))
+ return 0;
+
+ if (skb_network_offset(skb) +
+ sizeof(struct ipv6hdr) +
+ sizeof(struct hop_jumbo_hdr) > skb_headlen(skb))
+ return 0;
+
+ nhdr = ipv6_hdr(skb);
+
+ if (nhdr->nexthdr != NEXTHDR_HOP)
+ return 0;
+
+ jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1);
+ if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 ||
+ jhdr->nexthdr != IPPROTO_TCP)
+ return 0;
+ return jhdr->nexthdr;
+}
+
static inline bool ipv6_accept_ra(struct inet6_dev *idev)
{
/* If forwarding is enabled, RA are not accepted unless the special
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 382ebb862ea8..ebadb2103968 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -514,7 +514,6 @@ struct ieee80211_fils_discovery {
* to that BSS) that can change during the lifetime of the BSS.
*
* @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
- * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK
* @uora_exists: is the UORA element advertised by AP
* @ack_enabled: indicates support to receive a multi-TID that solicits either
* ACK, BACK or both
@@ -1144,20 +1143,41 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info)
return info->tx_time_est << 2;
}
+/***
+ * struct ieee80211_rate_status - mrr stage for status path
+ *
+ * This struct is used in struct ieee80211_tx_status to provide drivers a
+ * dynamic way to report about used rates and power levels per packet.
+ *
+ * @rate_idx The actual used rate.
+ * @try_count How often the rate was tried.
+ * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the
+ * corresponding wifi hardware. The idx shall point to the power level
+ * that was used when sending the packet.
+ */
+struct ieee80211_rate_status {
+ struct rate_info rate_idx;
+ u8 try_count;
+ u8 tx_power_idx;
+};
+
/**
* struct ieee80211_tx_status - extended tx status info for rate control
*
* @sta: Station that the packet was transmitted for
* @info: Basic tx status information
* @skb: Packet skb (can be NULL if not provided by the driver)
- * @rate: The TX rate that was used when sending the packet
+ * @rates: Mrr stages that were used when sending the packet
+ * @n_rates: Number of mrr stages (count of instances for @rates)
* @free_list: list where processed skbs are stored to be free'd by the driver
*/
struct ieee80211_tx_status {
struct ieee80211_sta *sta;
struct ieee80211_tx_info *info;
struct sk_buff *skb;
- struct rate_info *rate;
+ struct ieee80211_rate_status *rates;
+ u8 n_rates;
+
struct list_head *free_list;
};
@@ -1201,9 +1221,9 @@ static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb
* in the TX status but the rate control information (it does clear
* the count since you need to fill that in anyway).
*
- * NOTE: You can only use this function if you do NOT use
- * info->driver_data! Use info->rate_driver_data
- * instead if you need only the less space that allows.
+ * NOTE: While the rates array is kept intact, this will wipe all of the
+ * driver_data fields in info, so it's up to the driver to restore
+ * any fields it needs after calling this helper.
*/
static inline void
ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
@@ -1701,7 +1721,7 @@ enum ieee80211_offload_flags {
* these need to be set (or cleared) when the interface is added
* or, if supported by the driver, the interface type is changed
* at runtime, mac80211 will never touch this field
- * @offloaad_flags: hardware offload capabilities/flags for this interface.
+ * @offload_flags: hardware offload capabilities/flags for this interface.
* These are initialized by mac80211 before calling .add_interface,
* .change_interface or .update_vif_offload and updated by the driver
* within these ops, based on supported features or runtime change
@@ -2056,6 +2076,45 @@ struct ieee80211_sta_txpwr {
enum nl80211_tx_power_setting type;
};
+#define MAX_STA_LINKS 15
+
+/**
+ * struct ieee80211_link_sta - station Link specific info
+ * All link specific info for a STA link for a non MLD STA(single)
+ * or a MLD STA(multiple entries) are stored here.
+ *
+ * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr
+ * in ieee80211_sta. For MLO Link STA this addr can be same or different
+ * from addr in ieee80211_sta (representing MLD STA addr)
+ * @supp_rates: Bitmap of supported rates
+ * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
+ * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
+ * @he_cap: HE capabilities of this STA
+ * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities
+ * @eht_cap: EHT capabilities of this STA
+ * @bandwidth: current bandwidth the station can receive with
+ * @rx_nss: in HT/VHT, the maximum number of spatial streams the
+ * station can receive at the moment, changed by operating mode
+ * notifications and capabilities. The value is only valid after
+ * the station moves to associated state.
+ * @txpwr: the station tx power configuration
+ *
+ */
+struct ieee80211_link_sta {
+ u8 addr[ETH_ALEN];
+
+ u32 supp_rates[NUM_NL80211_BANDS];
+ struct ieee80211_sta_ht_cap ht_cap;
+ struct ieee80211_sta_vht_cap vht_cap;
+ struct ieee80211_sta_he_cap he_cap;
+ struct ieee80211_he_6ghz_capa he_6ghz_capa;
+ struct ieee80211_sta_eht_cap eht_cap;
+
+ u8 rx_nss;
+ enum ieee80211_sta_rx_bandwidth bandwidth;
+ struct ieee80211_sta_txpwr txpwr;
+};
+
/**
* struct ieee80211_sta - station table entry
*
@@ -2065,15 +2124,11 @@ struct ieee80211_sta_txpwr {
* either be protected by rcu_read_lock() explicitly or implicitly,
* or you must take good care to not use such a pointer after a
* call to your sta_remove callback that removed it.
+ * This also represents the MLD STA in case of MLO association
+ * and holds pointers to various link STA's
*
* @addr: MAC address
* @aid: AID we assigned to the station if we're an AP
- * @supp_rates: Bitmap of supported rates (per band)
- * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
- * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
- * @he_cap: HE capabilities of this STA
- * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities
- * @eht_cap: EHT capabilities of this STA
* @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU
* that this station is allowed to transmit to us.
* Can be modified by driver.
@@ -2085,11 +2140,6 @@ struct ieee80211_sta_txpwr {
* if wme is supported. The bits order is like in
* IEEE80211_WMM_IE_STA_QOSINFO_AC_*.
* @max_sp: max Service Period. Only valid if wme is supported.
- * @bandwidth: current bandwidth the station can receive with
- * @rx_nss: in HT/VHT, the maximum number of spatial streams the
- * station can receive at the moment, changed by operating mode
- * notifications and capabilities. The value is only valid after
- * the station moves to associated state.
* @smps_mode: current SMPS mode (off, static or dynamic)
* @rates: rate control selection table
* @tdls: indicates whether the STA is a TDLS peer
@@ -2102,25 +2152,28 @@ struct ieee80211_sta_txpwr {
* @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not.
* @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control.
* @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID
- * @txpwr: the station tx power configuration
* @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that
* the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames
+ * @multi_link_sta: Identifies if this sta is a MLD STA
+ * @deflink: This holds the default link STA information, for non MLO STA all link
+ * specific STA information is accessed through @deflink or through
+ * link[0] which points to address of @deflink. For MLO Link STA
+ * the first added link STA will point to deflink.
+ * @link: reference to Link Sta entries. For Non MLO STA, except 1st link,
+ * i.e link[0] all links would be assigned to NULL by default and
+ * would access link information via @deflink or link[0]. For MLO
+ * STA, first link STA being added will point its link pointer to
+ * @deflink address and remaining would be allocated and the address
+ * would be assigned to link[link_id] where link_id is the id assigned
+ * by the AP.
*/
struct ieee80211_sta {
- u32 supp_rates[NUM_NL80211_BANDS];
u8 addr[ETH_ALEN];
u16 aid;
- struct ieee80211_sta_ht_cap ht_cap;
- struct ieee80211_sta_vht_cap vht_cap;
- struct ieee80211_sta_he_cap he_cap;
- struct ieee80211_he_6ghz_capa he_6ghz_capa;
- struct ieee80211_sta_eht_cap eht_cap;
u16 max_rx_aggregation_subframes;
bool wme;
u8 uapsd_queues;
u8 max_sp;
- u8 rx_nss;
- enum ieee80211_sta_rx_bandwidth bandwidth;
enum ieee80211_smps_mode smps_mode;
struct ieee80211_sta_rates __rcu *rates;
bool tdls;
@@ -2147,10 +2200,13 @@ struct ieee80211_sta {
bool support_p2p_ps;
u16 max_rc_amsdu_len;
u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS];
- struct ieee80211_sta_txpwr txpwr;
struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1];
+ bool multi_link_sta;
+ struct ieee80211_link_sta deflink;
+ struct ieee80211_link_sta *link[MAX_STA_LINKS];
+
/* must be last */
u8 drv_priv[] __aligned(sizeof(void *));
};
@@ -2434,6 +2490,9 @@ struct ieee80211_txq {
* usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to
* the stack.
*
+ * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color
+ * collision detection and doesn't need it in software.
+ *
* @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
*/
enum ieee80211_hw_flags {
@@ -2489,6 +2548,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD,
IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD,
IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP,
+ IEEE80211_HW_DETECTS_COLOR_COLLISION,
/* keep last, obviously */
NUM_IEEE80211_HW_FLAGS
@@ -2618,6 +2678,12 @@ enum ieee80211_hw_flags {
* refilling deficit of each TXQ.
*
* @max_mtu: the max mtu could be set.
+ *
+ * @tx_power_levels: a list of power levels supported by the wifi hardware.
+ * The power levels can be specified either as integer or fractions.
+ * The power level at idx 0 shall be the maximum positive power level.
+ *
+ * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list.
*/
struct ieee80211_hw {
struct ieee80211_conf conf;
@@ -2656,6 +2722,8 @@ struct ieee80211_hw {
u8 tx_sk_pacing_shift;
u8 weight_multiplier;
u32 max_mtu;
+ const s8 *tx_power_levels;
+ u8 max_txpwr_levels_idx;
};
static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw,
@@ -6367,7 +6435,7 @@ static inline int rate_supported(struct ieee80211_sta *sta,
enum nl80211_band band,
int index)
{
- return (sta == NULL || sta->supp_rates[band] & BIT(index));
+ return (sta == NULL || sta->deflink.supp_rates[band] & BIT(index));
}
static inline s8
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 2c3bbc6645ba..bdac0ddbdcdb 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -498,4 +498,23 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw);
void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb,
bool ifs_handling);
+/**
+ * ieee802154_xmit_error - offloaded frame transmission failed
+ *
+ * @hw: pointer as obtained from ieee802154_alloc_hw().
+ * @skb: buffer for transmission
+ * @reason: error code
+ */
+void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb,
+ int reason);
+
+/**
+ * ieee802154_xmit_hw_error - frame could not be offloaded to the transmitter
+ * because of a hardware error (bus error, timeout, etc)
+ *
+ * @hw: pointer as obtained from ieee802154_alloc_hw().
+ * @skb: buffer for transmission
+ */
+void ieee802154_xmit_hw_error(struct ieee802154_hw *hw, struct sk_buff *skb);
+
#endif /* NET_MAC802154_H */
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 0a3b0fb04a3b..4d761ad530c9 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -35,7 +35,8 @@ struct mptcp_ext {
frozen:1,
reset_transient:1;
u8 reset_reason:4,
- csum_reqd:1;
+ csum_reqd:1,
+ infinite_map:1;
};
#define MPTCP_RM_IDS_MAX 8
@@ -124,7 +125,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
struct mptcp_out_options *opts);
bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
-void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
struct mptcp_out_options *opts);
void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info);
@@ -283,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; }
static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
#endif
+#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL)
+struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk);
+#else
+static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
+#endif
+
#endif /* __NET_MPTCP_H */
diff --git a/include/net/net_debug.h b/include/net/net_debug.h
new file mode 100644
index 000000000000..1e74684cbbdb
--- /dev/null
+++ b/include/net/net_debug.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NET_DEBUG_H
+#define _LINUX_NET_DEBUG_H
+
+#include <linux/bug.h>
+#include <linux/kern_levels.h>
+
+struct net_device;
+
+__printf(3, 4) __cold
+void netdev_printk(const char *level, const struct net_device *dev,
+ const char *format, ...);
+__printf(2, 3) __cold
+void netdev_emerg(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_alert(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_crit(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_err(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_warn(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_notice(const struct net_device *dev, const char *format, ...);
+__printf(2, 3) __cold
+void netdev_info(const struct net_device *dev, const char *format, ...);
+
+#define netdev_level_once(level, dev, fmt, ...) \
+do { \
+ static bool __section(".data.once") __print_once; \
+ \
+ if (!__print_once) { \
+ __print_once = true; \
+ netdev_printk(level, dev, fmt, ##__VA_ARGS__); \
+ } \
+} while (0)
+
+#define netdev_emerg_once(dev, fmt, ...) \
+ netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__)
+#define netdev_alert_once(dev, fmt, ...) \
+ netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__)
+#define netdev_crit_once(dev, fmt, ...) \
+ netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__)
+#define netdev_err_once(dev, fmt, ...) \
+ netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__)
+#define netdev_warn_once(dev, fmt, ...) \
+ netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__)
+#define netdev_notice_once(dev, fmt, ...) \
+ netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__)
+#define netdev_info_once(dev, fmt, ...) \
+ netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netdev_dbg(__dev, format, args...) \
+do { \
+ dynamic_netdev_dbg(__dev, format, ##args); \
+} while (0)
+#elif defined(DEBUG)
+#define netdev_dbg(__dev, format, args...) \
+ netdev_printk(KERN_DEBUG, __dev, format, ##args)
+#else
+#define netdev_dbg(__dev, format, args...) \
+({ \
+ if (0) \
+ netdev_printk(KERN_DEBUG, __dev, format, ##args); \
+})
+#endif
+
+#if defined(VERBOSE_DEBUG)
+#define netdev_vdbg netdev_dbg
+#else
+
+#define netdev_vdbg(dev, format, args...) \
+({ \
+ if (0) \
+ netdev_printk(KERN_DEBUG, dev, format, ##args); \
+ 0; \
+})
+#endif
+
+/* netif printk helpers, similar to netdev_printk */
+
+#define netif_printk(priv, type, level, dev, fmt, args...) \
+do { \
+ if (netif_msg_##type(priv)) \
+ netdev_printk(level, (dev), fmt, ##args); \
+} while (0)
+
+#define netif_level(level, priv, type, dev, fmt, args...) \
+do { \
+ if (netif_msg_##type(priv)) \
+ netdev_##level(dev, fmt, ##args); \
+} while (0)
+
+#define netif_emerg(priv, type, dev, fmt, args...) \
+ netif_level(emerg, priv, type, dev, fmt, ##args)
+#define netif_alert(priv, type, dev, fmt, args...) \
+ netif_level(alert, priv, type, dev, fmt, ##args)
+#define netif_crit(priv, type, dev, fmt, args...) \
+ netif_level(crit, priv, type, dev, fmt, ##args)
+#define netif_err(priv, type, dev, fmt, args...) \
+ netif_level(err, priv, type, dev, fmt, ##args)
+#define netif_warn(priv, type, dev, fmt, args...) \
+ netif_level(warn, priv, type, dev, fmt, ##args)
+#define netif_notice(priv, type, dev, fmt, args...) \
+ netif_level(notice, priv, type, dev, fmt, ##args)
+#define netif_info(priv, type, dev, fmt, args...) \
+ netif_level(info, priv, type, dev, fmt, ##args)
+
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define netif_dbg(priv, type, netdev, format, args...) \
+do { \
+ if (netif_msg_##type(priv)) \
+ dynamic_netdev_dbg(netdev, format, ##args); \
+} while (0)
+#elif defined(DEBUG)
+#define netif_dbg(priv, type, dev, format, args...) \
+ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args)
+#else
+#define netif_dbg(priv, type, dev, format, args...) \
+({ \
+ if (0) \
+ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+ 0; \
+})
+#endif
+
+/* if @cond then downgrade to debug, else print at @level */
+#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \
+ do { \
+ if (cond) \
+ netif_dbg(priv, type, netdev, fmt, ##args); \
+ else \
+ netif_ ## level(priv, type, netdev, fmt, ##args); \
+ } while (0)
+
+#if defined(VERBOSE_DEBUG)
+#define netif_vdbg netif_dbg
+#else
+#define netif_vdbg(priv, type, dev, format, args...) \
+({ \
+ if (0) \
+ netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \
+ 0; \
+})
+#endif
+
+
+#if defined(CONFIG_DEBUG_NET)
+#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+#else
+#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#endif
+
+#endif /* _LINUX_NET_DEBUG_H */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index b08b70989d2c..a32be8aa7ed2 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -43,6 +43,12 @@ union nf_conntrack_expect_proto {
/* insert expect proto private data here */
};
+struct nf_conntrack_net_ecache {
+ struct delayed_work dwork;
+ spinlock_t dying_lock;
+ struct hlist_nulls_head dying_list;
+};
+
struct nf_conntrack_net {
/* only used when new connection is allocated: */
atomic_t count;
@@ -58,8 +64,7 @@ struct nf_conntrack_net {
struct ctl_table_header *sysctl_header;
#endif
#ifdef CONFIG_NF_CONNTRACK_EVENTS
- struct delayed_work ecache_dwork;
- struct netns_ct *ct_net;
+ struct nf_conntrack_net_ecache ecache;
#endif
};
@@ -96,7 +101,6 @@ struct nf_conn {
/* Have we seen traffic both ways yet? (bitset) */
unsigned long status;
- u16 cpu;
possible_net_t ct_net;
#if IS_ENABLED(CONFIG_NF_NAT)
@@ -232,13 +236,16 @@ static inline bool nf_ct_kill(struct nf_conn *ct)
return nf_ct_delete(ct, 0, 0);
}
-/* Set all unconfirmed conntrack as dying */
-void nf_ct_unconfirmed_destroy(struct net *);
+struct nf_ct_iter_data {
+ struct net *net;
+ void *data;
+ u32 portid;
+ int report;
+};
/* Iterate over all conntracks: if iter returns true, it's deleted. */
-void nf_ct_iterate_cleanup_net(struct net *net,
- int (*iter)(struct nf_conn *i, void *data),
- void *data, u32 portid, int report);
+void nf_ct_iterate_cleanup_net(int (*iter)(struct nf_conn *i, void *data),
+ const struct nf_ct_iter_data *iter_data);
/* also set unconfirmed conntracks as dying. Only use in module exit path. */
void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data),
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 13807ea94cd2..6406cfee34c2 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
if (ct) {
if (!nf_ct_is_confirmed(ct))
ret = __nf_conntrack_confirm(skb);
- if (likely(ret == NF_ACCEPT))
+ if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct))
nf_ct_deliver_cached_events(ct);
}
return ret;
diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 9645b47fa7e4..e227d997fc71 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -10,6 +10,7 @@ struct nf_conncount_data;
struct nf_conncount_list {
spinlock_t list_lock;
+ u32 last_gc; /* jiffies at most recent gc */
struct list_head head; /* connections with the same filtering key */
unsigned int count; /* length of list */
};
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 6c4c490a3e34..0c1dac318e02 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -14,7 +14,6 @@
#include <net/netfilter/nf_conntrack_extend.h>
enum nf_ct_ecache_state {
- NFCT_ECACHE_UNKNOWN, /* destroy event not sent */
NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */
NFCT_ECACHE_DESTROY_SENT, /* sent destroy event after failure */
};
@@ -23,7 +22,6 @@ struct nf_conntrack_ecache {
unsigned long cache; /* bitops want long */
u16 ctmask; /* bitmask of ct events to be delivered */
u16 expmask; /* bitmask of expect events to be delivered */
- enum nf_ct_ecache_state state:8;/* ecache state */
u32 missed; /* missed events */
u32 portid; /* netlink portid of destroyer */
};
@@ -38,28 +36,12 @@ nf_ct_ecache_find(const struct nf_conn *ct)
#endif
}
-static inline struct nf_conntrack_ecache *
-nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
+static inline bool nf_ct_ecache_exist(const struct nf_conn *ct)
{
#ifdef CONFIG_NF_CONNTRACK_EVENTS
- struct net *net = nf_ct_net(ct);
- struct nf_conntrack_ecache *e;
-
- if (!ctmask && !expmask && net->ct.sysctl_events) {
- ctmask = ~0;
- expmask = ~0;
- }
- if (!ctmask && !expmask)
- return NULL;
-
- e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp);
- if (e) {
- e->ctmask = ctmask;
- e->expmask = expmask;
- }
- return e;
+ return nf_ct_ext_exist(ct, NF_CT_EXT_ECACHE);
#else
- return NULL;
+ return false;
#endif
}
@@ -91,6 +73,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct);
int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct,
u32 portid, int report);
+bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp);
#else
static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct)
@@ -105,6 +88,10 @@ static inline int nf_conntrack_eventmask_report(unsigned int eventmask,
return 0;
}
+static inline bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp)
+{
+ return false;
+}
#endif
static inline void
@@ -130,30 +117,20 @@ nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct,
u32 portid, int report)
{
#ifdef CONFIG_NF_CONNTRACK_EVENTS
- const struct net *net = nf_ct_net(ct);
-
- if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb))
- return 0;
-
- return nf_conntrack_eventmask_report(1 << event, ct, portid, report);
-#else
- return 0;
+ if (nf_ct_ecache_exist(ct))
+ return nf_conntrack_eventmask_report(1 << event, ct, portid, report);
#endif
+ return 0;
}
static inline int
nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct)
{
#ifdef CONFIG_NF_CONNTRACK_EVENTS
- const struct net *net = nf_ct_net(ct);
-
- if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb))
- return 0;
-
- return nf_conntrack_eventmask_report(1 << event, ct, 0, 0);
-#else
- return 0;
+ if (nf_ct_ecache_exist(ct))
+ return nf_conntrack_eventmask_report(1 << event, ct, 0, 0);
#endif
+ return 0;
}
#ifdef CONFIG_NF_CONNTRACK_EVENTS
@@ -166,6 +143,8 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state);
void nf_conntrack_ecache_pernet_init(struct net *net);
void nf_conntrack_ecache_pernet_fini(struct net *net);
+struct nf_conntrack_net_ecache *nf_conn_pernet_ecache(const struct net *net);
+
static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net)
{
return net->ct.ecache_dwork_pending;
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 96635ad2acc7..0b247248b032 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -34,21 +34,11 @@ enum nf_ct_ext_id {
NF_CT_EXT_NUM,
};
-#define NF_CT_EXT_HELPER_TYPE struct nf_conn_help
-#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
-#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj
-#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct
-#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
-#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
-#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout
-#define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels
-#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy
-#define NF_CT_EXT_ACT_CT_TYPE struct nf_conn_act_ct_ext
-
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {
u8 offset[NF_CT_EXT_NUM];
u8 len;
+ unsigned int gen_id;
char data[] __aligned(8);
};
@@ -62,17 +52,28 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
return (ct->ext && __nf_ct_ext_exist(ct->ext, id));
}
-static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
+void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id);
+
+static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id)
{
- if (!nf_ct_ext_exist(ct, id))
+ struct nf_ct_ext *ext = ct->ext;
+
+ if (!ext || !__nf_ct_ext_exist(ext, id))
return NULL;
+ if (unlikely(ext->gen_id))
+ return __nf_ct_ext_find(ext, id);
+
return (void *)ct->ext + ct->ext->offset[id];
}
-#define nf_ct_ext_find(ext, id) \
- ((id##_TYPE *)__nf_ct_ext_find((ext), (id)))
/* Add this type, returns pointer to data or NULL. */
void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
+/* ext genid. if ext->id != ext_genid, extensions cannot be used
+ * anymore unless conntrack has CONFIRMED bit set.
+ */
+extern atomic_t nf_conntrack_ext_genid;
+void nf_ct_ext_bump_genid(void);
+
#endif /* _NF_CONNTRACK_EXTEND_H */
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index 3c23298e68ca..66bab6c60d12 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -17,10 +17,18 @@ struct nf_conn_labels {
unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)];
};
+/* Can't use nf_ct_ext_find(), flow dissector cannot use symbols
+ * exported by nf_conntrack module.
+ */
static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct)
{
#ifdef CONFIG_NF_CONNTRACK_LABELS
- return nf_ct_ext_find(ct, NF_CT_EXT_LABELS);
+ struct nf_ct_ext *ext = ct->ext;
+
+ if (!ext || !__nf_ct_ext_exist(ext, NF_CT_EXT_LABELS))
+ return NULL;
+
+ return (void *)ct->ext + ct->ext->offset[NF_CT_EXT_LABELS];
#else
return NULL;
#endif
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 3ea94f6f3844..fea258983d23 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -17,14 +17,6 @@ struct nf_ct_timeout {
char data[];
};
-struct ctnl_timeout {
- struct list_head head;
- struct rcu_head rcu_head;
- refcount_t refcnt;
- char name[CTNL_TIMEOUT_NAME_MAX];
- struct nf_ct_timeout timeout;
-};
-
struct nf_conn_timeout {
struct nf_ct_timeout __rcu *timeout;
};
diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h
index 9051c3a0c8e7..7c669792fb9c 100644
--- a/include/net/netfilter/nf_reject.h
+++ b/include/net/netfilter/nf_reject.h
@@ -5,12 +5,28 @@
#include <linux/types.h>
#include <uapi/linux/in.h>
-static inline bool nf_reject_verify_csum(__u8 proto)
+static inline bool nf_reject_verify_csum(struct sk_buff *skb, int dataoff,
+ __u8 proto)
{
/* Skip protocols that don't use 16-bit one's complement checksum
* of the entire payload.
*/
switch (proto) {
+ /* Protocols with optional checksums. */
+ case IPPROTO_UDP: {
+ const struct udphdr *udp_hdr;
+ struct udphdr _udp_hdr;
+
+ udp_hdr = skb_header_pointer(skb, dataoff,
+ sizeof(_udp_hdr),
+ &_udp_hdr);
+ if (!udp_hdr || udp_hdr->check)
+ return true;
+
+ return false;
+ }
+ case IPPROTO_GRE:
+
/* Protocols with other integrity checks. */
case IPPROTO_AH:
case IPPROTO_ESP:
@@ -19,9 +35,6 @@ static inline bool nf_reject_verify_csum(__u8 proto)
/* Protocols with partial checksums. */
case IPPROTO_UDPLITE:
case IPPROTO_DCCP:
-
- /* Protocols with optional checksums. */
- case IPPROTO_GRE:
return false;
}
return true;
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 0294f3d473af..0677cd3de034 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -93,14 +93,9 @@ struct nf_ip_net {
#endif
};
-struct ct_pcpu {
- spinlock_t lock;
- struct hlist_nulls_head unconfirmed;
- struct hlist_nulls_head dying;
-};
-
struct netns_ct {
#ifdef CONFIG_NF_CONNTRACK_EVENTS
+ bool ctnetlink_has_listener;
bool ecache_dwork_pending;
#endif
u8 sysctl_log_invalid; /* Log invalid packets */
@@ -110,7 +105,6 @@ struct netns_ct {
u8 sysctl_tstamp;
u8 sysctl_checksum;
- struct ct_pcpu __percpu *pcpu_lists;
struct ip_conntrack_stat __percpu *stat;
struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
struct nf_ip_net nf_ct_proto;
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index ea5fb70e5101..813c93499f20 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -117,6 +117,10 @@ struct page_pool_stats {
struct page_pool_recycle_stats recycle_stats;
};
+int page_pool_ethtool_stats_get_count(void);
+u8 *page_pool_ethtool_stats_get_strings(u8 *data);
+u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
+
/*
* Drivers that wish to harvest page pool stats and report them to users
* (perhaps via ethtool, debugfs, or another mechanism) can allocate a
@@ -124,6 +128,23 @@ struct page_pool_stats {
*/
bool page_pool_get_stats(struct page_pool *pool,
struct page_pool_stats *stats);
+#else
+
+static inline int page_pool_ethtool_stats_get_count(void)
+{
+ return 0;
+}
+
+static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data)
+{
+ return data;
+}
+
+static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
+{
+ return data;
+}
+
#endif
struct page_pool {
diff --git a/include/net/ping.h b/include/net/ping.h
index 2fe78874318c..e4ff3911cbf5 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -71,12 +71,12 @@ void ping_err(struct sk_buff *skb, int offset, u32 info);
int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd,
struct sk_buff *);
-int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
+int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len);
int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
void *user_icmph, size_t icmph_len);
int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-bool ping_rcv(struct sk_buff *skb);
+enum skb_drop_reason ping_rcv(struct sk_buff *skb);
#ifdef CONFIG_PROC_FS
void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family);
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3b57a93228a..8cf001aed858 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -547,10 +547,12 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
}
int tc_setup_offload_action(struct flow_action *flow_action,
- const struct tcf_exts *exts);
+ const struct tcf_exts *exts,
+ struct netlink_ext_ack *extack);
void tc_cleanup_offload_action(struct flow_action *flow_action);
int tc_setup_action(struct flow_action *flow_action,
- struct tc_action *actions[]);
+ struct tc_action *actions[],
+ struct netlink_ext_ack *extack);
int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
void *type_data, bool err_stop, bool rtnl_held);
diff --git a/include/net/route.h b/include/net/route.h
index 25404fc2b483..991a3985712d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -43,6 +43,19 @@
#define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
#define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
+static inline __u8 ip_sock_rt_scope(const struct sock *sk)
+{
+ if (sock_flag(sk, SOCK_LOCALROUTE))
+ return RT_SCOPE_LINK;
+
+ return RT_SCOPE_UNIVERSE;
+}
+
+static inline __u8 ip_sock_rt_tos(const struct sock *sk)
+{
+ return RT_TOS(inet_sk(sk)->tos);
+}
+
struct ip_tunnel_info;
struct fib_nh;
struct fib_info;
@@ -289,39 +302,38 @@ static inline char rt_tos2priority(u8 tos)
* ip_route_newports() calls.
*/
-static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src,
- u32 tos, int oif, u8 protocol,
+static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
+ __be32 src, int oif, u8 protocol,
__be16 sport, __be16 dport,
- struct sock *sk)
+ const struct sock *sk)
{
__u8 flow_flags = 0;
if (inet_sk(sk)->transparent)
flow_flags |= FLOWI_FLAG_ANYSRC;
- flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
- protocol, flow_flags, dst, src, dport, sport,
- sk->sk_uid);
+ flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk),
+ ip_sock_rt_scope(sk), protocol, flow_flags, dst,
+ src, dport, sport, sk->sk_uid);
}
-static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
- __be32 dst, __be32 src, u32 tos,
- int oif, u8 protocol,
+static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst,
+ __be32 src, int oif, u8 protocol,
__be16 sport, __be16 dport,
struct sock *sk)
{
struct net *net = sock_net(sk);
struct rtable *rt;
- ip_route_connect_init(fl4, dst, src, tos, oif, protocol,
- sport, dport, sk);
+ ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk);
if (!dst || !src) {
rt = __ip_route_output_key(net, fl4);
if (IS_ERR(rt))
return rt;
ip_rt_put(rt);
- flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr);
+ flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr,
+ fl4->saddr);
}
security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
return ip_route_output_flow(net, fl4, sk);
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 9f48733bfd21..bf8bb3357825 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -10,9 +10,23 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,
typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
enum rtnl_link_flags {
- RTNL_FLAG_DOIT_UNLOCKED = 1,
+ RTNL_FLAG_DOIT_UNLOCKED = BIT(0),
+ RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1),
};
+enum rtnl_kinds {
+ RTNL_KIND_NEW,
+ RTNL_KIND_DEL,
+ RTNL_KIND_GET,
+ RTNL_KIND_SET
+};
+#define RTNL_KIND_MASK 0x3
+
+static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype)
+{
+ return msgtype & RTNL_KIND_MASK;
+}
+
void rtnl_register(int protocol, int msgtype,
rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);
int rtnl_register_module(struct module *owner, int protocol, int msgtype,
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index bf3716fe83e0..a04999ee99b0 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -103,7 +103,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
extern struct percpu_counter sctp_sockets_allocated;
int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
-struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
+struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int *);
typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
void sctp_transport_walk_start(struct rhashtable_iter *iter);
diff --git a/include/net/sock.h b/include/net/sock.h
index c4b91fc19b9c..c585ef6565d9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -161,9 +161,6 @@ typedef __u64 __bitwise __addrpair;
* for struct sock and struct inet_timewait_sock.
*/
struct sock_common {
- /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
- * address on 64bit arches : cf INET_MATCH()
- */
union {
__addrpair skc_addrpair;
struct {
@@ -292,7 +289,6 @@ struct sk_filter;
* @sk_pacing_shift: scaling factor for TCP Small Queues
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
- * @defer_list: head of llist storing skbs to be freed
* @sk_callback_lock: used with the callbacks in the end of this struct
* @sk_error_queue: rarely used
* @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
@@ -352,6 +348,7 @@ struct sk_filter;
* @sk_txtime_report_errors: set report errors mode for SO_TXTIME
* @sk_txtime_unused: unused txtime flags
* @ns_tracker: tracker for netns reference
+ * @sk_bind2_node: bind node in the bhash2 table
*/
struct sock {
/*
@@ -417,7 +414,6 @@ struct sock {
struct sk_buff *head;
struct sk_buff *tail;
} sk_backlog;
- struct llist_head defer_list;
#define sk_rmem_alloc sk_backlog.rmem_alloc
@@ -542,6 +538,7 @@ struct sock {
#endif
struct rcu_head sk_rcu;
netns_tracker ns_tracker;
+ struct hlist_node sk_bind2_node;
};
enum sk_pacing {
@@ -822,6 +819,16 @@ static inline void sk_add_bind_node(struct sock *sk,
hlist_add_head(&sk->sk_bind_node, list);
}
+static inline void __sk_del_bind2_node(struct sock *sk)
+{
+ __hlist_del(&sk->sk_bind2_node);
+}
+
+static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list)
+{
+ hlist_add_head(&sk->sk_bind2_node, list);
+}
+
#define sk_for_each(__sk, list) \
hlist_for_each_entry(__sk, list, sk_node)
#define sk_for_each_rcu(__sk, list) \
@@ -839,6 +846,8 @@ static inline void sk_add_bind_node(struct sock *sk,
hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
#define sk_for_each_bound(__sk, list) \
hlist_for_each_entry(__sk, list, sk_bind_node)
+#define sk_for_each_bound_bhash2(__sk, list) \
+ hlist_for_each_entry(__sk, list, sk_bind2_node)
/**
* sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
@@ -895,6 +904,7 @@ enum sock_flags {
SOCK_TXTIME,
SOCK_XDP, /* XDP is attached */
SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
+ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */
};
#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1202,8 +1212,7 @@ struct proto {
int (*sendmsg)(struct sock *sk, struct msghdr *msg,
size_t len);
int (*recvmsg)(struct sock *sk, struct msghdr *msg,
- size_t len, int noblock, int flags,
- int *addr_len);
+ size_t len, int flags, int *addr_len);
int (*sendpage)(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
int (*bind)(struct sock *sk,
@@ -1825,11 +1834,17 @@ int sock_getsockopt(struct socket *sock, int level, int op,
char __user *optval, int __user *optlen);
int sock_gettstamp(struct socket *sock, void __user *userstamp,
bool timeval, bool time32);
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
- int noblock, int *errcode);
struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
unsigned long data_len, int noblock,
int *errcode, int max_page_order);
+
+static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk,
+ unsigned long size,
+ int noblock, int *errcode)
+{
+ return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
+}
+
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
void sock_kfree_s(struct sock *sk, void *mem, int size);
void sock_kzfree_s(struct sock *sk, void *mem, int size);
@@ -2392,7 +2407,14 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
void (*destructor)(struct sock *sk,
struct sk_buff *skb));
int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+
+int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
+ enum skb_drop_reason *reason);
+
+static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ return sock_queue_rcv_skb_reason(sk, skb, NULL);
+}
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
struct sk_buff *sock_dequeue_err_skb(struct sock *sk);
@@ -2643,20 +2665,21 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
__sock_recv_wifi_status(msg, sk, skb);
}
-void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb);
+void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb);
#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
-static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
- struct sk_buff *skb)
+static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb)
{
-#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \
- (1UL << SOCK_RCVTSTAMP))
+#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \
+ (1UL << SOCK_RCVTSTAMP) | \
+ (1UL << SOCK_RCVMARK))
#define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \
SOF_TIMESTAMPING_RAW_HARDWARE)
- if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
- __sock_recv_ts_and_drops(msg, sk, skb);
+ if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY)
+ __sock_recv_cmsgs(msg, sk, skb);
else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
sock_write_timestamp(sk, skb->tstamp);
else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
@@ -2866,13 +2889,14 @@ static inline void sk_pacing_shift_update(struct sock *sk, int val)
*/
static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
{
+ int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
int mdif;
- if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)
+ if (!bound_dev_if || bound_dev_if == dif)
return true;
mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif);
- if (mdif && mdif == sk->sk_bound_dev_if)
+ if (mdif && mdif == bound_dev_if)
return true;
return false;
diff --git a/include/net/strparser.h b/include/net/strparser.h
index 732b7097d78e..a191486eb1e4 100644
--- a/include/net/strparser.h
+++ b/include/net/strparser.h
@@ -70,6 +70,10 @@ struct sk_skb_cb {
* when dst_reg == src_reg.
*/
u64 temp_reg;
+ struct tls_msg {
+ u8 control;
+ u8 decrypted;
+ } tls;
};
static inline struct strp_msg *strp_msg(struct sk_buff *skb)
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index eb8f01c819e6..832efd40e023 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -59,4 +59,19 @@ static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a)
return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK;
}
+static inline bool is_tcf_gact_continue(const struct tc_action *a)
+{
+ return __is_tcf_gact_act(a, TC_ACT_UNSPEC, false);
+}
+
+static inline bool is_tcf_gact_reclassify(const struct tc_action *a)
+{
+ return __is_tcf_gact_act(a, TC_ACT_RECLASSIFY, false);
+}
+
+static inline bool is_tcf_gact_pipe(const struct tc_action *a)
+{
+ return __is_tcf_gact_act(a, TC_ACT_PIPE, false);
+}
+
#endif /* __NET_TC_GACT_H */
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index 00bfee70609e..dc1079f28e13 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -17,6 +17,7 @@ struct tcf_skbedit_params {
u32 mark;
u32 mask;
u16 queue_mapping;
+ u16 mapping_mod;
u16 ptype;
struct rcu_head rcu;
};
@@ -94,4 +95,16 @@ static inline u32 tcf_skbedit_priority(const struct tc_action *a)
return priority;
}
+/* Return true iff action is queue_mapping */
+static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a)
+{
+ return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING);
+}
+
+/* Return true iff action is inheritdsfield */
+static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a)
+{
+ return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD);
+}
+
#endif /* __NET_TC_SKBEDIT_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index cc1295037533..1e99f5c61f84 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -407,7 +407,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen);
void tcp_set_keepalive(struct sock *sk, int val);
void tcp_syn_ack_timeout(const struct request_sock *req);
-int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len);
int tcp_set_rcvlowat(struct sock *sk, int val);
int tcp_set_window_clamp(struct sock *sk, int val);
@@ -1142,15 +1142,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk)
return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN;
}
-static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_ca_ops->set_state)
- icsk->icsk_ca_ops->set_state(sk, ca_state);
- icsk->icsk_ca_state = ca_state;
-}
-
static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1159,6 +1150,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
icsk->icsk_ca_ops->cwnd_event(sk, event);
}
+/* From tcp_cong.c */
+void tcp_set_ca_state(struct sock *sk, const u8 ca_state);
+
/* From tcp_rate.c */
void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
@@ -1215,9 +1209,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
#define TCP_INFINITE_SSTHRESH 0x7fffffff
+static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd;
+}
+
+static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val)
+{
+ WARN_ON_ONCE((int)val <= 0);
+ tp->snd_cwnd = val;
+}
+
static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
{
- return tp->snd_cwnd < tp->snd_ssthresh;
+ return tcp_snd_cwnd(tp) < tp->snd_ssthresh;
}
static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
@@ -1243,8 +1248,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
return tp->snd_ssthresh;
else
return max(tp->snd_ssthresh,
- ((tp->snd_cwnd >> 1) +
- (tp->snd_cwnd >> 2)));
+ ((tcp_snd_cwnd(tp) >> 1) +
+ (tcp_snd_cwnd(tp) >> 2)));
}
/* Use define here intentionally to get WARN_ON location shown at the caller */
@@ -1286,7 +1291,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
/* If in slow start, ensure cwnd grows to twice what was ACKed. */
if (tcp_in_slow_start(tp))
- return tp->snd_cwnd < 2 * tp->max_packets_out;
+ return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out;
return tp->is_cwnd_limited;
}
@@ -1378,18 +1383,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
enum skb_drop_reason *reason);
-#ifdef CONFIG_INET
-void __sk_defer_free_flush(struct sock *sk);
-
-static inline void sk_defer_free_flush(struct sock *sk)
-{
- if (llist_empty(&sk->defer_list))
- return;
- __sk_defer_free_flush(sk);
-}
-#else
-static inline void sk_defer_free_flush(struct sock *sk) {}
-#endif
int tcp_filter(struct sock *sk, struct sk_buff *skb);
void tcp_set_state(struct sock *sk, int state);
diff --git a/include/net/tls.h b/include/net/tls.h
index b6968a5b5538..8017f1703447 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -64,6 +64,7 @@
#define TLS_AAD_SPACE_SIZE 13
#define MAX_IV_SIZE 16
+#define TLS_TAG_SIZE 16
#define TLS_MAX_REC_SEQ_SIZE 8
/* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes.
@@ -117,11 +118,6 @@ struct tls_rec {
u8 aead_req_ctx[];
};
-struct tls_msg {
- struct strp_msg rxm;
- u8 control;
-};
-
struct tx_work {
struct delayed_work work;
struct sock *sk;
@@ -152,13 +148,10 @@ struct tls_sw_context_rx {
void (*saved_data_ready)(struct sock *sk);
struct sk_buff *recv_pkt;
- u8 control;
u8 async_capable:1;
- u8 decrypted:1;
atomic_t decrypt_pending;
/* protect crypto_wait with decrypt_pending*/
spinlock_t decrypt_compl_lock;
- bool async_notify;
};
struct tls_record_info {
@@ -245,6 +238,7 @@ struct tls_context {
u8 tx_conf:3;
u8 rx_conf:3;
+ u8 zerocopy_sendfile:1;
int (*push_pending_record)(struct sock *sk, int flags);
void (*sk_write_space)(struct sock *sk);
@@ -378,7 +372,7 @@ void tls_sw_free_resources_rx(struct sock *sk);
void tls_sw_release_resources_rx(struct sock *sk);
void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
- int nonblock, int flags, int *addr_len);
+ int flags, int *addr_len);
bool tls_sw_sock_is_readable(struct sock *sk);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
@@ -411,7 +405,9 @@ void tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
static inline struct tls_msg *tls_msg(struct sk_buff *skb)
{
- return (struct tls_msg *)strp_msg(skb);
+ struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb;
+
+ return &scb->tls;
}
static inline bool tls_is_partially_sent_record(struct tls_context *ctx)
diff --git a/include/net/udp.h b/include/net/udp.h
index f1c2a88c9005..b83a00330566 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -250,14 +250,14 @@ void udp_destruct_sock(struct sock *sk);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
-struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
- int noblock, int *off, int *err);
+struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off,
+ int *err);
static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
- int noblock, int *err)
+ int *err)
{
int off = 0;
- return __skb_recv_udp(sk, flags, noblock, &off, err);
+ return __skb_recv_udp(sk, flags, &off, err);
}
int udp_v4_early_demux(struct sk_buff *skb);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index d2efddce65d4..c39d910d4b45 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -126,13 +126,17 @@ struct xfrm_state_walk {
struct xfrm_address_filter *filter;
};
-struct xfrm_state_offload {
+enum {
+ XFRM_DEV_OFFLOAD_IN = 1,
+ XFRM_DEV_OFFLOAD_OUT,
+};
+
+struct xfrm_dev_offload {
struct net_device *dev;
netdevice_tracker dev_tracker;
struct net_device *real_dev;
unsigned long offload_handle;
- unsigned int num_exthdrs;
- u8 flags;
+ u8 dir : 2;
};
struct xfrm_mode {
@@ -247,7 +251,7 @@ struct xfrm_state {
struct xfrm_lifetime_cur curlft;
struct hrtimer mtimer;
- struct xfrm_state_offload xso;
+ struct xfrm_dev_offload xso;
/* used to fix curlft->add_time when changing date */
long saved_tmo;
@@ -1006,7 +1010,7 @@ struct xfrm_offload {
#define CRYPTO_FALLBACK 8
#define XFRM_GSO_SEGMENT 16
#define XFRM_GRO 32
-#define XFRM_ESP_NO_TRAILER 64
+/* 64 is free */
#define XFRM_DEV_RESUME 128
#define XFRM_XMIT 256
@@ -1878,7 +1882,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x)
{
- struct xfrm_state_offload *xso = &x->xso;
+ struct xfrm_dev_offload *xso = &x->xso;
if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn)
xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x);
@@ -1904,7 +1908,7 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
static inline void xfrm_dev_state_delete(struct xfrm_state *x)
{
- struct xfrm_state_offload *xso = &x->xso;
+ struct xfrm_dev_offload *xso = &x->xso;
if (xso->dev)
xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
@@ -1912,7 +1916,7 @@ static inline void xfrm_dev_state_delete(struct xfrm_state *x)
static inline void xfrm_dev_state_free(struct xfrm_state *x)
{
- struct xfrm_state_offload *xso = &x->xso;
+ struct xfrm_dev_offload *xso = &x->xso;
struct net_device *dev = xso->dev;
if (dev && dev->xfrmdev_ops) {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 69d883f7fb41..11ee4eaf84bd 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2497,15 +2497,7 @@ struct ib_device_ops {
struct ib_flow_attr *flow_attr,
struct ib_udata *udata);
int (*destroy_flow)(struct ib_flow *flow_id);
- struct ib_flow_action *(*create_flow_action_esp)(
- struct ib_device *device,
- const struct ib_flow_action_attrs_esp *attr,
- struct uverbs_attr_bundle *attrs);
int (*destroy_flow_action)(struct ib_flow_action *action);
- int (*modify_flow_action_esp)(
- struct ib_flow_action *action,
- const struct ib_flow_action_attrs_esp *attr,
- struct uverbs_attr_bundle *attrs);
int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port,
int state);
int (*get_vf_config)(struct ib_device *device, int vf, u32 port,
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 9b4e6c78d0f4..5f88385a7748 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -105,6 +105,11 @@
#define REG_RESERVED_ADDR 0xffffffff
#define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR)
+#define for_each_stat(ocelot, stat) \
+ for ((stat) = (ocelot)->stats_layout; \
+ ((stat)->name[0] != '\0'); \
+ (stat)++)
+
enum ocelot_target {
ANA = 1,
QS,
@@ -538,6 +543,8 @@ struct ocelot_stat_layout {
char name[ETH_GSTRING_LEN];
};
+#define OCELOT_STAT_END { .name = "" }
+
struct ocelot_stats_region {
struct list_head node;
u32 offset;
@@ -647,34 +654,41 @@ struct ocelot_mirror {
int to;
};
+struct ocelot_port;
+
struct ocelot_port {
struct ocelot *ocelot;
struct regmap *target;
- bool vlan_aware;
+ struct net_device *bond;
+ struct net_device *bridge;
+
+ struct ocelot_port *dsa_8021q_cpu;
+
/* VLAN that untagged frames are classified to, on ingress */
const struct ocelot_bridge_vlan *pvid_vlan;
+ phy_interface_t phy_mode;
+
unsigned int ptp_skbs_in_flight;
- u8 ptp_cmd;
struct sk_buff_head tx_skbs;
+
+ u16 mrp_ring_id;
+
+ u8 ptp_cmd;
u8 ts_id;
- phy_interface_t phy_mode;
+ u8 index;
- u8 *xmit_template;
+ u8 stp_state;
+ bool vlan_aware;
bool is_dsa_8021q_cpu;
bool learn_ena;
- struct net_device *bond;
bool lag_tx_active;
- u16 mrp_ring_id;
-
- struct net_device *bridge;
int bridge_num;
- u8 stp_state;
int speed;
};
@@ -855,8 +869,9 @@ void ocelot_deinit(struct ocelot *ocelot);
void ocelot_init_port(struct ocelot *ocelot, int port);
void ocelot_deinit_port(struct ocelot *ocelot, int port);
-void ocelot_port_set_dsa_8021q_cpu(struct ocelot *ocelot, int port);
-void ocelot_port_unset_dsa_8021q_cpu(struct ocelot *ocelot, int port);
+void ocelot_port_assign_dsa_8021q_cpu(struct ocelot *ocelot, int port, int cpu);
+void ocelot_port_unassign_dsa_8021q_cpu(struct ocelot *ocelot, int port);
+u32 ocelot_port_assigned_dsa_8021q_cpu_mask(struct ocelot *ocelot, int port);
/* DSA callbacks */
void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data);
@@ -868,9 +883,7 @@ void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs);
int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled,
struct netlink_ext_ack *extack);
void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state);
-u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot);
u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port);
-void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot, bool joining);
int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port,
struct switchdev_brport_flags val);
void ocelot_port_bridge_flags(struct ocelot *ocelot, int port,
@@ -991,6 +1004,9 @@ int ocelot_mact_learn_streamdata(struct ocelot *ocelot, int dst_idx,
enum macaccess_entry_type type,
int sfid, int ssid);
+int ocelot_migrate_mdbs(struct ocelot *ocelot, unsigned long from_mask,
+ unsigned long to_mask);
+
int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix,
struct ocelot_policer *pol);
int ocelot_vcap_policer_del(struct ocelot *ocelot, u32 pol_ix);
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index de26c992f821..c601a4598b0d 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -11,7 +11,7 @@
/* Cookie definitions for private VCAP filters installed by the driver.
* Must be unique per VCAP block.
*/
-#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port)
+#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port))
#define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port)
#define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port)
#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port))
diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
index f8e28e686c65..563e48617374 100644
--- a/include/trace/events/mptcp.h
+++ b/include/trace/events/mptcp.h
@@ -84,6 +84,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
__field(u8, reset_transient)
__field(u8, reset_reason)
__field(u8, csum_reqd)
+ __field(u8, infinite_map)
),
TP_fast_assign(
@@ -102,9 +103,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
__entry->reset_transient = mpext->reset_transient;
__entry->reset_reason = mpext->reset_reason;
__entry->csum_reqd = mpext->csum_reqd;
+ __entry->infinite_map = mpext->infinite_map;
),
- TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u",
+ TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u",
__entry->data_ack, __entry->data_seq,
__entry->subflow_seq, __entry->data_len,
__entry->csum, __entry->use_map,
@@ -112,7 +114,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext,
__entry->use_ack, __entry->ack64,
__entry->mpc_map, __entry->frozen,
__entry->reset_transient, __entry->reset_reason,
- __entry->csum_reqd)
+ __entry->csum_reqd, __entry->infinite_map)
);
DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag,
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 1c714336b863..d20bf4aa0204 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -14,215 +14,6 @@
#include <linux/errqueue.h>
/*
- * Define enums for tracing information.
- *
- * These should all be kept sorted, making it easier to match the string
- * mapping tables further on.
- */
-#ifndef __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY
-#define __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY
-
-enum rxrpc_skb_trace {
- rxrpc_skb_cleaned,
- rxrpc_skb_freed,
- rxrpc_skb_got,
- rxrpc_skb_lost,
- rxrpc_skb_new,
- rxrpc_skb_purged,
- rxrpc_skb_received,
- rxrpc_skb_rotated,
- rxrpc_skb_seen,
- rxrpc_skb_unshared,
- rxrpc_skb_unshared_nomem,
-};
-
-enum rxrpc_local_trace {
- rxrpc_local_got,
- rxrpc_local_new,
- rxrpc_local_processing,
- rxrpc_local_put,
- rxrpc_local_queued,
-};
-
-enum rxrpc_peer_trace {
- rxrpc_peer_got,
- rxrpc_peer_new,
- rxrpc_peer_processing,
- rxrpc_peer_put,
-};
-
-enum rxrpc_conn_trace {
- rxrpc_conn_got,
- rxrpc_conn_new_client,
- rxrpc_conn_new_service,
- rxrpc_conn_put_client,
- rxrpc_conn_put_service,
- rxrpc_conn_queued,
- rxrpc_conn_reap_service,
- rxrpc_conn_seen,
-};
-
-enum rxrpc_client_trace {
- rxrpc_client_activate_chans,
- rxrpc_client_alloc,
- rxrpc_client_chan_activate,
- rxrpc_client_chan_disconnect,
- rxrpc_client_chan_pass,
- rxrpc_client_chan_wait_failed,
- rxrpc_client_cleanup,
- rxrpc_client_discard,
- rxrpc_client_duplicate,
- rxrpc_client_exposed,
- rxrpc_client_replace,
- rxrpc_client_to_active,
- rxrpc_client_to_idle,
-};
-
-enum rxrpc_call_trace {
- rxrpc_call_connected,
- rxrpc_call_error,
- rxrpc_call_got,
- rxrpc_call_got_kernel,
- rxrpc_call_got_timer,
- rxrpc_call_got_userid,
- rxrpc_call_new_client,
- rxrpc_call_new_service,
- rxrpc_call_put,
- rxrpc_call_put_kernel,
- rxrpc_call_put_noqueue,
- rxrpc_call_put_notimer,
- rxrpc_call_put_timer,
- rxrpc_call_put_userid,
- rxrpc_call_queued,
- rxrpc_call_queued_ref,
- rxrpc_call_release,
- rxrpc_call_seen,
-};
-
-enum rxrpc_transmit_trace {
- rxrpc_transmit_await_reply,
- rxrpc_transmit_end,
- rxrpc_transmit_queue,
- rxrpc_transmit_queue_last,
- rxrpc_transmit_rotate,
- rxrpc_transmit_rotate_last,
- rxrpc_transmit_wait,
-};
-
-enum rxrpc_receive_trace {
- rxrpc_receive_end,
- rxrpc_receive_front,
- rxrpc_receive_incoming,
- rxrpc_receive_queue,
- rxrpc_receive_queue_last,
- rxrpc_receive_rotate,
-};
-
-enum rxrpc_recvmsg_trace {
- rxrpc_recvmsg_cont,
- rxrpc_recvmsg_data_return,
- rxrpc_recvmsg_dequeue,
- rxrpc_recvmsg_enter,
- rxrpc_recvmsg_full,
- rxrpc_recvmsg_hole,
- rxrpc_recvmsg_next,
- rxrpc_recvmsg_requeue,
- rxrpc_recvmsg_return,
- rxrpc_recvmsg_terminal,
- rxrpc_recvmsg_to_be_accepted,
- rxrpc_recvmsg_wait,
-};
-
-enum rxrpc_rtt_tx_trace {
- rxrpc_rtt_tx_cancel,
- rxrpc_rtt_tx_data,
- rxrpc_rtt_tx_no_slot,
- rxrpc_rtt_tx_ping,
-};
-
-enum rxrpc_rtt_rx_trace {
- rxrpc_rtt_rx_cancel,
- rxrpc_rtt_rx_lost,
- rxrpc_rtt_rx_obsolete,
- rxrpc_rtt_rx_ping_response,
- rxrpc_rtt_rx_requested_ack,
-};
-
-enum rxrpc_timer_trace {
- rxrpc_timer_begin,
- rxrpc_timer_exp_ack,
- rxrpc_timer_exp_hard,
- rxrpc_timer_exp_idle,
- rxrpc_timer_exp_keepalive,
- rxrpc_timer_exp_lost_ack,
- rxrpc_timer_exp_normal,
- rxrpc_timer_exp_ping,
- rxrpc_timer_exp_resend,
- rxrpc_timer_expired,
- rxrpc_timer_init_for_reply,
- rxrpc_timer_init_for_send_reply,
- rxrpc_timer_restart,
- rxrpc_timer_set_for_ack,
- rxrpc_timer_set_for_hard,
- rxrpc_timer_set_for_idle,
- rxrpc_timer_set_for_keepalive,
- rxrpc_timer_set_for_lost_ack,
- rxrpc_timer_set_for_normal,
- rxrpc_timer_set_for_ping,
- rxrpc_timer_set_for_resend,
- rxrpc_timer_set_for_send,
-};
-
-enum rxrpc_propose_ack_trace {
- rxrpc_propose_ack_client_tx_end,
- rxrpc_propose_ack_input_data,
- rxrpc_propose_ack_ping_for_check_life,
- rxrpc_propose_ack_ping_for_keepalive,
- rxrpc_propose_ack_ping_for_lost_ack,
- rxrpc_propose_ack_ping_for_lost_reply,
- rxrpc_propose_ack_ping_for_params,
- rxrpc_propose_ack_processing_op,
- rxrpc_propose_ack_respond_to_ack,
- rxrpc_propose_ack_respond_to_ping,
- rxrpc_propose_ack_retry_tx,
- rxrpc_propose_ack_rotate_rx,
- rxrpc_propose_ack_terminal_ack,
-};
-
-enum rxrpc_propose_ack_outcome {
- rxrpc_propose_ack_subsume,
- rxrpc_propose_ack_update,
- rxrpc_propose_ack_use,
-};
-
-enum rxrpc_congest_change {
- rxrpc_cong_begin_retransmission,
- rxrpc_cong_cleared_nacks,
- rxrpc_cong_new_low_nack,
- rxrpc_cong_no_change,
- rxrpc_cong_progress,
- rxrpc_cong_retransmit_again,
- rxrpc_cong_rtt_window_end,
- rxrpc_cong_saw_nack,
-};
-
-enum rxrpc_tx_point {
- rxrpc_tx_point_call_abort,
- rxrpc_tx_point_call_ack,
- rxrpc_tx_point_call_data_frag,
- rxrpc_tx_point_call_data_nofrag,
- rxrpc_tx_point_call_final_resend,
- rxrpc_tx_point_conn_abort,
- rxrpc_tx_point_rxkad_challenge,
- rxrpc_tx_point_rxkad_response,
- rxrpc_tx_point_reject,
- rxrpc_tx_point_version_keepalive,
- rxrpc_tx_point_version_reply,
-};
-
-#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
-
-/*
* Declare tracing information enums and their string mappings for display.
*/
#define rxrpc_skb_traces \
@@ -452,6 +243,36 @@ enum rxrpc_tx_point {
E_(rxrpc_tx_point_version_reply, "VerReply")
/*
+ * Generate enums for tracing information.
+ */
+#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
+#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
+
+#undef EM
+#undef E_
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte);
+enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte);
+enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte);
+enum rxrpc_conn_trace { rxrpc_conn_traces } __mode(byte);
+enum rxrpc_local_trace { rxrpc_local_traces } __mode(byte);
+enum rxrpc_peer_trace { rxrpc_peer_traces } __mode(byte);
+enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte);
+enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte);
+enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte);
+enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte);
+enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte);
+enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte);
+enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte);
+enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte);
+enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte);
+enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte);
+
+#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
+
+/*
* Export enum symbols via userspace.
*/
#undef EM
@@ -459,21 +280,21 @@ enum rxrpc_tx_point {
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define E_(a, b) TRACE_DEFINE_ENUM(a);
-rxrpc_skb_traces;
-rxrpc_local_traces;
-rxrpc_conn_traces;
-rxrpc_client_traces;
rxrpc_call_traces;
-rxrpc_transmit_traces;
+rxrpc_client_traces;
+rxrpc_congest_changes;
+rxrpc_congest_modes;
+rxrpc_conn_traces;
+rxrpc_local_traces;
+rxrpc_propose_ack_outcomes;
+rxrpc_propose_ack_traces;
rxrpc_receive_traces;
rxrpc_recvmsg_traces;
-rxrpc_rtt_tx_traces;
rxrpc_rtt_rx_traces;
+rxrpc_rtt_tx_traces;
+rxrpc_skb_traces;
rxrpc_timer_traces;
-rxrpc_propose_ack_traces;
-rxrpc_propose_ack_outcomes;
-rxrpc_congest_modes;
-rxrpc_congest_changes;
+rxrpc_transmit_traces;
rxrpc_tx_points;
/*
@@ -583,7 +404,7 @@ TRACE_EVENT(rxrpc_client,
TP_fast_assign(
__entry->conn = conn ? conn->debug_id : 0;
__entry->channel = channel;
- __entry->usage = conn ? atomic_read(&conn->usage) : -2;
+ __entry->usage = conn ? refcount_read(&conn->ref) : -2;
__entry->op = op;
__entry->cid = conn ? conn->proto.cid : 0;
),
@@ -1574,6 +1395,8 @@ TRACE_EVENT(rxrpc_rx_discard_ack,
__entry->call_ackr_prev)
);
+#undef EM
+#undef E_
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index e1670e1e4934..a477bf907498 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -37,6 +37,20 @@
EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \
EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \
EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \
+ EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \
+ EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \
+ EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \
+ TCP_INVALID_SEQUENCE) \
+ EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \
+ EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \
+ EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \
+ EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \
+ EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \
+ EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \
+ EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \
+ TCP_ACK_UNSENT_DATA) \
+ EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \
+ TCP_OFO_QUEUE_PRUNE) \
EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \
EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \
BPF_CGROUP_EGRESS) \
@@ -50,7 +64,7 @@
EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \
EM(SKB_DROP_REASON_XDP, XDP) \
EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \
- EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \
+ EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \
EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \
EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \
EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \
@@ -61,6 +75,11 @@
EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \
EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \
EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \
+ EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \
+ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \
+ EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \
+ EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \
+ EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \
EMe(SKB_DROP_REASON_MAX, MAX)
#undef EM
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 521059d8dc0a..901b440238d5 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -279,7 +279,7 @@ TRACE_EVENT(tcp_probe,
__entry->data_len = skb->len - __tcp_hdrlen(th);
__entry->snd_nxt = tp->snd_nxt;
__entry->snd_una = tp->snd_una;
- __entry->snd_cwnd = tp->snd_cwnd;
+ __entry->snd_cwnd = tcp_snd_cwnd(tp);
__entry->snd_wnd = tp->snd_wnd;
__entry->rcv_wnd = tp->rcv_wnd;
__entry->ssthresh = tcp_current_ssthresh(sk);
@@ -371,6 +371,51 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
TP_ARGS(skb)
);
+TRACE_EVENT(tcp_cong_state_set,
+
+ TP_PROTO(struct sock *sk, const u8 ca_state),
+
+ TP_ARGS(sk, ca_state),
+
+ TP_STRUCT__entry(
+ __field(const void *, skaddr)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ __field(__u8, cong_state)
+ ),
+
+ TP_fast_assign(
+ struct inet_sock *inet = inet_sk(sk);
+ __be32 *p32;
+
+ __entry->skaddr = sk;
+
+ __entry->sport = ntohs(inet->inet_sport);
+ __entry->dport = ntohs(inet->inet_dport);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = inet->inet_saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = inet->inet_daddr;
+
+ TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+ sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
+
+ __entry->cong_state = ca_state;
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u",
+ __entry->sport, __entry->dport,
+ __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6,
+ __entry->cong_state)
+);
+
#endif /* _TRACE_TCP_H */
/* This part must be outside protection */
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 467ca2f28760..638230899e98 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -130,6 +130,8 @@
#define SO_TXREHASH 74
+#define SO_RCVMARK 75
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h
deleted file mode 100644
index 5135027b93c1..000000000000
--- a/include/uapi/linux/atm_zatm.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by
- driver-specific utilities) */
-
-/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
-
-
-#ifndef LINUX_ATM_ZATM_H
-#define LINUX_ATM_ZATM_H
-
-/*
- * Note: non-kernel programs including this file must also include
- * sys/types.h for struct timeval
- */
-
-#include <linux/atmapi.h>
-#include <linux/atmioc.h>
-
-#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
- /* get pool statistics */
-#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc)
- /* get statistics and zero */
-#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc)
- /* set pool parameters */
-
-struct zatm_pool_info {
- int ref_count; /* free buffer pool usage counters */
- int low_water,high_water; /* refill parameters */
- int rqa_count,rqu_count; /* queue condition counters */
- int offset,next_off; /* alignment optimizations: offset */
- int next_cnt,next_thres; /* repetition counter and threshold */
-};
-
-struct zatm_pool_req {
- int pool_num; /* pool number */
- struct zatm_pool_info info; /* actual information */
-};
-
-#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */
-#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */
-#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */
-#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */
-
-#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to
- record; must be 2^n */
-
-#endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d14b10b85e51..f4009dbdf62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1013,6 +1013,7 @@ enum bpf_link_type {
BPF_LINK_TYPE_XDP = 6,
BPF_LINK_TYPE_PERF_EVENT = 7,
BPF_LINK_TYPE_KPROBE_MULTI = 8,
+ BPF_LINK_TYPE_STRUCT_OPS = 9,
MAX_BPF_LINK_TYPE,
};
@@ -1489,6 +1490,15 @@ union bpf_attr {
__aligned_u64 addrs;
__aligned_u64 cookies;
} kprobe_multi;
+ struct {
+ /* this is overlaid with the target_btf_id above. */
+ __u32 target_btf_id;
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 cookie;
+ } tracing;
};
} link_create;
@@ -5143,6 +5153,102 @@ union bpf_attr {
* The **hash_algo** is returned on success,
* **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
* invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ * Description
+ * Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * old value. *ptr* can be NULL, otherwise it must be a referenced
+ * pointer which will be released when this helper is called.
+ * Return
+ * The old value of kptr (which can be NULL). The returned pointer
+ * if not NULL, is a reference which must be released using its
+ * corresponding release function, or moved into a BPF map before
+ * program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * Description
+ * Perform a lookup in *percpu map* for an entry associated to
+ * *key* on *cpu*.
+ * Return
+ * Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Get a dynptr to local memory *data*.
+ *
+ * *data* must be a ptr to a map value.
+ * The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * -EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * through the dynptr interface. *flags* must be 0.
+ *
+ * Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * reservation fails. This is enforced by the verifier.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*,
+ * through the dynptr interface. This is a no-op if the dynptr is
+ * invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_submit'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample through the dynptr
+ * interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_discard'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset)
+ * Description
+ * Read *len* bytes from *src* into *dst*, starting from *offset*
+ * into *src*.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *src*'s data, -EINVAL if *src* is an invalid dynptr.
+ *
+ * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len)
+ * Description
+ * Write *len* bytes from *src* into *dst*, starting from *offset*
+ * into *dst*.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * Description
+ * Get a pointer to the underlying dynptr data.
+ *
+ * *len* must be a statically known value. The returned data slice
+ * is invalidated whenever the dynptr is invalidated.
+ * Return
+ * Pointer to the underlying dynptr data, NULL if the dynptr is
+ * read-only, if the dynptr is invalid, or if the offset and length
+ * is out of bounds.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5339,6 +5445,16 @@ union bpf_attr {
FN(copy_from_user_task), \
FN(skb_set_tstamp), \
FN(ima_file_hash), \
+ FN(kptr_xchg), \
+ FN(map_lookup_percpu_elem), \
+ FN(skc_to_mptcp_sock), \
+ FN(dynptr_from_mem), \
+ FN(ringbuf_reserve_dynptr), \
+ FN(ringbuf_submit_dynptr), \
+ FN(ringbuf_discard_dynptr), \
+ FN(dynptr_read), \
+ FN(dynptr_write), \
+ FN(dynptr_data), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5592,6 +5708,10 @@ struct bpf_tunnel_key {
__u8 tunnel_ttl;
__u16 tunnel_ext; /* Padding, future use. */
__u32 tunnel_label;
+ union {
+ __u32 local_ipv4;
+ __u32 local_ipv6[4];
+ };
};
/* user accessible mirror of in-kernel xfrm_state.
@@ -6486,6 +6606,11 @@ struct bpf_timer {
__u64 :64;
} __attribute__((aligned(8)));
+struct bpf_dynptr {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
struct bpf_sysctl {
__u32 write; /* Sysctl is being read (= 0) or written (= 1).
* Allows 1,2,4-byte read, but no write.
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index b0d8fea1951d..a9162a6c0284 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -33,8 +33,8 @@ struct btf_type {
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
- * bits 24-27: kind (e.g. int, ptr, array...etc)
- * bits 28-30: unused
+ * bits 24-28: kind (e.g. int, ptr, array...etc)
+ * bits 29-30: unused
* bit 31: kind_flag, currently used by
* struct, union and fwd
*/
diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h
index 590f8aea2b6d..439c982f7e81 100644
--- a/include/uapi/linux/can/isotp.h
+++ b/include/uapi/linux/can/isotp.h
@@ -124,18 +124,19 @@ struct can_isotp_ll_options {
/* flags for isotp behaviour */
-#define CAN_ISOTP_LISTEN_MODE 0x001 /* listen only (do not send FC) */
-#define CAN_ISOTP_EXTEND_ADDR 0x002 /* enable extended addressing */
-#define CAN_ISOTP_TX_PADDING 0x004 /* enable CAN frame padding tx path */
-#define CAN_ISOTP_RX_PADDING 0x008 /* enable CAN frame padding rx path */
-#define CAN_ISOTP_CHK_PAD_LEN 0x010 /* check received CAN frame padding */
-#define CAN_ISOTP_CHK_PAD_DATA 0x020 /* check received CAN frame padding */
-#define CAN_ISOTP_HALF_DUPLEX 0x040 /* half duplex error state handling */
-#define CAN_ISOTP_FORCE_TXSTMIN 0x080 /* ignore stmin from received FC */
-#define CAN_ISOTP_FORCE_RXSTMIN 0x100 /* ignore CFs depending on rx stmin */
-#define CAN_ISOTP_RX_EXT_ADDR 0x200 /* different rx extended addressing */
-#define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */
-#define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */
+#define CAN_ISOTP_LISTEN_MODE 0x0001 /* listen only (do not send FC) */
+#define CAN_ISOTP_EXTEND_ADDR 0x0002 /* enable extended addressing */
+#define CAN_ISOTP_TX_PADDING 0x0004 /* enable CAN frame padding tx path */
+#define CAN_ISOTP_RX_PADDING 0x0008 /* enable CAN frame padding rx path */
+#define CAN_ISOTP_CHK_PAD_LEN 0x0010 /* check received CAN frame padding */
+#define CAN_ISOTP_CHK_PAD_DATA 0x0020 /* check received CAN frame padding */
+#define CAN_ISOTP_HALF_DUPLEX 0x0040 /* half duplex error state handling */
+#define CAN_ISOTP_FORCE_TXSTMIN 0x0080 /* ignore stmin from received FC */
+#define CAN_ISOTP_FORCE_RXSTMIN 0x0100 /* ignore CFs depending on rx stmin */
+#define CAN_ISOTP_RX_EXT_ADDR 0x0200 /* different rx extended addressing */
+#define CAN_ISOTP_WAIT_TX_DONE 0x0400 /* wait for tx completion */
+#define CAN_ISOTP_SF_BROADCAST 0x0800 /* 1-to-N functional addressing */
+#define CAN_ISOTP_CF_BROADCAST 0x1000 /* 1-to-N transmission w/o FC */
/* protocol machine default values */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index b897b80770f6..b3d40a5d72ff 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -131,6 +131,11 @@ enum devlink_command {
DEVLINK_CMD_RATE_NEW,
DEVLINK_CMD_RATE_DEL,
+ DEVLINK_CMD_LINECARD_GET, /* can dump */
+ DEVLINK_CMD_LINECARD_SET,
+ DEVLINK_CMD_LINECARD_NEW,
+ DEVLINK_CMD_LINECARD_DEL,
+
/* add new commands above here */
__DEVLINK_CMD_MAX,
DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -338,6 +343,19 @@ enum devlink_reload_limit {
#define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1)
+enum devlink_linecard_state {
+ DEVLINK_LINECARD_STATE_UNSPEC,
+ DEVLINK_LINECARD_STATE_UNPROVISIONED,
+ DEVLINK_LINECARD_STATE_UNPROVISIONING,
+ DEVLINK_LINECARD_STATE_PROVISIONING,
+ DEVLINK_LINECARD_STATE_PROVISIONING_FAILED,
+ DEVLINK_LINECARD_STATE_PROVISIONED,
+ DEVLINK_LINECARD_STATE_ACTIVE,
+
+ __DEVLINK_LINECARD_STATE_MAX,
+ DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1
+};
+
enum devlink_attr {
/* don't change the order or add anything between, this is ABI! */
DEVLINK_ATTR_UNSPEC,
@@ -553,6 +571,11 @@ enum devlink_attr {
DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */
+ DEVLINK_ATTR_LINECARD_INDEX, /* u32 */
+ DEVLINK_ATTR_LINECARD_STATE, /* u8 */
+ DEVLINK_ATTR_LINECARD_TYPE, /* string */
+ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 7bc4b8def12c..e0f0ee9bc89e 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1691,6 +1691,7 @@ enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89,
ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90,
ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91,
+ ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92,
/* must be last entry */
__ETHTOOL_LINK_MODE_MASK_NBITS
};
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 979850221b8d..d2fb4f7be61b 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -338,6 +338,7 @@ enum {
ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */
ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */
ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */
+ ETHTOOL_A_RINGS_TX_PUSH, /* u8 */
/* add new constants above here */
__ETHTOOL_A_RINGS_CNT,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cc284c048e69..5f58dcfe2787 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -211,6 +211,9 @@ struct rtnl_link_stats {
* @rx_nohandler: Number of packets received on the interface
* but dropped by the networking stack because the device is
* not designated to receive packets (e.g. backup link in a bond).
+ *
+ * @rx_otherhost_dropped: Number of packets dropped due to mismatch
+ * in destination MAC address.
*/
struct rtnl_link_stats64 {
__u64 rx_packets;
@@ -243,6 +246,8 @@ struct rtnl_link_stats64 {
__u64 rx_compressed;
__u64 tx_compressed;
__u64 rx_nohandler;
+
+ __u64 rx_otherhost_dropped;
};
/* Subset of link stats useful for in-HW collection. Meaning of the fields is as
@@ -363,6 +368,8 @@ enum {
IFLA_PARENT_DEV_NAME,
IFLA_PARENT_DEV_BUS_NAME,
IFLA_GRO_MAX_SIZE,
+ IFLA_TSO_MAX_SIZE,
+ IFLA_TSO_MAX_SEGS,
__IFLA_MAX
};
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index d4178dace0bf..549ddeaf788b 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -194,6 +194,7 @@ enum {
DEVCONF_IOAM6_ID,
DEVCONF_IOAM6_ID_WIDE,
DEVCONF_NDISC_EVICT_NOCARRIER,
+ DEVCONF_ACCEPT_UNSOLICITED_NA,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h
index c54e6eae5366..75b7257a51e1 100644
--- a/include/uapi/linux/mdio.h
+++ b/include/uapi/linux/mdio.h
@@ -67,6 +67,19 @@
#define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */
#define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */
#define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */
+#define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */
+#define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */
+#define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */
+#define MDIO_PMA_PMD_BT1 18 /* BASE-T1 PMA/PMD extended ability */
+#define MDIO_AN_T1_CTRL 512 /* BASE-T1 AN control */
+#define MDIO_AN_T1_STAT 513 /* BASE-T1 AN status */
+#define MDIO_AN_T1_ADV_L 514 /* BASE-T1 AN advertisement register [15:0] */
+#define MDIO_AN_T1_ADV_M 515 /* BASE-T1 AN advertisement register [31:16] */
+#define MDIO_AN_T1_ADV_H 516 /* BASE-T1 AN advertisement register [47:32] */
+#define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */
+#define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */
+#define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */
+#define MDIO_PMA_PMD_BT1_CTRL 2100 /* BASE-T1 PMA/PMD control register */
/* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */
#define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */
@@ -159,6 +172,7 @@
#define MDIO_PMA_CTRL2_10BT 0x000f /* 10BASE-T type */
#define MDIO_PMA_CTRL2_2_5GBT 0x0030 /* 2.5GBaseT type */
#define MDIO_PMA_CTRL2_5GBT 0x0031 /* 5GBaseT type */
+#define MDIO_PMA_CTRL2_BASET1 0x003D /* BASE-T1 type */
#define MDIO_PCS_CTRL2_TYPE 0x0003 /* PCS type selection */
#define MDIO_PCS_CTRL2_10GBR 0x0000 /* 10GBASE-R type */
#define MDIO_PCS_CTRL2_10GBX 0x0001 /* 10GBASE-X type */
@@ -212,6 +226,7 @@
#define MDIO_PMA_EXTABLE_1000BKX 0x0040 /* 1000BASE-KX ability */
#define MDIO_PMA_EXTABLE_100BTX 0x0080 /* 100BASE-TX ability */
#define MDIO_PMA_EXTABLE_10BT 0x0100 /* 10BASE-T ability */
+#define MDIO_PMA_EXTABLE_BT1 0x0800 /* BASE-T1 ability */
#define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */
/* PHY XGXS lane state register. */
@@ -268,6 +283,66 @@
#define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */
#define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */
+/* 10BASE-T1L PMA control */
+#define MDIO_PMA_10T1L_CTRL_LB_EN 0x0001 /* Enable loopback mode */
+#define MDIO_PMA_10T1L_CTRL_EEE_EN 0x0400 /* Enable EEE mode */
+#define MDIO_PMA_10T1L_CTRL_LOW_POWER 0x0800 /* Low-power mode */
+#define MDIO_PMA_10T1L_CTRL_2V4_EN 0x1000 /* Enable 2.4 Vpp operating mode */
+#define MDIO_PMA_10T1L_CTRL_TX_DIS 0x4000 /* Transmit disable */
+#define MDIO_PMA_10T1L_CTRL_PMA_RST 0x8000 /* MA reset */
+
+/* 10BASE-T1L PMA status register. */
+#define MDIO_PMA_10T1L_STAT_LINK 0x0001 /* PMA receive link up */
+#define MDIO_PMA_10T1L_STAT_FAULT 0x0002 /* Fault condition detected */
+#define MDIO_PMA_10T1L_STAT_POLARITY 0x0004 /* Receive polarity is reversed */
+#define MDIO_PMA_10T1L_STAT_RECV_FAULT 0x0200 /* Able to detect fault on receive path */
+#define MDIO_PMA_10T1L_STAT_EEE 0x0400 /* PHY has EEE ability */
+#define MDIO_PMA_10T1L_STAT_LOW_POWER 0x0800 /* PMA has low-power ability */
+#define MDIO_PMA_10T1L_STAT_2V4_ABLE 0x1000 /* PHY has 2.4 Vpp operating mode ability */
+#define MDIO_PMA_10T1L_STAT_LB_ABLE 0x2000 /* PHY has loopback ability */
+
+/* 10BASE-T1L PCS control register. */
+#define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */
+#define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */
+
+/* BASE-T1 PMA/PMD extended ability register. */
+#define MDIO_PMA_PMD_BT1_B10L_ABLE 0x0004 /* 10BASE-T1L Ability */
+
+/* BASE-T1 auto-negotiation advertisement register [15:0] */
+#define MDIO_AN_T1_ADV_L_PAUSE_CAP ADVERTISE_PAUSE_CAP
+#define MDIO_AN_T1_ADV_L_PAUSE_ASYM ADVERTISE_PAUSE_ASYM
+#define MDIO_AN_T1_ADV_L_FORCE_MS 0x1000 /* Force Master/slave Configuration */
+#define MDIO_AN_T1_ADV_L_REMOTE_FAULT ADVERTISE_RFAULT
+#define MDIO_AN_T1_ADV_L_ACK ADVERTISE_LPACK
+#define MDIO_AN_T1_ADV_L_NEXT_PAGE_REQ ADVERTISE_NPAGE
+
+/* BASE-T1 auto-negotiation advertisement register [31:16] */
+#define MDIO_AN_T1_ADV_M_B10L 0x4000 /* device is compatible with 10BASE-T1L */
+#define MDIO_AN_T1_ADV_M_MST 0x0010 /* advertise master preference */
+
+/* BASE-T1 auto-negotiation advertisement register [47:32] */
+#define MDIO_AN_T1_ADV_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level Transmit Request */
+#define MDIO_AN_T1_ADV_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level Transmit Ability */
+
+/* BASE-T1 AN LP Base Page ability register [15:0] */
+#define MDIO_AN_T1_LP_L_PAUSE_CAP LPA_PAUSE_CAP
+#define MDIO_AN_T1_LP_L_PAUSE_ASYM LPA_PAUSE_ASYM
+#define MDIO_AN_T1_LP_L_FORCE_MS 0x1000 /* LP Force Master/slave Configuration */
+#define MDIO_AN_T1_LP_L_REMOTE_FAULT LPA_RFAULT
+#define MDIO_AN_T1_LP_L_ACK LPA_LPACK
+#define MDIO_AN_T1_LP_L_NEXT_PAGE_REQ LPA_NPAGE
+
+/* BASE-T1 AN LP Base Page ability register [31:16] */
+#define MDIO_AN_T1_LP_M_MST 0x0010 /* LP master preference */
+#define MDIO_AN_T1_LP_M_B10L 0x4000 /* LP is compatible with 10BASE-T1L */
+
+/* BASE-T1 AN LP Base Page ability register [47:32] */
+#define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */
+#define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */
+
+/* BASE-T1 PMA/PMD control register */
+#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */
+
/* EEE Supported/Advertisement/LP Advertisement registers.
*
* EEE capability Register (3.20), Advertisement (7.60) and
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index 9690efedb5fa..921963589904 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -55,6 +55,9 @@ enum {
MPTCP_PM_ATTR_ADDR, /* nested address */
MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */
MPTCP_PM_ATTR_SUBFLOWS, /* u32 */
+ MPTCP_PM_ATTR_TOKEN, /* u32 */
+ MPTCP_PM_ATTR_LOC_ID, /* u8 */
+ MPTCP_PM_ATTR_ADDR_REMOTE, /* nested address */
__MPTCP_PM_ATTR_MAX
};
@@ -93,6 +96,10 @@ enum {
MPTCP_PM_CMD_SET_LIMITS,
MPTCP_PM_CMD_GET_LIMITS,
MPTCP_PM_CMD_SET_FLAGS,
+ MPTCP_PM_CMD_ANNOUNCE,
+ MPTCP_PM_CMD_REMOVE,
+ MPTCP_PM_CMD_SUBFLOW_CREATE,
+ MPTCP_PM_CMD_SUBFLOW_DESTROY,
__MPTCP_PM_CMD_AFTER_LAST
};
@@ -188,6 +195,7 @@ enum mptcp_event_attr {
MPTCP_ATTR_IF_IDX, /* s32 */
MPTCP_ATTR_RESET_REASON,/* u32 */
MPTCP_ATTR_RESET_FLAGS, /* u32 */
+ MPTCP_ATTR_SERVER_SIDE, /* u8 */
__MPTCP_ATTR_AFTER_LAST
};
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index db05fb55055e..39c565e460c7 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -32,6 +32,8 @@ enum {
NDA_NH_ID,
NDA_FDB_EXT_ATTRS,
NDA_FLAGS_EXT,
+ NDA_NDM_STATE_MASK,
+ NDA_NDM_FLAGS_MASK,
__NDA_MAX
};
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 4c0cde075c27..855dffb4c1c3 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -72,6 +72,7 @@ struct nlmsghdr {
/* Modifiers to DELETE request */
#define NLM_F_NONREC 0x100 /* Do not delete recursively */
+#define NLM_F_BULK 0x200 /* Delete multiple objects */
/* Flags for ACK message */
#define NLM_F_CAPPED 0x100 /* request was capped */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 0568a79097b8..d9490e3062a7 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3175,6 +3175,8 @@ enum nl80211_attrs {
NL80211_ATTR_EHT_CAPABILITY,
+ NL80211_ATTR_DISABLE_EHT,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 404f97fb239c..9a2ee1e39fad 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -587,6 +587,8 @@ enum {
TCA_FLOWER_KEY_HASH, /* u32 */
TCA_FLOWER_KEY_HASH_MASK, /* u32 */
+ TCA_FLOWER_KEY_NUM_OF_VLANS, /* u8 */
+
__TCA_FLOWER_MAX,
};
diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
index 800e93377218..6cb6101208d0 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -29,6 +29,7 @@
#define SKBEDIT_F_PTYPE 0x8
#define SKBEDIT_F_MASK 0x10
#define SKBEDIT_F_INHERITDSFIELD 0x20
+#define SKBEDIT_F_TXQ_SKBHASH 0x40
struct tc_skbedit {
tc_gen;
@@ -45,6 +46,7 @@ enum {
TCA_SKBEDIT_PTYPE,
TCA_SKBEDIT_MASK,
TCA_SKBEDIT_FLAGS,
+ TCA_SKBEDIT_QUEUE_MAPPING_MAX,
__TCA_SKBEDIT_MAX
};
#define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index 4dfc05651c98..c00adf2fe868 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -43,10 +43,6 @@
#include <linux/tipc.h>
#include <asm/byteorder.h>
-#ifndef __KERNEL__
-#include <arpa/inet.h> /* for ntohs etc. */
-#endif
-
/*
* Configuration
*
@@ -269,33 +265,33 @@ static inline int TLV_OK(const void *tlv, __u16 space)
*/
return (space >= TLV_SPACE(0)) &&
- (ntohs(((struct tlv_desc *)tlv)->tlv_len) <= space);
+ (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_len) <= space);
}
static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type)
{
return TLV_OK(tlv, space) &&
- (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type);
+ (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_type) == exp_type);
}
static inline int TLV_GET_LEN(struct tlv_desc *tlv)
{
- return ntohs(tlv->tlv_len);
+ return __be16_to_cpu(tlv->tlv_len);
}
static inline void TLV_SET_LEN(struct tlv_desc *tlv, __u16 len)
{
- tlv->tlv_len = htons(len);
+ tlv->tlv_len = __cpu_to_be16(len);
}
static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv, __u16 type)
{
- return (ntohs(tlv->tlv_type) == type);
+ return (__be16_to_cpu(tlv->tlv_type) == type);
}
static inline void TLV_SET_TYPE(struct tlv_desc *tlv, __u16 type)
{
- tlv->tlv_type = htons(type);
+ tlv->tlv_type = __cpu_to_be16(type);
}
static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len)
@@ -305,8 +301,8 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len)
tlv_len = TLV_LENGTH(len);
tlv_ptr = (struct tlv_desc *)tlv;
- tlv_ptr->tlv_type = htons(type);
- tlv_ptr->tlv_len = htons(tlv_len);
+ tlv_ptr->tlv_type = __cpu_to_be16(type);
+ tlv_ptr->tlv_len = __cpu_to_be16(tlv_len);
if (len && data) {
memcpy(TLV_DATA(tlv_ptr), data, len);
memset((char *)TLV_DATA(tlv_ptr) + len, 0, TLV_SPACE(len) - tlv_len);
@@ -348,7 +344,7 @@ static inline void *TLV_LIST_DATA(struct tlv_list_desc *list)
static inline void TLV_LIST_STEP(struct tlv_list_desc *list)
{
- __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len));
+ __u16 tlv_space = TLV_ALIGN(__be16_to_cpu(list->tlv_ptr->tlv_len));
list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space);
list->tlv_space -= tlv_space;
@@ -404,9 +400,9 @@ static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags,
msg_len = TCM_LENGTH(data_len);
tcm_hdr = (struct tipc_cfg_msg_hdr *)msg;
- tcm_hdr->tcm_len = htonl(msg_len);
- tcm_hdr->tcm_type = htons(cmd);
- tcm_hdr->tcm_flags = htons(flags);
+ tcm_hdr->tcm_len = __cpu_to_be32(msg_len);
+ tcm_hdr->tcm_type = __cpu_to_be16(cmd);
+ tcm_hdr->tcm_flags = __cpu_to_be16(flags);
if (data_len && data) {
memcpy(TCM_DATA(msg), data, data_len);
memset((char *)TCM_DATA(msg) + data_len, 0, TCM_SPACE(data_len) - msg_len);
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index 5f38be0ec0f3..ac39328eabe7 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -39,6 +39,7 @@
/* TLS socket options */
#define TLS_TX 1 /* Set transmit parameters */
#define TLS_RX 2 /* Set receive parameters */
+#define TLS_TX_ZEROCOPY_SENDFILE 3 /* transmit zerocopy sendfile */
/* Supported versions */
#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF)
@@ -160,6 +161,7 @@ enum {
TLS_INFO_CIPHER,
TLS_INFO_TXCONF,
TLS_INFO_RXCONF,
+ TLS_INFO_ZC_SENDFILE,
__TLS_INFO_MAX,
};
#define TLS_INFO_MAX (__TLS_INFO_MAX - 1)